https://www.opentrain.ai/papers/kcoevo-a-knowledge-graph-augmented-framework-for-evolutionary-code-generation--arxiv-2603.07581/2026-06-17T09:02:20.717Z https://www.opentrain.ai/papers/mawarith-a-dataset-and-benchmark-for-legal-inheritance-reasoning-with-llms--arxiv-2603.07539/2026-06-17T21:44:12.441Z https://www.opentrain.ai/papers/tablemind-an-uncertainty-aware-programmatic-agent-for-tool-augmented-table-reaso--arxiv-2603.07528/2026-06-19T14:26:16.886Z https://www.opentrain.ai/papers/skip-to-the-good-part-representation-structure-inference-time-layer-skipping-in--arxiv-2603.07475/2026-06-15T23:42:01.202Z https://www.opentrain.ai/papers/dial-a-knowledge-grounded-dialect-specific-nl2sql-system--arxiv-2603.07449/2026-06-18T04:22:16.308Z https://www.opentrain.ai/papers/few-tokens-big-leverage-preserving-safety-alignment-by-constraining-safety-token--arxiv-2603.07445/2026-06-17T13:13:15.894Z https://www.opentrain.ai/papers/generalization-in-online-reinforcement-learning-for-mobile-agents--arxiv-2603.07432/2026-06-19T15:28:17.312Z https://www.opentrain.ai/papers/can-large-language-models-keep-up-benchmarking-online-adaptation-to-continual-kn--arxiv-2603.07392/2026-06-16T15:08:34.453Z https://www.opentrain.ai/papers/sok-agentic-retrieval-augmented-generation-rag-taxonomy-architectures-evaluation--arxiv-2603.07379/2026-06-19T15:01:29.346Z https://www.opentrain.ai/papers/the-third-ambition-artificial-intelligence-and-the-science-of-human-behavior--arxiv-2603.07329/2026-06-17T13:16:15.157Z https://www.opentrain.ai/papers/lying-to-win-assessing-llm-deception-through-human-ai-games-and-parallel-world-p--arxiv-2603.07202/2026-06-19T22:46:43.063Z https://www.opentrain.ai/papers/governance-architecture-for-autonomous-agent-systems-threats-framework-and-engin--arxiv-2603.07191/2026-06-17T19:29:23.558Z https://www.opentrain.ai/papers/deep-expert-injection-for-anchoring-retinal-vlms-with-domain-specific-knowledge--arxiv-2603.07131/2026-06-02T02:56:28.201Z https://www.opentrain.ai/papers/enhancing-consistency-of-werewolf-ai-through-dialogue-summarization-and-persona--arxiv-2603.07111/2026-06-15T05:04:25.322Z https://www.opentrain.ai/papers/entropy-aware-on-policy-distillation-of-language-models--arxiv-2603.07079/2026-06-18T15:46:34.110Z https://www.opentrain.ai/papers/language-aware-distillation-for-multilingual-instruction-following-speech-llms-w--arxiv-2603.07025/2026-06-19T04:56:32.411Z https://www.opentrain.ai/papers/autochecklist-composable-pipelines-for-checklist-generation-and-scoring-with-llm--arxiv-2603.07019/2026-06-19T00:14:32.474Z https://www.opentrain.ai/papers/can-safety-emerge-from-weak-supervision-a-systematic-analysis-of-small-language--arxiv-2603.07017/2026-06-19T11:15:17.488Z https://www.opentrain.ai/papers/chart-rl-generalized-chart-comprehension-via-reinforcement-learning-with-verifia--arxiv-2603.06958/2026-06-18T21:58:26.217Z https://www.opentrain.ai/papers/reforming-the-mechanism-editing-reasoning-patterns-in-llms-with-circuit-reshapin--arxiv-2603.06923/2026-06-16T14:59:03.209Z https://www.opentrain.ai/papers/a-dynamic-self-evolving-extraction-system--arxiv-2603.06915/2026-06-17T08:39:43.447Z https://www.opentrain.ai/papers/liecraft-a-multi-agent-framework-for-evaluating-deceptive-capabilities-in-langua--arxiv-2603.06874/2026-06-17T18:11:25.724Z https://www.opentrain.ai/papers/dark-triad-model-organisms-of-misalignment-narrow-fine-tuning-mirrors-human-anti--arxiv-2603.06816/2026-06-17T21:43:01.670Z https://www.opentrain.ai/papers/beyond-rows-to-reasoning-agentic-retrieval-for-multimodal-spreadsheet-understand--arxiv-2603.06503/2026-06-17T21:44:08.069Z https://www.opentrain.ai/papers/cold-steer-steering-large-language-models-via-in-context-one-step-learning-dynam--arxiv-2603.06495/2026-06-20T03:35:46.812Z https://www.opentrain.ai/papers/abductive-reasoning-with-syllogistic-forms-in-large-language-models--arxiv-2603.06428/2026-06-13T01:04:24.385Z https://www.opentrain.ai/papers/from-prompting-to-preference-optimization-a-comparative-study-of-llm-based-autom--arxiv-2603.06424/2026-06-20T08:22:12.362Z https://www.opentrain.ai/papers/evaluation-of-deontic-conditional-reasoning-in-large-language-models-the-case-of--arxiv-2603.06416/2026-06-17T13:19:15.642Z https://www.opentrain.ai/papers/mind-the-gap-pitfalls-of-llm-alignment-with-asian-public-opinion--arxiv-2603.06264/2026-06-18T17:02:45.796Z https://www.opentrain.ai/papers/spot-span-level-pause-of-thought-for-efficient-and-interpretable-latent-reasonin--arxiv-2603.06222/2026-06-08T15:30:54.207Z https://www.opentrain.ai/papers/lit-ragbench-benchmarking-generator-capabilities-of-large-language-models-in-ret--arxiv-2603.06198/2026-06-20T04:15:17.840Z https://www.opentrain.ai/papers/wisdom-of-the-ai-crowd-ai-crowd-for-ground-truth-approximation-in-content-analys--arxiv-2603.06197/2026-06-14T07:00:13.813Z https://www.opentrain.ai/papers/diffusion-language-models-are-natively-length-aware--arxiv-2603.06123/2026-06-18T06:28:53.752Z https://www.opentrain.ai/papers/making-implicit-premises-explicit-in-logical-understanding-of-enthymemes--arxiv-2603.06114/2026-06-18T14:35:34.337Z https://www.opentrain.ai/papers/experiences-build-characters-the-linguistic-origins-and-functional-impact-of-llm--arxiv-2603.06088/2026-06-16T13:44:17.850Z https://www.opentrain.ai/papers/viewfusion-structured-spatial-thinking-chains-for-multi-view-reasoning--arxiv-2603.06024/2026-06-17T15:21:52.053Z https://www.opentrain.ai/papers/masfactory-a-graph-centric-framework-for-orchestrating-llm-based-multi-agent-sys--arxiv-2603.06007/2026-06-20T07:35:16.113Z https://www.opentrain.ai/papers/implicit-style-conditioning-a-structured-style-rewrite-framework-for-low-resourc--arxiv-2603.05933/2026-06-14T21:24:51.745Z https://www.opentrain.ai/papers/x-opd-cross-modal-on-policy-distillation-for-capability-alignment-in-speech-llms--arxiv-2603.24596/2026-06-20T00:27:38.653Z https://www.opentrain.ai/papers/learning-next-action-predictors-from-human-computer-interaction--arxiv-2603.05923/2026-06-18T11:35:14.535Z https://www.opentrain.ai/papers/verchol-grammar-first-tokenization-for-agglutinative-languages--arxiv-2603.05883/2026-06-14T10:52:14.402Z https://www.opentrain.ai/papers/reflexicoder-teaching-large-language-models-to-self-reflect-on-generated-code-an--arxiv-2603.05863/2026-06-20T00:27:30.415Z https://www.opentrain.ai/papers/knowing-without-acting-the-disentangled-geometry-of-safety-mechanisms-in-large-l--arxiv-2603.05773/2026-06-18T14:51:43.946Z https://www.opentrain.ai/papers/depth-charge-jailbreak-large-language-models-from-deep-safety-attention-heads--arxiv-2603.05772/2026-06-18T15:04:13.948Z https://www.opentrain.ai/papers/reasoning-theater-disentangling-model-beliefs-from-chain-of-thought--arxiv-2603.05488/2026-06-19T13:34:01.785Z https://www.opentrain.ai/papers/leveraging-llm-parametric-knowledge-for-fact-checking-without-retrieval--arxiv-2603.05471/2026-06-18T08:30:46.713Z https://www.opentrain.ai/papers/distributed-partial-information-puzzles-examining-common-ground-construction-und--arxiv-2603.05450/2026-06-18T08:37:02.216Z https://www.opentrain.ai/papers/disctt-consensus-guided-self-curriculum-for-efficient-test-time-adaptation-in-re--arxiv-2603.05357/2026-06-18T14:57:31.315Z https://www.opentrain.ai/papers/building-effective-ai-coding-agents-for-the-terminal-scaffolding-harness-context--arxiv-2603.05344/2026-06-19T00:57:01.294Z https://www.opentrain.ai/papers/wavslm-single-stream-speech-language-modeling-via-wavlm-distillation--arxiv-2603.05299/2026-06-18T15:24:33.330Z https://www.opentrain.ai/papers/sarcasmminer-a-dual-track-post-training-framework-for-robust-audio-visual-sarcas--arxiv-2603.05275/2026-06-16T02:35:15.525Z https://www.opentrain.ai/papers/balancing-coverage-and-draft-latency-in-vocabulary-trimming-for-faster-speculati--arxiv-2603.05210/2026-06-16T23:43:22.766Z https://www.opentrain.ai/papers/c2-faith-benchmarking-llm-judges-for-causal-and-coverage-faithfulness-in-chain-o--arxiv-2603.05167/2026-06-19T19:03:49.670Z https://www.opentrain.ai/papers/lbm-hierarchical-large-auto-bidding-model-via-reasoning-and-acting--arxiv-2603.05134/2026-06-18T16:56:25.355Z https://www.opentrain.ai/papers/neuronmoe-neuron-guided-mixture-of-experts-for-efficient-multilingual-llm-extens--arxiv-2603.05046/2026-06-19T23:22:53.400Z https://www.opentrain.ai/papers/survive-at-all-costs-exploring-llm-s-risky-behaviors-under-survival-pressure--arxiv-2603.05028/2026-06-17T17:51:54.393Z https://www.opentrain.ai/papers/s5-shb-agent-society-5-0-enabled-multi-model-agentic-blockchain-framework-for-sm--arxiv-2603.05027/2026-06-18T08:39:25.446Z https://www.opentrain.ai/papers/thaisafetybench-assessing-language-model-safety-in-thai-cultural-contexts--arxiv-2603.04992/2026-06-18T04:38:23.794Z https://www.opentrain.ai/papers/when-weak-llms-speak-with-confidence-preference-alignment-gets-stronger--arxiv-2603.04968/2026-06-19T19:51:28.582Z https://www.opentrain.ai/papers/visionpangu-a-compact-and-fine-grained-multimodal-assistant-with-1-7b-parameters--arxiv-2603.04957/2026-06-18T08:30:36.374Z https://www.opentrain.ai/papers/retrieval-augmented-generation-with-covariate-time-series--arxiv-2603.04951/2026-06-18T13:30:25.465Z https://www.opentrain.ai/papers/ails-ntua-at-semeval-2026-task-10-agentic-llms-for-psycholinguistic-marker-extra--arxiv-2603.04921/2026-06-18T07:49:30.812Z https://www.opentrain.ai/papers/free-lunch-for-pass-k-low-cost-diverse-sampling-for-diffusion-language-models--arxiv-2603.04893/2026-06-19T14:20:25.130Z https://www.opentrain.ai/papers/beyond-the-context-window-a-cost-performance-analysis-of-fact-based-memory-vs-lo--arxiv-2603.04814/2026-06-19T02:36:51.467Z https://www.opentrain.ai/papers/tsembed-unlocking-task-scaling-in-universal-multimodal-embeddings--arxiv-2603.04772/2026-06-19T14:01:19.135Z https://www.opentrain.ai/papers/stacked-from-one-multi-scale-self-injection-for-context-window-extension--arxiv-2603.04759/2026-06-12T08:28:13.387Z https://www.opentrain.ai/papers/dare-aligning-llm-agents-with-the-r-statistical-ecosystem-via-distribution-aware--arxiv-2603.04743/2026-06-18T13:13:31.115Z https://www.opentrain.ai/papers/if-rewardbench-benchmarking-judge-models-for-instruction-following-evaluation--arxiv-2603.04738/2026-06-18T19:23:47.141Z https://www.opentrain.ai/papers/optimizing-language-models-for-crosslingual-knowledge-consistency--arxiv-2603.04678/2026-06-18T08:30:26.434Z https://www.opentrain.ai/papers/using-vision-language-models-to-predict-item-difficulty--arxiv-2603.04670/2026-06-19T00:42:28.345Z https://www.opentrain.ai/papers/vibe-code-bench-evaluating-ai-models-on-end-to-end-web-application-development--arxiv-2603.04601/2026-06-20T03:53:58.241Z https://www.opentrain.ai/papers/taxonrl-reinforcement-learning-with-intermediate-rewards-for-interpretable-fine--arxiv-2603.04380/2026-06-19T00:43:21.330Z https://www.opentrain.ai/papers/world-properties-without-world-models-recovering-spatial-and-temporal-structure--arxiv-2603.04317/2026-06-18T16:56:17.326Z https://www.opentrain.ai/papers/memex-rl-scaling-long-horizon-llm-agents-via-indexed-experience-memory--arxiv-2603.04257/2026-06-17T21:42:36.189Z https://www.opentrain.ai/papers/retrieval-or-representation-reassessing-benchmark-gaps-in-multilingual-and-visua--arxiv-2603.04238/2026-06-19T02:58:29.664Z https://www.opentrain.ai/papers/when-do-language-models-endorse-limitations-on-human-rights-principles--arxiv-2603.04217/2026-06-17T21:44:16.879Z https://www.opentrain.ai/papers/bielik-q2-sharp-a-comparative-study-of-extreme-2-bit-quantization-methods-for-a--arxiv-2603.04162/2026-06-19T15:58:28.419Z https://www.opentrain.ai/papers/traces-of-social-competence-in-large-language-models--arxiv-2603.04161/2026-06-17T04:16:28.183Z https://www.opentrain.ai/papers/beamperl-parameter-efficient-rl-with-verifiable-rewards-specializes-compact-llms--arxiv-2603.04124/2026-06-19T03:00:00.691Z https://www.opentrain.ai/papers/monitoring-emergent-reward-hacking-during-generation-via-internal-activations--arxiv-2603.04069/2026-06-18T11:07:14.953Z https://www.opentrain.ai/papers/who-judges-the-judge-evaluating-llm-as-a-judge-for-french-medical-open-ended-qa--arxiv-2603.04033/2026-06-18T16:56:23.821Z https://www.opentrain.ai/papers/rethinking-role-playing-evaluation-anonymous-benchmarking-and-a-systematic-study--arxiv-2603.03915/2026-06-20T06:36:57.484Z https://www.opentrain.ai/papers/from-threat-intelligence-to-firewall-rules-semantic-relations-in-hybrid-ai-agent--arxiv-2603.03911/2026-06-18T22:49:26.951Z https://www.opentrain.ai/papers/semantic-bridging-domains-pseudo-source-as-test-time-connector--arxiv-2603.03844/2026-06-14T21:46:12.918Z https://www.opentrain.ai/papers/swe-ci-evaluating-agent-capabilities-in-maintaining-codebases-via-continuous-int--arxiv-2603.03823/2026-06-19T17:06:00.100Z https://www.opentrain.ai/papers/moose-star-unlocking-tractable-training-for-scientific-discovery-by-breaking-the--arxiv-2603.03756/2026-06-18T10:10:47.543Z https://www.opentrain.ai/papers/confidence-calibrated-small-large-language-model-collaboration-for-cost-efficien--arxiv-2603.03752/2026-06-19T20:10:12.270Z https://www.opentrain.ai/papers/concur-benchmarking-llms-for-concurrent-code-generation--arxiv-2603.03683/2026-06-19T05:04:57.032Z https://www.opentrain.ai/papers/self-sovereign-agent--arxiv-2604.08551/2026-04-19T21:13:22.364Z https://www.opentrain.ai/papers/mind-unified-inquiry-and-diagnosis-rl-with-criteria-grounded-clinical-supports-f--arxiv-2603.03677/2026-06-17T21:43:12.418Z https://www.opentrain.ai/papers/can-llm-aid-in-solving-constraints-with-inductive-definitions--arxiv-2603.03668/2026-06-20T06:05:44.746Z https://www.opentrain.ai/papers/byteflow-language-modeling-through-adaptive-byte-compression-without-a-tokenizer--arxiv-2603.03583/2026-06-16T07:43:26.821Z https://www.opentrain.ai/papers/build-judge-optimize-a-blueprint-for-continuous-improvement-of-multi-agent-consu--arxiv-2603.03565/2026-06-19T12:42:18.760Z https://www.opentrain.ai/papers/tucano-2-cool-better-open-source-llms-for-portuguese--arxiv-2603.03543/2026-06-20T05:21:12.299Z https://www.opentrain.ai/papers/farther-the-shift-sparser-the-representation-analyzing-ood-mechanisms-in-llms--arxiv-2603.03415/2026-06-18T07:50:28.390Z https://www.opentrain.ai/papers/code2math-can-your-code-agent-effectively-evolve-math-problems-through-explorati--arxiv-2603.03202/2026-06-18T01:49:18.746Z https://www.opentrain.ai/papers/mod-dpo-towards-mitigating-cross-modal-hallucinations-in-omni-llms-using-modalit--arxiv-2603.03192/2026-06-20T09:21:45.024Z https://www.opentrain.ai/papers/agentic-ai-based-coverage-closure-for-formal-verification--arxiv-2603.03147/2026-06-18T16:56:26.432Z https://www.opentrain.ai/papers/tao-attack-toward-advanced-optimization-based-jailbreak-attacks-for-large-langua--arxiv-2603.03081/2026-06-19T11:43:31.790Z https://www.opentrain.ai/papers/privmedchat-end-to-end-differentially-private-rlhf-for-medical-dialogue-systems--arxiv-2603.03054/2026-06-19T03:01:46.947Z https://www.opentrain.ai/papers/mabert-a-padding-safe-interleaved-transformer-mamba-hybrid-encoder-for-efficient--arxiv-2603.03001/2026-06-19T20:26:22.689Z https://www.opentrain.ai/papers/contextualized-privacy-defense-for-llm-agents--arxiv-2603.02983/2026-06-19T11:15:21.425Z https://www.opentrain.ai/papers/learning-to-generate-and-extract-a-multi-agent-collaboration-framework-for-zero--arxiv-2603.02909/2026-06-18T16:56:45.174Z https://www.opentrain.ai/papers/eval4sim-an-evaluation-framework-for-persona-simulation--arxiv-2603.02876/2026-06-19T06:54:18.245Z https://www.opentrain.ai/papers/a-browser-based-open-source-assistant-for-multimodal-content-verification--arxiv-2603.02842/2026-06-18T04:53:46.382Z https://www.opentrain.ai/papers/ocr-or-not-rethinking-document-information-extraction-in-the-mllms-era-with-real--arxiv-2603.02789/2026-06-20T05:13:41.366Z https://www.opentrain.ai/papers/benchmark-of-benchmarks-unpacking-influence-and-code-repository-quality-in-llm-s--arxiv-2603.04459/2026-06-18T09:15:41.056Z https://www.opentrain.ai/papers/sensory-aware-sequential-recommendation-via-review-distilled-representations--arxiv-2603.02709/2026-06-09T17:23:01.921Z https://www.opentrain.ai/papers/graph-grpo-stabilizing-multi-agent-topology-learning-via-group-relative-policy-o--arxiv-2603.02701/2026-06-19T19:04:02.028Z https://www.opentrain.ai/papers/itlc-at-semeval-2026-task-11-normalization-and-deterministic-parsing-for-formal--arxiv-2603.02676/2026-06-20T00:27:48.810Z https://www.opentrain.ai/papers/real-time-generation-of-game-video-commentary-with-multimodal-llms-pause-aware-d--arxiv-2603.02655/2026-06-19T03:02:41.194Z https://www.opentrain.ai/papers/stitchcuda-an-automated-multi-agents-end-to-end-gpu-programing-framework-with-ru--arxiv-2603.02637/2026-06-20T07:20:34.232Z https://www.opentrain.ai/papers/cross-family-speculative-prefill-training-free-long-context-compression-with-sma--arxiv-2603.02631/2026-06-19T03:02:16.141Z https://www.opentrain.ai/papers/think-but-don-t-overthink-reproducing-recursive-language-models--arxiv-2603.02615/2026-06-20T07:55:17.324Z https://www.opentrain.ai/papers/muse-a-run-centric-platform-for-multimodal-unified-safety-evaluation-of-large-la--arxiv-2603.02482/2026-06-19T22:17:28.643Z https://www.opentrain.ai/papers/detecting-ai-generated-essays-in-writing-assessment-responsible-use-and-generali--arxiv-2603.02353/2026-06-19T23:23:12.934Z https://www.opentrain.ai/papers/characterizing-memorization-in-diffusion-language-models-generalized-extraction--arxiv-2603.02333/2026-06-16T23:19:49.908Z https://www.opentrain.ai/papers/reasoning-core-a-scalable-procedural-data-generation-suite-for-symbolic-pre-trai--arxiv-2603.02208/2026-06-19T22:59:43.795Z https://www.opentrain.ai/papers/organizing-orchestrating-and-benchmarking-agent-skills-at-ecosystem-scale--arxiv-2603.02176/2026-06-19T12:37:53.400Z https://www.opentrain.ai/papers/llms-as-strategic-actors-behavioral-alignment-risk-calibration-and-argumentation--arxiv-2603.02128/2026-06-18T12:53:26.253Z https://www.opentrain.ai/papers/recursive-think-answer-process-for-llms-and-vlms--arxiv-2603.02099/2026-06-18T17:43:46.814Z https://www.opentrain.ai/papers/clinconsensus-a-consensus-based-benchmark-for-evaluating-chinese-medical-llms-ac--arxiv-2603.02097/2026-06-19T02:59:29.259Z https://www.opentrain.ai/papers/learning-from-synthetic-data-improves-multi-hop-reasoning--arxiv-2603.02091/2026-06-19T15:56:28.730Z https://www.opentrain.ai/papers/gendb-the-next-generation-of-query-processing-synthesized-not-engineered--arxiv-2603.02081/2026-06-19T00:37:32.761Z https://www.opentrain.ai/papers/exploring-plan-space-through-conversation-an-agentic-framework-for-llm-mediated--arxiv-2603.02070/2026-06-19T15:43:40.372Z https://www.opentrain.ai/papers/estllm-enhancing-estonian-capabilities-in-multilingual-llms-via-continued-pretra--arxiv-2603.02041/2026-06-17T21:34:51.569Z https://www.opentrain.ai/papers/learning-to-read-where-to-look-disease-aware-vision-language-pretraining-for-3d--arxiv-2603.02026/2026-06-18T08:36:13.220Z https://www.opentrain.ai/papers/mmr-life-piecing-together-real-life-scenes-for-multimodal-multi-image-reasoning--arxiv-2603.02024/2026-06-19T18:55:43.614Z https://www.opentrain.ai/papers/according-to-me-long-term-personalized-referential-memory-qa--arxiv-2603.01990/2026-06-18T14:56:22.051Z https://www.opentrain.ai/papers/amemgym-interactive-memory-benchmarking-for-assistants-in-long-horizon-conversat--arxiv-2603.01966/2026-06-19T02:47:30.733Z https://www.opentrain.ai/papers/semantic-similarity-is-a-spurious-measure-of-comic-understanding-lessons-learned--arxiv-2603.01950/2026-06-14T10:46:44.344Z https://www.opentrain.ai/papers/efficient-rlvr-training-via-weighted-mutual-information-data-selection--arxiv-2603.01907/2026-06-19T02:21:56.550Z https://www.opentrain.ai/papers/kdflow-a-user-friendly-and-efficient-knowledge-distillation-framework-for-large--arxiv-2603.01875/2026-06-18T08:31:25.354Z https://www.opentrain.ai/papers/let-the-agent-search-autonomous-exploration-beats-rigid-workflows-in-temporal-qu--arxiv-2603.01853/2026-06-18T16:56:16.209Z https://www.opentrain.ai/papers/alter-asymmetric-lora-for-token-entropy-guided-unlearning-of-llms--arxiv-2603.01792/2026-06-18T16:56:42.388Z https://www.opentrain.ai/papers/freeact-freeing-activations-for-llm-quantization--arxiv-2603.01776/2026-06-19T14:27:04.688Z https://www.opentrain.ai/papers/topocurate-modeling-interaction-topology-for-tool-use-agent-training--arxiv-2603.01714/2026-06-19T23:23:35.885Z https://www.opentrain.ai/papers/surgical-post-training-cutting-errors-keeping-knowledge--arxiv-2603.01683/2026-06-17T20:25:30.713Z https://www.opentrain.ai/papers/graph-of-mark-promote-spatial-reasoning-in-multimodal-language-models-with-graph--arxiv-2603.06663/2026-06-18T09:12:15.032Z https://www.opentrain.ai/papers/lexchronos-an-agentic-framework-for-structured-event-timeline-extraction-in-indi--arxiv-2603.01651/2026-06-18T08:58:29.557Z https://www.opentrain.ai/papers/learning-to-draft-adaptive-speculative-decoding-with-reinforcement-learning--arxiv-2603.01639/2026-06-17T06:56:16.145Z https://www.opentrain.ai/papers/anatomy-of-the-modality-gap-dissecting-the-internal-states-of-end-to-end-speech--arxiv-2603.01502/2026-06-20T01:25:06.311Z https://www.opentrain.ai/papers/protrlsearch-a-multi-round-multimodal-protein-search-agent-with-large-language-m--arxiv-2603.01464/2026-06-05T06:49:24.707Z https://www.opentrain.ai/papers/from-verbatim-to-gist-distilling-pyramidal-multimodal-memory-via-semantic-inform--arxiv-2603.01455/2026-06-18T01:54:12.737Z https://www.opentrain.ai/papers/enhancing-persona-following-at-decoding-time-via-dynamic-importance-estimation-f--arxiv-2603.01438/2026-03-31T22:59:46.382Z https://www.opentrain.ai/papers/understanding-the-physics-of-key-value-cache-compression-for-llms-through-attent--arxiv-2603.01426/2026-06-03T14:23:33.482Z https://www.opentrain.ai/papers/laser-internalizing-explicit-reasoning-into-latent-space-for-dense-retrieval--arxiv-2603.01425/2026-06-18T04:23:39.359Z https://www.opentrain.ai/papers/toward-graph-tokenizing-large-language-models-with-reconstructive-graph-instruct--arxiv-2603.01385/2026-06-17T07:55:14.976Z https://www.opentrain.ai/papers/pancanbench-a-comprehensive-benchmark-for-evaluating-large-language-models-in-pa--arxiv-2603.01343/2026-06-17T21:30:10.279Z https://www.opentrain.ai/papers/metastate-persistent-working-memory-for-discrete-diffusion-language-models--arxiv-2603.01331/2026-06-19T20:52:31.896Z https://www.opentrain.ai/papers/learn-hard-problems-during-rl-with-reference-guided-fine-tuning--arxiv-2603.01223/2026-06-16T20:36:27.052Z https://www.opentrain.ai/papers/reasoning-boosts-opinion-alignment-in-llms--arxiv-2603.01214/2026-06-16T14:18:52.322Z https://www.opentrain.ai/papers/groupgpt-a-token-efficient-and-privacy-preserving-agentic-framework-for-multi-us--arxiv-2603.01059/2026-06-20T07:45:47.176Z https://www.opentrain.ai/papers/mc-search-evaluating-and-enhancing-multimodal-agentic-search-with-structured-lon--arxiv-2603.00873/2026-06-18T15:26:23.701Z https://www.opentrain.ai/papers/ppc-mt-parallel-point-cloud-completion-with-mamba-transformer-hybrid-architectur--arxiv-2603.00870/2026-06-18T06:42:24.381Z https://www.opentrain.ai/papers/medgpt-oss-training-a-general-purpose-vision-language-model-for-biomedicine--arxiv-2603.00842/2026-06-17T23:56:33.867Z https://www.opentrain.ai/papers/constitutional-black-box-monitoring-for-scheming-in-llm-agents--arxiv-2603.00829/2026-06-18T15:43:23.177Z https://www.opentrain.ai/papers/qwen3-coder-next-technical-report--arxiv-2603.00729/2026-06-20T07:40:25.534Z https://www.opentrain.ai/papers/rlar-an-agentic-reward-system-for-multi-task-reinforcement-learning-on-large-lan--arxiv-2603.00724/2026-06-19T22:02:31.807Z https://www.opentrain.ai/papers/ravel-reasoning-agents-for-validating-and-evaluating-llm-text-synthesis--arxiv-2603.00686/2026-06-20T05:52:17.028Z https://www.opentrain.ai/papers/bluff-benchmarking-the-detection-of-false-and-synthetic-content-across-58-low-re--arxiv-2603.00634/2026-06-19T03:41:25.661Z https://www.opentrain.ai/papers/tracesir-a-multi-agent-framework-for-structured-analysis-and-reporting-of-agenti--arxiv-2603.00623/2026-06-18T17:11:44.889Z https://www.opentrain.ai/papers/from-literature-to-hypotheses-an-ai-co-scientist-system-for-biomarker-guided-dru--arxiv-2603.00612/2026-06-17T11:19:42.021Z https://www.opentrain.ai/papers/langgap-diagnosing-and-closing-the-language-gap-in-vision-language-action-models--arxiv-2603.00592/2026-06-15T10:52:19.173Z https://www.opentrain.ai/papers/super-research-answering-highly-complex-questions-with-large-language-models-thr--arxiv-2603.00582/2026-06-17T08:38:38.277Z https://www.opentrain.ai/papers/draft-thinking-learning-efficient-reasoning-in-long-chain-of-thought-llms--arxiv-2603.00578/2026-06-18T02:14:26.250Z https://www.opentrain.ai/papers/comol-efficient-mixture-of-lora-experts-via-dynamic-core-space-merging--arxiv-2603.00573/2026-06-18T01:40:53.700Z https://www.opentrain.ai/papers/rtlocating-intent-aware-rtl-localization-for-hardware-design-iteration--arxiv-2603.00434/2026-06-16T14:51:22.404Z https://www.opentrain.ai/papers/llm-bootstrapped-targeted-finding-guidance-for-factual-mllm-based-medical-report--arxiv-2603.00426/2026-06-18T13:17:16.213Z https://www.opentrain.ai/papers/distribution-aware-companding-quantization-of-large-language-models--arxiv-2603.00364/2026-06-18T00:18:28.906Z https://www.opentrain.ai/papers/transformers-remember-first-forget-last-dual-process-interference-in-llms--arxiv-2603.00270/2026-06-18T09:38:43.667Z https://www.opentrain.ai/papers/do-llms-benefit-from-their-own-words--arxiv-2602.24287/2026-06-17T22:22:12.118Z https://www.opentrain.ai/papers/controllable-reasoning-models-are-private-thinkers--arxiv-2602.24210/2026-06-19T19:13:46.791Z https://www.opentrain.ai/papers/uncertainty-quantification-for-multimodal-large-language-models-with-incoherence--arxiv-2602.24195/2026-06-16T07:31:37.654Z https://www.opentrain.ai/papers/task-centric-acceleration-of-small-language-models--arxiv-2602.24174/2026-06-15T22:07:39.066Z https://www.opentrain.ai/papers/argllm-app-an-interactive-system-for-argumentative-reasoning-with-large-language--arxiv-2602.24172/2026-06-17T08:11:08.361Z https://www.opentrain.ai/papers/toward-guarantees-for-clinical-reasoning-in-vision-language-models-via-formal-ve--arxiv-2602.24111/2026-06-15T07:45:02.362Z https://www.opentrain.ai/papers/recycling-failures-salvaging-exploration-in-rlvr-via-fine-grained-off-policy-gui--arxiv-2602.24110/2026-06-17T20:13:49.931Z https://www.opentrain.ai/papers/preference-packing-efficient-preference-optimization-for-large-language-models--arxiv-2602.24082/2026-06-17T21:30:31.652Z https://www.opentrain.ai/papers/a-novel-hierarchical-multi-agent-system-for-payments-using-llms--arxiv-2602.24068/2026-06-19T06:35:17.331Z https://www.opentrain.ai/papers/task-complexity-matters-an-empirical-study-of-reasoning-in-llms-for-sentiment-an--arxiv-2602.24060/2026-06-20T09:31:16.881Z https://www.opentrain.ai/papers/ref-adv-exploring-mllm-visual-reasoning-in-referring-expression-tasks--arxiv-2602.23898/2026-06-19T10:50:45.175Z https://www.opentrain.ai/papers/lk-losses-direct-acceptance-rate-optimization-for-speculative-decoding--arxiv-2602.23881/2026-05-31T05:50:23.377Z https://www.opentrain.ai/papers/swe-rebench-v2-language-agnostic-swe-task-collection-at-scale--arxiv-2602.23866/2026-06-19T12:05:47.972Z https://www.opentrain.ai/papers/utptrack-towards-simple-and-unified-token-pruning-for-visual-tracking--arxiv-2602.23734/2026-06-17T07:54:45.712Z https://www.opentrain.ai/papers/hidrop-hierarchical-vision-token-reduction-in-mllms-via-late-injection-concave-p--arxiv-2602.23699/2026-06-17T09:09:55.019Z https://www.opentrain.ai/papers/triz-ragner-a-retrieval-augmented-large-language-model-for-triz-aware-named-enti--arxiv-2602.23656/2026-06-20T05:32:15.401Z https://www.opentrain.ai/papers/multi-agent-causal-reasoning-for-suicide-ideation-detection-through-online-conve--arxiv-2602.23577/2026-06-15T12:09:57.860Z https://www.opentrain.ai/papers/idp-accelerator-agentic-document-intelligence-from-extraction-to-compliance-vali--arxiv-2602.23481/2026-06-20T06:15:25.463Z https://www.opentrain.ai/papers/fhirpath-qa-executable-question-answering-over-fhir-electronic-health-records--arxiv-2602.23479/2026-06-19T16:19:50.783Z https://www.opentrain.ai/papers/citeaudit-you-cited-it-but-did-you-read-it-a-benchmark-for-verifying-scientific--arxiv-2602.23452/2026-06-20T01:37:37.131Z https://www.opentrain.ai/papers/truncated-step-level-sampling-with-process-rewards-for-retrieval-augmented-reaso--arxiv-2602.23440/2026-06-17T09:44:23.290Z https://www.opentrain.ai/papers/scale-can-t-overcome-pragmatics-the-impact-of-reporting-bias-on-vision-language--arxiv-2602.23351/2026-05-11T02:47:08.802Z https://www.opentrain.ai/papers/toward-expert-investment-teams-a-multi-agent-llm-system-with-fine-grained-tradin--arxiv-2602.23330/2026-06-18T19:37:12.193Z https://www.opentrain.ai/papers/a-mixture-of-experts-model-for-multimodal-emotion-recognition-in-conversations--arxiv-2602.23300/2026-05-10T02:45:45.653Z https://www.opentrain.ai/papers/cxreasonagent-evidence-grounded-diagnostic-reasoning-agent-for-chest-x-rays--arxiv-2602.23276/2026-06-16T14:05:27.280Z https://www.opentrain.ai/papers/discourse-aware-dual-track-streaming-response-for-low-latency-spoken-dialogue-sy--arxiv-2602.23266/2026-06-17T12:51:25.061Z https://www.opentrain.ai/papers/agentdropoutv2-optimizing-information-flow-in-multi-agent-systems-via-test-time--arxiv-2602.23258/2026-06-17T15:17:29.471Z https://www.opentrain.ai/papers/why-diffusion-language-models-struggle-with-truly-parallel-non-autoregressive-de--arxiv-2602.23225/2026-06-19T11:50:15.475Z https://www.opentrain.ai/papers/innerq-hardware-aware-tuning-free-quantization-of-kv-cache-for-large-language-mo--arxiv-2602.23200/2026-06-16T14:21:17.188Z https://www.opentrain.ai/papers/sc-arena-a-natural-language-benchmark-for-single-cell-reasoning-with-knowledge-a--arxiv-2602.23199/2026-06-18T09:33:13.062Z https://www.opentrain.ai/papers/esaa-event-sourcing-for-autonomous-agents-in-llm-based-software-engineering--arxiv-2602.23193/2026-06-19T20:43:48.341Z https://www.opentrain.ai/papers/dygnrole-modeling-asymmetry-in-dynamic-graphs-with-node-role-oriented-latent-enc--arxiv-2602.23135/2026-05-04T07:16:55.734Z https://www.opentrain.ai/papers/multi-agent-large-language-model-based-emotional-detoxification-through-personal--arxiv-2602.23123/2026-06-19T22:16:35.203Z https://www.opentrain.ai/papers/automated-vulnerability-detection-in-source-code-using-deep-representation-learn--arxiv-2602.23121/2026-06-14T08:45:14.314Z https://www.opentrain.ai/papers/assessing-deanonymization-risks-with-stylometry-assisted-llm-agent--arxiv-2602.23079/2026-06-17T13:11:15.330Z https://www.opentrain.ai/papers/citellm-an-agentic-platform-for-trustworthy-scientific-reference-discovery--arxiv-2602.23075/2026-06-20T09:43:19.759Z https://www.opentrain.ai/papers/residual-koopman-spectral-profiling-for-predicting-and-preventing-transformer-tr--arxiv-2602.22988/2026-06-18T09:20:50.712Z https://www.opentrain.ai/papers/spm-bench-benchmarking-large-language-models-for-scanning-probe-microscopy--arxiv-2602.22971/2026-03-10T11:07:12.372Z https://www.opentrain.ai/papers/mm-neuroonco-a-multimodal-benchmark-and-instruction-dataset-for-mri-based-brain--arxiv-2602.22955/2026-06-16T00:35:22.654Z https://www.opentrain.ai/papers/pmoe-prompting-diverse-experts-together-wins-more-in-visual-adaptation--arxiv-2602.22938/2026-06-20T07:17:22.421Z https://www.opentrain.ai/papers/omnigaia-towards-native-omni-modal-ai-agents--arxiv-2602.22897/2026-06-17T16:19:15.243Z https://www.opentrain.ai/papers/deeppresenter-environment-grounded-reflection-for-agentic-presentation-generatio--arxiv-2602.22839/2026-06-20T07:24:58.749Z https://www.opentrain.ai/papers/hierarchy-of-groups-policy-optimization-for-long-horizon-agentic-tasks--arxiv-2602.22817/2026-06-18T14:35:45.531Z https://www.opentrain.ai/papers/miroflow-towards-high-performance-and-robust-open-source-agent-framework-for-gen--arxiv-2602.22808/2026-06-19T17:09:24.154Z https://www.opentrain.ai/papers/towards-better-rl-training-data-utilization-via-second-order-rollout--arxiv-2602.22765/2026-06-19T11:09:19.152Z https://www.opentrain.ai/papers/know-what-you-know-metacognitive-entropy-calibration-for-verifiable-rl-reasoning--arxiv-2602.22751/2026-06-19T20:35:37.278Z https://www.opentrain.ai/papers/amlris-alignment-aware-masked-learning-for-referring-image-segmentation--arxiv-2602.22740/2026-06-18T14:56:58.425Z https://www.opentrain.ai/papers/agentsentry-mitigating-indirect-prompt-injection-in-llm-agents-via-temporal-caus--arxiv-2602.22724/2026-04-09T20:12:17.639Z https://www.opentrain.ai/papers/rlhfless-serverless-computing-for-efficient-rlhf--arxiv-2602.22718/2026-06-17T13:11:24.561Z https://www.opentrain.ai/papers/sope-spherical-coordinate-based-positional-embedding-for-enhancing-spatial-perce--arxiv-2602.22716/2026-06-19T05:37:28.647Z https://www.opentrain.ai/papers/immaculate-a-practical-llm-auditing-framework-via-verifiable-computation--arxiv-2602.22700/2026-06-18T04:40:25.732Z https://www.opentrain.ai/papers/reinforcing-real-world-service-agents-balancing-utility-and-cost-in-task-oriente--arxiv-2602.22697/2026-04-11T10:50:52.999Z https://www.opentrain.ai/papers/superglasses-benchmarking-vision-language-models-as-intelligent-agents-for-ai-sm--arxiv-2602.22683/2026-06-16T14:03:54.816Z https://www.opentrain.ai/papers/vectorizing-the-trie-efficient-constrained-decoding-for-llm-based-generative-ret--arxiv-2602.22647/2026-06-16T09:37:55.771Z https://www.opentrain.ai/papers/search-p1-path-centric-reward-shaping-for-stable-and-efficient-agentic-rag-train--arxiv-2602.22576/2026-06-19T03:18:37.150Z https://www.opentrain.ai/papers/stable-adaptive-thinking-via-advantage-shaping-and-length-aware-gradient-regulat--arxiv-2602.22556/2026-04-17T16:26:57.136Z https://www.opentrain.ai/papers/rain-merging-a-gradient-free-method-to-enhance-instruction-following-in-large-re--arxiv-2602.22538/2026-06-18T13:16:24.530Z https://www.opentrain.ai/papers/mind-the-gap-in-cultural-alignment-task-aware-culture-management-for-large-langu--arxiv-2602.22475/2026-06-16T14:04:17.384Z https://www.opentrain.ai/papers/bridging-latent-reasoning-and-target-language-generation-via-retrieval-transitio--arxiv-2602.22453/2026-06-16T14:20:36.943Z https://www.opentrain.ai/papers/scaling-in-not-up-testing-thick-citation-context-analysis-with-gpt-5-and-fragile--arxiv-2602.22359/2026-06-18T13:16:45.163Z https://www.opentrain.ai/papers/decoder-based-sense-knowledge-distillation--arxiv-2602.22351/2026-06-17T18:13:13.510Z https://www.opentrain.ai/papers/improving-parametric-knowledge-access-in-reasoning-language-models--arxiv-2602.22193/2026-06-20T00:00:59.138Z https://www.opentrain.ai/papers/gui-libra-training-native-gui-agents-to-reason-and-act-with-action-aware-supervi--arxiv-2602.22190/2026-06-19T17:43:38.809Z https://www.opentrain.ai/papers/decoding-the-hook-a-multimodal-llm-framework-for-analyzing-the-hooking-period-of--arxiv-2602.22299/2026-06-17T13:23:06.016Z https://www.opentrain.ai/papers/dysco-dynamic-attention-scaling-decoding-for-long-context-lms--arxiv-2602.22175/2026-06-17T17:57:57.095Z https://www.opentrain.ai/papers/dynamic-personality-adaptation-in-large-language-models-via-state-machines--arxiv-2602.22157/2026-06-16T14:04:32.258Z https://www.opentrain.ai/papers/indicifeval-a-benchmark-for-verifiable-instruction-following-evaluation-in-14-in--arxiv-2602.22125/2026-06-19T18:47:55.142Z https://www.opentrain.ai/papers/swe-protege-learning-to-selectively-collaborate-with-an-expert-unlocks-small-lan--arxiv-2602.22124/2026-06-17T10:28:55.827Z https://www.opentrain.ai/papers/confidence-driven-multi-scale-model-selection-for-cost-efficient-inference--arxiv-2602.22090/2026-06-18T21:55:46.020Z https://www.opentrain.ai/papers/understanding-artificial-theory-of-mind-perturbed-tasks-and-reasoning-in-large-l--arxiv-2602.22072/2026-06-15T23:19:32.603Z https://www.opentrain.ai/papers/radar-reasoning-as-discrimination-with-aligned-representations-for-llm-based-kno--arxiv-2602.21951/2026-06-18T00:00:41.655Z https://www.opentrain.ai/papers/medsyn-benchmarking-multi-evidence-synthesis-in-complex-clinical-cases-for-multi--arxiv-2602.21950/2026-06-20T09:51:04.985Z https://www.opentrain.ai/papers/large-language-models-are-algorithmically-blind--arxiv-2602.21947/2026-06-18T03:11:46.711Z https://www.opentrain.ai/papers/finreasoning-a-hierarchical-benchmark-for-reliable-financial-research-reporting--arxiv-2603.19254/2026-06-19T12:18:47.946Z https://www.opentrain.ai/papers/explang-improved-exploration-and-exploitation-in-llm-reasoning-with-on-policy-th--arxiv-2602.21887/2026-06-19T05:24:58.224Z https://www.opentrain.ai/papers/dynamicgtr-leveraging-graph-topology-representation-preferences-to-boost-vlm-cap--arxiv-2602.21864/2026-06-16T18:33:52.725Z https://www.opentrain.ai/papers/proactivemobile-a-comprehensive-benchmark-for-boosting-proactive-intelligence-on--arxiv-2602.21858/2026-06-19T15:04:17.885Z https://www.opentrain.ai/papers/distill-and-align-decomposition-for-enhanced-claim-verification--arxiv-2602.21857/2026-06-20T07:21:30.970Z https://www.opentrain.ai/papers/fewmmbench-a-benchmark-for-multimodal-few-shot-learning--arxiv-2602.21854/2026-06-15T07:19:57.519Z https://www.opentrain.ai/papers/docdjinn-controllable-synthetic-document-generation-with-vlms-and-handwriting-di--arxiv-2602.21824/2026-06-12T09:36:32.091Z https://www.opentrain.ai/papers/prompt-architecture-determines-reasoning-quality-a-variable-isolation-study-on-t--arxiv-2602.21814/2026-06-17T08:18:53.712Z https://www.opentrain.ai/papers/d-cot-disciplined-chain-of-thought-learning-for-efficient-reasoning-in-small-lan--arxiv-2602.21786/2026-06-19T11:52:14.964Z https://www.opentrain.ai/papers/explore-on-graph-incentivizing-autonomous-exploration-of-large-language-models-o--arxiv-2602.21728/2026-06-18T18:26:44.876Z https://www.opentrain.ai/papers/two-stage-active-distribution-network-voltage-control-via-llm-rl-collaboration-a--arxiv-2602.21715/2026-06-17T14:10:17.412Z https://www.opentrain.ai/papers/dynamic-multimodal-activation-steering-for-hallucination-mitigation-in-large-vis--arxiv-2602.21704/2026-06-19T10:07:42.652Z https://www.opentrain.ai/papers/hierarchical-llm-based-multi-agent-framework-with-prompt-optimization-for-multi--arxiv-2602.21670/2026-06-19T22:41:40.056Z https://www.opentrain.ai/papers/dwa-kd-dual-space-weighting-and-time-warped-alignment-for-cross-tokenizer-knowle--arxiv-2602.21669/2026-06-18T13:17:17.432Z https://www.opentrain.ai/papers/sparsity-induction-for-accurate-post-training-pruning-of-large-language-models--arxiv-2602.21652/2026-06-16T14:05:03.410Z https://www.opentrain.ai/papers/scalable-multilingual-multimodal-machine-translation-with-speech-text-fusion--arxiv-2602.21646/2026-04-15T21:24:17.691Z https://www.opentrain.ai/papers/rucl-stratified-rubric-based-curriculum-learning-for-multimodal-large-language-m--arxiv-2602.21628/2026-06-19T11:56:27.931Z https://www.opentrain.ai/papers/when-more-is-less-a-systematic-analysis-of-spatial-and-commonsense-information-f--arxiv-2602.21619/2026-03-13T04:20:46.572Z https://www.opentrain.ai/papers/virtual-biopsy-for-intracranial-tumors-diagnosis-on-mri--arxiv-2602.21613/2026-03-12T10:41:30.483Z https://www.opentrain.ai/papers/structurally-aligned-subtask-level-memory-for-software-engineering-agents--arxiv-2602.21611/2026-06-19T06:31:47.839Z https://www.opentrain.ai/papers/arlarena-a-unified-framework-for-stable-agentic-reinforcement-learning--arxiv-2602.21534/2026-06-18T17:19:17.030Z https://www.opentrain.ai/papers/one-brain-omni-modalities-towards-unified-non-invasive-brain-decoding-with-large--arxiv-2602.21522/2026-06-18T21:30:14.529Z https://www.opentrain.ai/papers/beyond-refusal-probing-the-limits-of-agentic-self-correction-for-semantic-sensit--arxiv-2602.21496/2026-06-20T03:48:39.928Z https://www.opentrain.ai/papers/both-ends-count-just-how-good-are-llm-agents-at-text-to-big-sql--arxiv-2602.21480/2026-03-08T19:09:28.468Z https://www.opentrain.ai/papers/vecglypher-unified-vector-glyph-generation-with-language-models--arxiv-2602.21461/2026-04-25T12:33:23.549Z https://www.opentrain.ai/papers/revisiting-text-ranking-in-deep-research--arxiv-2602.21456/2026-06-17T19:02:33.082Z https://www.opentrain.ai/papers/minar-mechanistic-interpretability-for-neural-algorithmic-reasoning--arxiv-2602.21442/2026-06-16T19:16:13.350Z https://www.opentrain.ai/papers/causal-decoding-for-hallucination-resistant-multimodal-large-language-models--arxiv-2602.21441/2026-06-19T17:45:40.165Z https://www.opentrain.ai/papers/overconfident-errors-need-stronger-correction-asymmetric-confidence-penalties-fo--arxiv-2602.21420/2026-06-19T18:33:15.012Z https://www.opentrain.ai/papers/black-box-reliability-certification-for-ai-agents-via-self-consistency-sampling--arxiv-2602.21368/2026-06-17T23:57:24.523Z https://www.opentrain.ai/papers/a-hierarchical-multi-agent-system-for-autonomous-discovery-in-geoscientific-data--arxiv-2602.21351/2026-06-17T17:44:32.381Z https://www.opentrain.ai/papers/toolmath-a-math-tool-benchmark-for-realistic-long-horizon-multi-tool-reasoning--arxiv-2602.21265/2026-06-18T02:01:20.005Z https://www.opentrain.ai/papers/under-the-influence-quantifying-persuasion-and-vigilance-in-large-language-model--arxiv-2602.21262/2026-06-18T12:24:31.011Z https://www.opentrain.ai/papers/merry-semantically-decoupled-evaluation-of-multimodal-emotional-and-role-consist--arxiv-2602.21941/2026-06-18T13:16:38.559Z https://www.opentrain.ai/papers/e-mmkgr-a-unified-multimodal-knowledge-graph-framework-for-e-commerce-applicatio--arxiv-2602.20877/2026-06-19T08:34:18.901Z https://www.opentrain.ai/papers/actor-curator-co-adaptive-curriculum-learning-via-policy-improvement-bandits-for--arxiv-2602.20532/2026-06-18T19:38:32.126Z https://www.opentrain.ai/papers/on-data-engineering-for-scaling-llm-terminal-capabilities--arxiv-2602.21193/2026-06-18T01:58:17.062Z https://www.opentrain.ai/papers/medclipseg-probabilistic-vision-language-adaptation-for-data-efficient-and-gener--arxiv-2602.20423/2026-06-20T04:13:52.883Z https://www.opentrain.ai/papers/a-very-big-video-reasoning-suite--arxiv-2602.20159/2026-06-19T13:35:22.038Z https://www.opentrain.ai/papers/mas-fire-fault-injection-and-reliability-evaluation-for-llm-based-multi-agent-sy--arxiv-2602.19843/2026-06-19T05:17:56.694Z https://www.opentrain.ai/papers/case-aware-llm-as-a-judge-evaluation-for-enterprise-scale-rag-systems--arxiv-2602.20379/2026-06-18T16:48:22.786Z https://www.opentrain.ai/papers/k-search-llm-kernel-generation-via-co-evolving-intrinsic-world-model--arxiv-2602.19128/2026-06-19T06:15:26.249Z https://www.opentrain.ai/papers/regionroute-regional-style-transfer-with-diffusion-model--arxiv-2602.19254/2026-06-18T09:20:17.208Z https://www.opentrain.ai/papers/think-with-grounding-curriculum-reinforced-reasoning-with-video-grounding-for-lo--arxiv-2602.18702/2026-06-20T06:09:19.156Z https://www.opentrain.ai/papers/tag-thinking-with-action-unit-grounding-for-facial-expression-recognition--arxiv-2602.18763/2026-06-19T04:53:54.339Z https://www.opentrain.ai/papers/decoding-as-optimisation-on-the-probability-simplex-from-top-k-to-top-p-nucleus--arxiv-2602.18292/2026-06-19T04:49:46.636Z https://www.opentrain.ai/papers/mira-memory-integrated-reinforcement-learning-agent-with-limited-llm-guidance--arxiv-2602.17930/2026-06-17T11:25:24.072Z https://www.opentrain.ai/papers/arcee-trinity-large-technical-report--arxiv-2602.17004/2026-06-19T15:22:40.123Z https://www.opentrain.ai/papers/sketch2feedback-grammar-in-the-loop-framework-for-rubric-aligned-feedback-on-stu--arxiv-2602.18520/2026-06-19T05:22:18.743Z https://www.opentrain.ai/papers/trojan-horses-in-recruiting-a-red-teaming-case-study-on-indirect-prompt-injectio--arxiv-2602.18514/2026-06-19T05:19:23.363Z https://www.opentrain.ai/papers/megu-machine-guided-unlearning-with-target-feature-disentanglement--arxiv-2602.17088/2026-06-19T04:58:52.436Z https://www.opentrain.ai/papers/retrospective-in-context-learning-for-temporal-credit-assignment-with-large-lang--arxiv-2602.17497/2026-06-19T04:53:19.330Z https://www.opentrain.ai/papers/genezip-region-aware-compression-for-long-context-dna-modeling--arxiv-2602.17739/2026-06-18T19:27:15.674Z https://www.opentrain.ai/papers/stable-asynchrony-variance-controlled-off-policy-rl-for-llms--arxiv-2602.17616/2026-06-18T06:59:40.258Z https://www.opentrain.ai/papers/fine-grained-uncertainty-quantification-for-long-form-language-model-outputs-a-c--arxiv-2602.17431/2026-06-16T17:06:25.414Z https://www.opentrain.ai/papers/team-of-thoughts-efficient-test-time-scaling-of-agentic-systems-through-orchestr--arxiv-2602.16485/2026-06-19T05:19:41.510Z