https://www.opentrain.ai/papers/gem-graph-enhanced-mixture-of-experts-with-react-agents-for-dialogue-state-track--arxiv-2605.04449/2026-06-18T07:21:58.020Z https://www.opentrain.ai/papers/hierarchical-visual-agent-managing-contexts-in-joint-image-text-space-for-advanc--arxiv-2605.04304/2026-06-19T21:53:40.124Z https://www.opentrain.ai/papers/material-database-agent-a-multimodal-agentic-framework-for-scientific-literature--arxiv-2605.04278/2026-06-19T22:02:23.722Z https://www.opentrain.ai/papers/audio-visual-intelligence-in-large-foundation-models--arxiv-2605.04045/2026-06-19T22:19:27.637Z https://www.opentrain.ai/papers/safety-and-accuracy-follow-different-scaling-laws-in-clinical-large-language-mod--arxiv-2605.04039/2026-06-19T22:30:12.535Z https://www.opentrain.ai/papers/openseeker-v2-pushing-the-limits-of-search-agents-with-informative-and-high-diff--arxiv-2605.04036/2026-06-18T22:01:21.530Z https://www.opentrain.ai/papers/awaking-spatial-intelligence-in-unified-multimodal-understanding-and-generation--arxiv-2605.04128/2026-06-19T21:45:51.854Z https://www.opentrain.ai/papers/correct-is-not-enough-training-reasoning-planners-with-executor-grounded-rewards--arxiv-2605.03862/2026-06-19T22:11:13.384Z https://www.opentrain.ai/papers/stream-r1-reliability-perplexity-aware-reward-distillation-for-streaming-video-g--arxiv-2605.03849/2026-06-19T22:15:52.453Z https://www.opentrain.ai/papers/sere-structural-example-retrieval-for-enhancing-llms-in-event-causality-identifi--arxiv-2605.03701/2026-06-19T21:56:16.200Z https://www.opentrain.ai/papers/cascade-case-based-continual-adaptation-for-large-language-models-during-deploym--arxiv-2605.06702/2026-06-19T06:14:31.621Z https://www.opentrain.ai/papers/bit-ua-aaubs-at-archehr-qa-2026-evaluating-open-source-and-proprietary-llms-via--arxiv-2605.03618/2026-06-19T22:17:16.076Z https://www.opentrain.ai/papers/workspace-bench-1-0-benchmarking-ai-agents-on-workspace-tasks-with-large-scale-f--arxiv-2605.03596/2026-06-19T02:35:29.892Z https://www.opentrain.ai/papers/revisiting-graph-tokenizing-large-language-models-a-systematic-evaluation-of-gra--arxiv-2605.03514/2026-06-19T22:14:41.782Z https://www.opentrain.ai/papers/curaview-a-multi-agent-framework-for-medical-hallucination-detection-with-graphr--arxiv-2605.03476/2026-06-19T10:23:47.296Z https://www.opentrain.ai/papers/finer-sql-boosting-small-language-models-for-text-to-sql--arxiv-2605.03465/2026-06-19T22:18:50.169Z https://www.opentrain.ai/papers/exposing-llm-safety-gaps-through-mathematical-encoding-new-attacks-and-systemati--arxiv-2605.03441/2026-06-19T21:55:54.588Z https://www.opentrain.ai/papers/when-to-think-when-to-speak-learning-disclosure-policies-for-llm-reasoning--arxiv-2605.03314/2026-06-19T17:33:37.235Z https://www.opentrain.ai/papers/rldx-1-technical-report--arxiv-2605.03269/2026-06-19T03:36:57.423Z https://www.opentrain.ai/papers/liberating-llm-capabilities-in-full-duplex-speech-models--arxiv-2606.07547/2026-06-19T22:15:20.779Z https://www.opentrain.ai/papers/molmoact2-action-reasoning-models-for-real-world-deployment--arxiv-2605.02881/2026-06-18T13:03:31.034Z https://www.opentrain.ai/papers/reinforcement-learning-for-llm-based-multi-agent-systems-through-orchestration-t--arxiv-2605.02801/2026-06-19T21:52:13.301Z https://www.opentrain.ai/papers/linearizing-vision-transformer-with-test-time-training--arxiv-2605.02772/2026-06-19T21:54:59.876Z https://www.opentrain.ai/papers/perceptual-flow-network-for-visually-grounded-reasoning--arxiv-2605.02730/2026-06-19T21:53:26.281Z https://www.opentrain.ai/papers/academiclaw-when-students-set-challenges-for-ai-agents--arxiv-2605.02661/2026-06-19T22:04:25.434Z https://www.opentrain.ai/papers/grail-a-deep-granularity-hybrid-resonance-framework-for-real-time-agent-discover--arxiv-2605.02489/2026-06-19T12:55:41.646Z https://www.opentrain.ai/papers/the-compliance-trap-how-structural-constraints-degrade-frontier-ai-metacognition--arxiv-2605.02398/2026-06-18T15:09:19.449Z https://www.opentrain.ai/papers/molvibench-evaluating-llms-on-molecular-vibe-coding--arxiv-2605.02351/2026-06-19T22:18:21.049Z https://www.opentrain.ai/papers/physicianbench-evaluating-llm-agents-in-real-world-ehr-environments--arxiv-2605.02240/2026-06-18T22:49:54.521Z https://www.opentrain.ai/papers/enhanced-llm-reasoning-by-optimizing-reward-functions-with-search-driven-reinfor--arxiv-2605.02073/2026-06-19T22:27:42.372Z https://www.opentrain.ai/papers/counting-as-a-minimal-probe-of-language-model-reliability--arxiv-2605.02028/2026-06-19T11:31:47.969Z https://www.opentrain.ai/papers/beyond-semantic-similarity-rethinking-retrieval-for-agentic-search-via-direct-co--arxiv-2605.05242/2026-06-19T16:20:17.824Z https://www.opentrain.ai/papers/the-reasoning-trap-an-information-theoretic-bound-on-closed-system-multi-step-ll--arxiv-2605.01704/2026-06-19T21:58:38.177Z https://www.opentrain.ai/papers/injecting-distributional-awareness-into-mllms-via-reinforcement-learning-for-dee--arxiv-2605.01402/2026-06-19T12:53:41.001Z https://www.opentrain.ai/papers/esarbench-a-benchmark-for-agentic-uav-embodied-search-and-rescue--arxiv-2605.01371/2026-06-19T21:54:44.894Z https://www.opentrain.ai/papers/chain-of-evidence-pixel-level-visual-attribution-for-iterative-retrieval-augment--arxiv-2605.01284/2026-06-19T12:56:19.229Z https://www.opentrain.ai/papers/when-llms-stop-following-steps-a-diagnostic-study-of-procedural-execution-in-lan--arxiv-2605.00817/2026-06-18T06:12:33.305Z https://www.opentrain.ai/papers/persistent-visual-memory-sustaining-perception-for-deep-generation-in-lvlms--arxiv-2605.00814/2026-06-19T21:48:20.111Z https://www.opentrain.ai/papers/let-vit-speak-generative-language-image-pre-training--arxiv-2605.00809/2026-06-19T09:04:41.584Z https://www.opentrain.ai/papers/themis-training-robust-multilingual-code-reward-models-for-flexible-multi-criter--arxiv-2605.00754/2026-06-19T21:50:14.630Z https://www.opentrain.ai/papers/learning-to-act-and-cooperate-for-distributed-black-box-consensus-optimization--arxiv-2605.00691/2026-05-05T18:25:25.453Z https://www.opentrain.ai/papers/unividx-a-unified-multimodal-framework-for-versatile-video-generation-via-diffus--arxiv-2605.00658/2026-06-19T21:46:35.356Z https://www.opentrain.ai/papers/healthcare-ai-gym-for-medical-agents--arxiv-2605.02943/2026-06-19T09:52:53.992Z https://www.opentrain.ai/papers/hierarchical-abstract-tree-for-cross-document-retrieval-augmented-generation--arxiv-2605.00529/2026-06-19T22:04:43.307Z https://www.opentrain.ai/papers/aem-adaptive-entropy-modulation-for-multi-turn-agentic-reinforcement-learning--arxiv-2605.00425/2026-06-19T22:28:39.391Z https://www.opentrain.ai/papers/odysseus-scaling-vlms-to-100-turn-decision-making-in-games-via-reinforcement-lea--arxiv-2605.00347/2026-06-19T21:49:15.292Z https://www.opentrain.ai/papers/rsat-structured-attribution-makes-small-language-models-faithful-table-reasoners--arxiv-2605.00199/2026-06-19T21:51:56.601Z https://www.opentrain.ai/papers/hermes-toward-a-unified-driving-world-model-for-3d-scene-understanding-and-gener--arxiv-2604.28196/2026-06-19T21:52:22.159Z https://www.opentrain.ai/papers/visual-generation-in-the-new-era-an-evolution-from-atomic-mapping-to-agentic-wor--arxiv-2604.28185/2026-06-19T00:00:09.981Z https://www.opentrain.ai/papers/phyco-learning-controllable-physical-priors-for-generative-motion--arxiv-2604.28169/2026-06-19T15:48:39.666Z https://www.opentrain.ai/papers/flashrt-towards-computationally-and-memory-efficient-red-teaming-for-prompt-inje--arxiv-2604.28157/2026-06-19T21:53:25.185Z https://www.opentrain.ai/papers/claw-eval-live-a-live-agent-benchmark-for-evolving-real-world-workflows--arxiv-2604.28139/2026-06-19T21:52:14.251Z https://www.opentrain.ai/papers/mascing-configurable-mixture-of-experts-behavior-via-activation-steering-masks--arxiv-2604.27818/2026-06-18T13:20:45.381Z https://www.opentrain.ai/papers/from-context-to-skills-can-language-models-learn-from-context-skillfully--arxiv-2604.27660/2026-06-19T13:56:44.512Z https://www.opentrain.ai/papers/world2minecraft-occupancy-driven-simulated-scenes-construction--arxiv-2604.27578/2026-06-19T12:54:23.105Z https://www.opentrain.ai/papers/leveraging-verifier-based-reinforcement-learning-in-image-editing--arxiv-2604.27505/2026-06-19T21:54:14.271Z https://www.opentrain.ai/papers/skills-coach-a-self-evolving-skill-optimizer-via-training-free-grpo--arxiv-2604.27488/2026-06-19T09:04:33.137Z https://www.opentrain.ai/papers/interactweb-bench-can-multimodal-agent-escape-blind-execution-in-interactive-web--arxiv-2604.27419/2026-06-19T22:14:26.029Z https://www.opentrain.ai/papers/minicpm-o-4-5-towards-real-time-full-duplex-omni-modal-interaction--arxiv-2604.27393/2026-06-19T11:24:46.391Z https://www.opentrain.ai/papers/compliance-versus-sensibility-on-the-reasoning-controllability-in-large-language--arxiv-2604.27251/2026-06-19T13:56:25.248Z https://www.opentrain.ai/papers/web2bigtable-a-bi-level-multi-agent-llm-system-for-internet-scale-information-se--arxiv-2604.27221/2026-06-18T17:25:14.925Z https://www.opentrain.ai/papers/path-lock-expert-separating-reasoning-mode-in-hybrid-thinking-via-architecture-l--arxiv-2604.27201/2026-06-18T09:55:47.402Z https://www.opentrain.ai/papers/co-evolving-policy-distillation--arxiv-2604.27083/2026-06-19T22:55:15.457Z https://www.opentrain.ai/papers/turning-the-tide-cross-architecture-distillation-for-diffusion-large-language-mo--arxiv-2604.26951/2026-06-19T22:06:43.379Z https://www.opentrain.ai/papers/clawgym-a-scalable-framework-for-building-effective-claw-agents--arxiv-2604.26904/2026-06-19T21:46:54.497Z https://www.opentrain.ai/papers/glm-5v-turbo-toward-a-native-foundation-model-for-multimodal-agents--arxiv-2604.26752/2026-06-19T22:17:42.164Z https://www.opentrain.ai/papers/unified-4d-world-action-modeling-from-video-priors-with-asynchronous-denoising--arxiv-2604.26694/2026-06-19T12:57:21.558Z https://www.opentrain.ai/papers/addressing-performance-saturation-for-llm-rl-via-precise-entropy-curve-control--arxiv-2604.26326/2026-06-19T09:30:43.181Z https://www.opentrain.ai/papers/radio-vipe-online-tightly-coupled-multi-modal-fusion-for-open-vocabulary-semanti--arxiv-2604.26067/2026-06-19T22:11:42.032Z https://www.opentrain.ai/papers/recursive-multi-agent-systems--arxiv-2604.25917/2026-06-19T12:39:22.166Z https://www.opentrain.ai/papers/toward-scalable-terminal-task-synthesis-via-skill-graphs--arxiv-2604.25727/2026-06-18T23:06:59.833Z https://www.opentrain.ai/papers/step-audio-r1-5-technical-report--arxiv-2604.25719/2026-06-19T21:59:47.996Z https://www.opentrain.ai/papers/refinement-via-regeneration-enlarging-modification-space-boosts-image-refinement--arxiv-2604.25636/2026-06-19T21:45:43.477Z https://www.opentrain.ai/papers/a-systematic-post-train-framework-for-video-generation--arxiv-2604.25427/2026-06-19T21:50:04.803Z https://www.opentrain.ai/papers/autoresearchbench-benchmarking-ai-agents-on-complex-scientific-literature-discov--arxiv-2604.25256/2026-06-19T21:47:25.278Z https://www.opentrain.ai/papers/prior-aligned-data-cleaning-for-tabular-foundation-models--arxiv-2604.25154/2026-06-19T21:55:24.078Z https://www.opentrain.ai/papers/fama-failure-aware-meta-agentic-framework-for-open-source-llms-in-interactive-to--arxiv-2604.25135/2026-06-19T22:13:56.423Z https://www.opentrain.ai/papers/nemotron-3-nano-omni-efficient-and-open-multimodal-intelligence--arxiv-2604.24954/2026-06-18T20:46:46.604Z https://www.opentrain.ai/papers/large-language-models-explore-by-latent-distilling--arxiv-2604.24927/2026-06-19T22:21:31.120Z https://www.opentrain.ai/papers/tuna-2-pixel-embeddings-beat-vision-encoders-for-multimodal-understanding-and-ge--arxiv-2604.24763/2026-06-19T23:26:45.094Z https://www.opentrain.ai/papers/world-r1-reinforcing-3d-constraints-for-text-to-video-generation--arxiv-2604.24764/2026-06-19T12:24:17.298Z https://www.opentrain.ai/papers/x2sam-any-segmentation-in-images-and-videos--arxiv-2605.00891/2026-06-19T22:09:53.560Z https://www.opentrain.ai/papers/the-last-human-written-paper-agent-native-research-artifacts--arxiv-2604.24658/2026-06-16T13:50:42.220Z https://www.opentrain.ai/papers/meta-cot-enhancing-granularity-and-generalization-in-image-editing--arxiv-2604.24625/2026-06-18T13:03:35.880Z https://www.opentrain.ai/papers/improving-vision-language-models-with-perception-centric-process-reward-models--arxiv-2604.24583/2026-06-19T18:58:16.026Z https://www.opentrain.ai/papers/programming-with-data-test-driven-data-engineering-for-self-improving-llms-from--arxiv-2604.24819/2026-06-19T14:07:20.141Z https://www.opentrain.ai/papers/zero-to-cad-agentic-synthesis-of-interpretable-cad-programs-at-million-scale-wit--arxiv-2604.24479/2026-06-19T21:52:45.713Z https://www.opentrain.ai/papers/seaevo-advancing-algorithm-discovery-with-strategy-space-evolution--arxiv-2604.24372/2026-06-18T23:20:49.886Z https://www.opentrain.ai/papers/rewarding-the-scientific-process-process-level-reward-modeling-for-agentic-data--arxiv-2604.24198/2026-06-19T21:55:45.827Z https://www.opentrain.ai/papers/from-skill-text-to-skill-structure-the-scheduling-structural-logical-representat--arxiv-2604.24026/2026-06-20T01:38:17.839Z https://www.opentrain.ai/papers/tcod-exploring-temporal-curriculum-in-on-policy-distillation-for-multi-turn-auto--arxiv-2604.24005/2026-06-19T11:13:18.780Z https://www.opentrain.ai/papers/stabilizing-efficient-reasoning-with-step-level-advantage-selection--arxiv-2604.24003/2026-06-19T21:46:30.674Z https://www.opentrain.ai/papers/goclick-lightweight-element-grounding-model-for-autonomous-gui-interaction--arxiv-2604.23941/2026-06-19T22:00:14.200Z https://www.opentrain.ai/papers/tsassistant-a-human-in-the-loop-agentic-framework-for-automated-target-safety-as--arxiv-2604.23938/2026-06-19T03:15:28.706Z https://www.opentrain.ai/papers/prox-e-fine-grained-3d-shape-editing-via-primitive-based-abstractions--arxiv-2604.23774/2026-06-19T21:53:35.134Z https://www.opentrain.ai/papers/pageguide-browser-extension-to-assist-users-in-navigating-a-webpage-and-locating--arxiv-2604.23772/2026-06-19T00:03:46.166Z https://www.opentrain.ai/papers/agentic-fusion-of-large-atomic-and-language-models-to-accelerate-superconductors--arxiv-2604.23758/2026-06-19T22:13:37.587Z https://www.opentrain.ai/papers/industryasseteqa-a-neurosymbolic-operational-intelligence-system-for-embodied-qu--arxiv-2604.23446/2026-06-19T11:24:33.666Z https://www.opentrain.ai/papers/oceanpile-a-large-scale-multimodal-ocean-corpus-for-foundation-models--arxiv-2605.00877/2026-06-19T22:13:23.507Z https://www.opentrain.ai/papers/discovering-agentic-safety-specifications-from-1-bit-danger-signals--arxiv-2604.23210/2026-06-19T21:55:14.191Z https://www.opentrain.ai/papers/how-do-ai-agents-spend-your-money-analyzing-and-predicting-token-consumption-in--arxiv-2604.22750/2026-06-19T15:51:36.297Z https://www.opentrain.ai/papers/aligning-dense-retrievers-with-llm-utility-via-distillationaligning-dense-retrie--arxiv-2604.22722/2026-06-19T17:08:36.638Z https://www.opentrain.ai/papers/thinking-without-words-efficient-latent-reasoning-with-abstract-chain-of-thought--arxiv-2604.22709/2026-06-19T06:19:48.911Z https://www.opentrain.ai/papers/berag-bayesian-ensemble-retrieval-augmented-generation-for-knowledge-based-visua--arxiv-2604.22678/2026-06-19T22:31:21.889Z https://www.opentrain.ai/papers/from-natural-language-to-verified-code-toward-ai-assisted-problem-to-code-genera--arxiv-2604.22601/2026-06-19T12:55:20.584Z https://www.opentrain.ai/papers/learning-evidence-highlighting-for-frozen-llms--arxiv-2604.22565/2026-06-19T22:00:46.412Z https://www.opentrain.ai/papers/solar-rl-semi-online-long-horizon-assignment-reinforcement-learning--arxiv-2604.22558/2026-06-19T21:50:31.891Z https://www.opentrain.ai/papers/controllable-spoken-dialogue-generation-an-llm-driven-grading-system-for-k-12-no--arxiv-2604.22542/2026-06-19T21:49:07.625Z https://www.opentrain.ai/papers/routelmt-learned-sample-routing-for-hybrid-llm-translation-deployment--arxiv-2604.22520/2026-06-19T21:53:47.720Z https://www.opentrain.ai/papers/aggregate-vs-personalized-judges-in-business-idea-evaluation-evidence-from-exper--arxiv-2604.22517/2026-06-19T21:59:30.645Z https://www.opentrain.ai/papers/cgc-compositional-grounded-contrast-for-fine-grained-multi-image-understanding--arxiv-2604.22498/2026-06-19T12:53:54.101Z https://www.opentrain.ai/papers/ssg-logit-balanced-vocabulary-partitioning-for-llm-watermarking--arxiv-2604.22438/2026-06-19T22:12:29.413Z https://www.opentrain.ai/papers/agentsearchbench-a-benchmark-for-ai-agent-search-in-the-wild--arxiv-2604.22436/2026-06-19T21:56:28.518Z https://www.opentrain.ai/papers/introducing-background-temperature-to-characterise-hidden-randomness-in-large-la--arxiv-2604.22411/2026-06-18T23:16:51.678Z https://www.opentrain.ai/papers/selective-contrastive-learning-for-gloss-free-sign-language-translation--arxiv-2604.22374/2026-06-19T21:46:45.180Z https://www.opentrain.ai/papers/cnsl-bench-benchmarking-the-sign-language-understanding-capabilities-of-mllms-on--arxiv-2604.22367/2026-06-19T22:20:36.571Z https://www.opentrain.ai/papers/preference-heads-in-large-language-models-a-mechanistic-framework-for-interpreta--arxiv-2604.22345/2026-06-19T18:41:26.433Z https://www.opentrain.ai/papers/context-fidelity-boosting-enhancing-faithful-generation-through-watermark-inspir--arxiv-2604.22335/2026-06-19T22:24:34.849Z https://www.opentrain.ai/papers/changequery-advancing-remote-sensing-change-analysis-for-natural-and-human-induc--arxiv-2604.22333/2026-06-19T22:08:59.154Z https://www.opentrain.ai/papers/blast-benchmarking-llms-with-asp-based-structured-testing--arxiv-2604.22306/2026-06-19T21:52:42.580Z https://www.opentrain.ai/papers/relevant-relevance-lexical-vectors-for-accurate-legal-text-classification--arxiv-2604.22292/2026-06-19T21:54:02.831Z https://www.opentrain.ai/papers/self-correction-as-feedback-control-error-dynamics-stability-thresholds-and-prom--arxiv-2604.22273/2026-06-19T12:53:42.310Z https://www.opentrain.ai/papers/semantic-error-correction-and-decoding-for-short-block-channel-codes--arxiv-2604.22269/2026-06-19T21:55:43.607Z https://www.opentrain.ai/papers/large-language-models-decide-early-and-explain-later--arxiv-2604.22266/2026-06-19T21:57:28.358Z https://www.opentrain.ai/papers/bridging-the-long-tail-gap-robust-retrieval-augmented-relation-completion-via-mu--arxiv-2604.22261/2026-06-19T21:49:57.414Z https://www.opentrain.ai/papers/tts-prism-a-perceptual-reasoning-and-interpretable-speech-model-for-fine-grained--arxiv-2604.22225/2026-06-19T21:49:29.960Z https://www.opentrain.ai/papers/verbal-confidence-saturation-in-3-9b-open-weight-instruction-tuned-llms-a-pre-re--arxiv-2604.22215/2026-06-19T21:54:55.807Z https://www.opentrain.ai/papers/unisonate-a-unified-model-for-speech-music-and-sound-effect-generation-with-text--arxiv-2604.22209/2026-06-19T22:21:59.731Z https://www.opentrain.ai/papers/behavioral-canaries-auditing-private-retrieved-context-usage-in-rl-fine-tuning--arxiv-2604.22191/2026-06-19T21:47:31.426Z https://www.opentrain.ai/papers/resrank-unifying-retrieval-and-listwise-reranking-via-end-to-end-joint-training--arxiv-2604.22180/2026-06-19T21:56:48.293Z https://www.opentrain.ai/papers/dworldeval-scalable-robotic-policy-evaluation-via-discrete-diffusion-world-model--arxiv-2604.22152/2026-06-19T17:21:30.259Z https://www.opentrain.ai/papers/voice-under-revision-large-language-models-and-the-normalization-of-personal-nar--arxiv-2604.22142/2026-06-19T21:54:41.915Z https://www.opentrain.ai/papers/emergent-strategic-reasoning-risks-in-ai-a-taxonomy-driven-evaluation-framework--arxiv-2604.22119/2026-06-19T22:20:00.626Z https://www.opentrain.ai/papers/sketchvlm-vision-language-models-can-annotate-images-to-explain-thoughts-and-gui--arxiv-2604.22875/2026-06-19T21:46:25.551Z https://www.opentrain.ai/papers/memanto-typed-semantic-memory-with-information-theoretic-retrieval-for-long-hori--arxiv-2604.22085/2026-06-19T09:34:18.080Z https://www.opentrain.ai/papers/outcome-rewards-do-not-guarantee-verifiable-or-causally-important-reasoning--arxiv-2604.22074/2026-06-18T09:37:14.762Z https://www.opentrain.ai/papers/reliability-auditing-for-downstream-llm-tasks-in-psychiatry-llm-generated-hospit--arxiv-2604.22063/2026-06-19T00:54:50.661Z https://www.opentrain.ai/papers/incentivizing-neuro-symbolic-language-based-reasoning-in-vlms-via-reinforcement--arxiv-2604.22062/2026-06-19T04:21:23.531Z https://www.opentrain.ai/papers/lightweight-retrieval-augmented-generation-and-large-language-model-based-modeli--arxiv-2604.22061/2026-06-19T04:22:02.846Z https://www.opentrain.ai/papers/context-unrolling-in-omni-models--arxiv-2604.21921/2026-06-19T04:40:53.243Z https://www.opentrain.ai/papers/when-prompts-override-vision-prompt-induced-hallucinations-in-lvlms--arxiv-2604.21911/2026-06-19T04:18:52.093Z https://www.opentrain.ai/papers/learning-to-communicate-toward-end-to-end-optimization-of-multi-agent-language-s--arxiv-2604.21794/2026-06-18T07:10:54.666Z https://www.opentrain.ai/papers/structmem-structured-memory-for-long-horizon-behavior-in-llms--arxiv-2604.21748/2026-06-19T12:55:53.079Z https://www.opentrain.ai/papers/encoder-free-human-motion-understanding-via-structured-motion-descriptions--arxiv-2604.21668/2026-06-19T04:44:27.060Z https://www.opentrain.ai/papers/process-supervision-via-verbal-critique-improves-reasoning-in-large-language-mod--arxiv-2604.21611/2026-06-19T04:15:37.227Z https://www.opentrain.ai/papers/generalizing-numerical-reasoning-in-table-data-through-operation-sketches-and-se--arxiv-2604.21495/2026-06-19T04:48:30.147Z https://www.opentrain.ai/papers/efficient-agent-evaluation-via-diversity-guided-user-simulation--arxiv-2604.21480/2026-06-19T04:35:38.307Z https://www.opentrain.ai/papers/care-counselor-aligned-response-engine-for-online-mental-health-support--arxiv-2604.21352/2026-06-19T04:43:15.755Z https://www.opentrain.ai/papers/beyond-single-plots-a-benchmark-for-question-answering-on-multi-charts--arxiv-2604.21344/2026-06-19T03:35:28.565Z https://www.opentrain.ai/papers/ideological-bias-in-llms-economic-causal-reasoning--arxiv-2604.21334/2026-06-19T04:25:58.756Z https://www.opentrain.ai/papers/understanding-and-mitigating-spurious-signal-amplification-in-test-time-reinforc--arxiv-2604.21327/2026-06-19T04:49:18.692Z https://www.opentrain.ai/papers/cap-controllable-alignment-prompting-for-unlearning-in-llms--arxiv-2604.21251/2026-06-19T04:39:39.773Z https://www.opentrain.ai/papers/learning-dynamic-representations-and-policies-from-multimodal-clinical-time-seri--arxiv-2604.21235/2026-06-19T04:17:52.771Z https://www.opentrain.ai/papers/trust-but-verify-introducing-davinci-a-framework-for-dual-attribution-and-verifi--arxiv-2604.21193/2026-06-19T04:27:36.576Z https://www.opentrain.ai/papers/breaking-mcp-with-function-hijacking-attacks-novel-threats-for-function-calling--arxiv-2604.20994/2026-06-18T21:00:38.440Z https://www.opentrain.ai/papers/co-evolving-llm-decision-and-skill-bank-agents-for-long-horizon-tasks--arxiv-2604.20987/2026-06-19T04:16:48.529Z https://www.opentrain.ai/papers/llada2-0-uni-unifying-multimodal-understanding-and-generation-with-diffusion-lar--arxiv-2604.20796/2026-06-18T04:23:20.738Z https://www.opentrain.ai/papers/working-memory-constraints-scaffold-learning-in-transformers-under-data-scarcity--arxiv-2604.20789/2026-06-15T14:48:48.507Z https://www.opentrain.ai/papers/compass-continual-multilingual-peft-with-adaptive-semantic-sampling--arxiv-2604.20720/2026-06-19T04:16:17.969Z https://www.opentrain.ai/papers/the-expense-of-seeing-attaining-trustworthy-multimodal-reasoning-within-the-mono--arxiv-2604.20665/2026-06-19T04:27:26.797Z https://www.opentrain.ai/papers/self-aware-vector-embeddings-for-retrieval-augmented-generation-a-neuroscience-i--arxiv-2604.20598/2026-06-19T04:46:44.289Z https://www.opentrain.ai/papers/exploring-spatial-intelligence-from-a-generative-perspective--arxiv-2604.20570/2026-06-19T04:34:57.032Z https://www.opentrain.ai/papers/chasm-unveiling-covert-advertisements-on-chinese-social-media--arxiv-2604.20511/2026-06-18T13:59:46.940Z https://www.opentrain.ai/papers/has-accelerating-rag-through-homology-aware-speculative-retrieval--arxiv-2604.20452/2026-06-19T04:28:16.621Z https://www.opentrain.ai/papers/webgen-r1-incentivizing-large-language-models-to-generate-functional-and-aesthet--arxiv-2604.20398/2026-06-19T04:16:56.916Z https://www.opentrain.ai/papers/hybrid-policy-distillation-for-llms--arxiv-2604.20244/2026-06-19T04:31:58.180Z https://www.opentrain.ai/papers/chasing-the-public-score-user-pressure-and-evaluation-exploitation-in-coding-age--arxiv-2604.20200/2026-06-19T04:18:30.027Z https://www.opentrain.ai/papers/temporally-extended-mixture-of-experts-models--arxiv-2604.20156/2026-06-19T04:18:19.383Z https://www.opentrain.ai/papers/evoagent-an-evolvable-agent-framework-with-skill-learning-and-multi-agent-delega--arxiv-2604.20133/2026-06-19T04:21:41.913Z https://www.opentrain.ai/papers/skilllearnbench-benchmarking-continual-learning-methods-for-agent-skill-generati--arxiv-2604.20087/2026-06-18T04:01:41.187Z https://www.opentrain.ai/papers/bootstrapping-post-training-signals-for-open-ended-tasks-via-rubric-based-self-p--arxiv-2604.20051/2026-06-19T04:42:32.863Z https://www.opentrain.ai/papers/embodiedmidtrain-bridging-the-gap-between-vision-language-models-and-vision-lang--arxiv-2604.20012/2026-04-27T15:36:52.252Z https://www.opentrain.ai/papers/visual-reasoning-through-tool-supervised-reinforcement-learning--arxiv-2604.19945/2026-06-19T04:27:56.942Z https://www.opentrain.ai/papers/creativegame-toward-mechanic-aware-creative-game-generation--arxiv-2604.19926/2026-06-18T13:59:46.223Z https://www.opentrain.ai/papers/mmcore-multimodal-connection-with-representation-aligned-latent-embeddings--arxiv-2604.19902/2026-06-19T04:35:15.658Z https://www.opentrain.ai/papers/anyrecon-arbitrary-view-3d-reconstruction-with-video-diffusion-model--arxiv-2604.19747/2026-06-19T04:27:42.868Z https://www.opentrain.ai/papers/playcoder-making-llm-generated-gui-code-playable--arxiv-2604.19742/2026-06-19T04:38:35.014Z https://www.opentrain.ai/papers/dr-venus-towards-frontier-edge-scale-deep-research-agents-with-only-10k-open-dat--arxiv-2604.19859/2026-06-19T04:29:23.672Z https://www.opentrain.ai/papers/chat2workflow-a-benchmark-for-generating-executable-visual-workflows-with-natura--arxiv-2604.19667/2026-06-19T04:24:39.409Z https://www.opentrain.ai/papers/pause-or-fabricate-training-language-models-for-grounded-reasoning--arxiv-2604.19656/2026-06-18T11:50:51.056Z https://www.opentrain.ai/papers/cointeract-physically-consistent-human-object-interaction-video-synthesis-via-sp--arxiv-2604.19636/2026-06-18T04:26:59.550Z https://www.opentrain.ai/papers/smartphotocrafter-unified-reasoning-generation-and-optimization-for-automatic-ph--arxiv-2604.19587/2026-06-19T12:55:29.148Z https://www.opentrain.ai/papers/a-self-evolving-framework-for-efficient-terminal-agents-via-observational-contex--arxiv-2604.19572/2026-06-19T11:09:40.275Z https://www.opentrain.ai/papers/what-makes-an-llm-a-good-optimizer-a-trajectory-analysis-of-llm-guided-evolution--arxiv-2604.19440/2026-06-19T04:40:32.490Z https://www.opentrain.ai/papers/hp-edit-a-human-preference-post-training-framework-for-image-editing--arxiv-2604.19406/2026-06-19T03:57:33.998Z https://www.opentrain.ai/papers/dash-kv-accelerating-long-context-llm-inference-via-asymmetric-kv-cache-hashing--arxiv-2604.19351/2026-06-19T08:05:29.916Z https://www.opentrain.ai/papers/evaluating-llm-driven-summarisation-of-parliamentary-debates-with-computational--arxiv-2604.19331/2026-06-18T15:09:58.291Z https://www.opentrain.ai/papers/rdp-lora-geometry-driven-identification-for-parameter-efficient-adaptation-in-la--arxiv-2604.19321/2026-06-19T04:15:27.104Z https://www.opentrain.ai/papers/detoxification-for-llm-from-dataset-itself--arxiv-2604.19124/2026-06-17T06:22:03.406Z https://www.opentrain.ai/papers/expert-upcycling-shifting-the-compute-efficient-frontier-of-mixture-of-experts--arxiv-2604.19835/2026-06-19T13:22:22.393Z https://www.opentrain.ai/papers/savoir-learning-social-savoir-faire-via-shapley-based-reward-attribution--arxiv-2604.18982/2026-06-19T04:24:40.452Z https://www.opentrain.ai/papers/ai-scientists-produce-results-without-reasoning-scientifically--arxiv-2604.18805/2026-06-18T14:58:16.958Z https://www.opentrain.ai/papers/mathnet-a-global-multimodal-benchmark-for-mathematical-reasoning-and-retrieval--arxiv-2604.18584/2026-06-19T03:50:32.001Z https://www.opentrain.ai/papers/sessa-selective-state-space-attention--arxiv-2604.18580/2026-04-28T10:59:54.296Z https://www.opentrain.ai/papers/when-can-llms-learn-to-reason-with-weak-supervision--arxiv-2604.18574/2026-06-19T17:21:27.241Z https://www.opentrain.ai/papers/steppo-step-aligned-policy-optimization-for-agentic-reinforcement-learning--arxiv-2604.18401/2026-06-17T06:42:44.474Z https://www.opentrain.ai/papers/river-llm-large-language-model-seamless-exit-based-on-kv-share--arxiv-2604.18396/2026-06-19T04:48:48.341Z https://www.opentrain.ai/papers/opengame-open-agentic-coding-for-games--arxiv-2604.18394/2026-06-19T04:18:47.970Z https://www.opentrain.ai/papers/agent-world-scaling-real-world-environment-synthesis-for-evolving-general-agent--arxiv-2604.18292/2026-06-19T04:39:52.497Z https://www.opentrain.ai/papers/beyond-pattern-matching-seven-cross-domain-techniques-for-prompt-injection-detec--arxiv-2604.18248/2026-06-19T04:41:37.989Z https://www.opentrain.ai/papers/aj-bench-benchmarking-agent-as-a-judge-for-environment-aware-evaluation--arxiv-2604.18240/2026-06-19T04:41:42.602Z https://www.opentrain.ai/papers/webcompass-towards-multimodal-web-coding-evaluation-for-code-language-models--arxiv-2604.18224/2026-06-19T12:18:45.873Z https://www.opentrain.ai/papers/multiplication-in-multimodal-llms-computation-with-text-image-and-audio-inputs--arxiv-2604.18203/2026-06-19T04:33:21.656Z https://www.opentrain.ai/papers/mm-judgebias-a-benchmark-for-evaluating-compositional-biases-in-mllm-as-a-judge--arxiv-2604.18164/2026-06-19T04:19:36.573Z https://www.opentrain.ai/papers/training-llm-agents-for-spontaneous-reward-free-self-evolution-via-world-knowled--arxiv-2604.18131/2026-06-19T04:19:40.468Z https://www.opentrain.ai/papers/unlocking-the-edge-deployment-and-ondevice-acceleration-of-multi-lora-enabled-on--arxiv-2604.18655/2026-06-19T04:28:26.062Z https://www.opentrain.ai/papers/on-the-reliability-of-computer-use-agents--arxiv-2604.17849/2026-06-19T04:20:41.421Z https://www.opentrain.ai/papers/democratizing-tool-learning-with-environments-fully-simulated-by-a-free-8b-langu--arxiv-2604.17739/2026-06-19T04:35:18.328Z https://www.opentrain.ai/papers/screen-before-you-interpret-a-portable-validity-protocol-for-benchmark-based-llm--arxiv-2604.17714/2026-06-18T20:22:51.656Z https://www.opentrain.ai/papers/the-geometric-canary-predicting-steerability-and-detecting-drift-via-representat--arxiv-2604.17698/2026-06-18T19:22:49.967Z https://www.opentrain.ai/papers/stratagem-learning-transferable-reasoning-via-trajectory-modulated-game-self-pla--arxiv-2604.17696/2026-06-19T04:43:40.075Z https://www.opentrain.ai/papers/moe-nd-per-layer-mixture-of-experts-routing-for-multi-axis-kv-cache-compression--arxiv-2604.17695/2026-06-19T04:42:59.886Z https://www.opentrain.ai/papers/agents-explore-but-agents-ignore-llms-lack-environmental-curiosity--arxiv-2604.17609/2026-06-19T04:45:56.638Z https://www.opentrain.ai/papers/terminal-wrench-a-dataset-of-331-reward-hackable-environments-and-3-632-exploit--arxiv-2604.17596/2026-06-19T04:38:43.104Z https://www.opentrain.ai/papers/unigeo-unifying-geometric-guidance-for-camera-controllable-image-editing-via-vid--arxiv-2604.17565/2026-06-19T04:22:34.005Z https://www.opentrain.ai/papers/hsg-hyperbolic-scene-graph--arxiv-2604.17454/2026-06-19T04:34:38.195Z https://www.opentrain.ai/papers/jupiter-n-technical-report--arxiv-2604.17429/2026-06-19T04:23:15.931Z https://www.opentrain.ai/papers/evomaster-a-foundational-agent-framework-for-building-evolving-autonomous-scient--arxiv-2604.17406/2026-06-19T04:28:54.856Z https://www.opentrain.ai/papers/speculative-decoding-for-autoregressive-video-generation--arxiv-2604.17397/2026-06-19T04:38:27.197Z https://www.opentrain.ai/papers/precise-debugging-benchmark-is-your-model-debugging-or-regenerating--arxiv-2604.17338/2026-06-18T08:21:46.170Z https://www.opentrain.ai/papers/when-background-matters-breaking-medical-vision-language-models-by-transferable--arxiv-2604.17318/2026-06-19T04:30:35.092Z https://www.opentrain.ai/papers/cat-dpo-category-adaptive-safety-alignment--arxiv-2604.17299/2026-06-18T14:14:55.638Z https://www.opentrain.ai/papers/llatisa-towards-difficulty-stratified-time-series-reasoning-from-visual-percepti--arxiv-2604.17295/2026-06-19T04:46:41.785Z https://www.opentrain.ai/papers/genericagent-a-token-efficient-self-evolving-llm-agent-via-contextual-informatio--arxiv-2604.17091/2026-06-19T04:26:17.927Z https://www.opentrain.ai/papers/abstain-r1-calibrated-abstention-and-post-refusal-clarification-via-verifiable-r--arxiv-2604.17073/2026-06-19T04:27:18.696Z https://www.opentrain.ai/papers/mnaft-modality-neuron-aware-fine-tuning-of-multimodal-large-language-models-for--arxiv-2604.16943/2026-06-19T04:35:30.328Z https://www.opentrain.ai/papers/easyvideor1-easier-rl-for-video-understanding--arxiv-2604.16893/2026-04-21T09:36:12.230Z https://www.opentrain.ai/papers/the-illusion-of-certainty-decoupling-capability-and-calibration-in-on-policy-dis--arxiv-2604.16830/2026-06-16T13:55:17.977Z https://www.opentrain.ai/papers/repurposing-3d-generative-model-for-autoregressive-layout-generation--arxiv-2604.16299/2026-06-17T12:07:39.493Z https://www.opentrain.ai/papers/vefx-bench-a-holistic-benchmark-for-generic-video-editing-and-visual-effects--arxiv-2604.16272/2026-06-19T04:17:32.316Z https://www.opentrain.ai/papers/atmanrl-towards-faithful-reasoning-via-differentiable-attention-saliency--arxiv-2604.16158/2026-06-19T04:24:47.261Z https://www.opentrain.ai/papers/mind-s-eye-a-benchmark-of-visual-abstraction-transformation-and-composition-for--arxiv-2604.16054/2026-06-19T04:42:52.624Z https://www.opentrain.ai/papers/on-the-robustness-of-llm-based-dense-retrievers-a-systematic-analysis-of-general--arxiv-2604.16576/2026-06-19T04:15:55.911Z https://www.opentrain.ai/papers/neurosymbolic-repo-level-code-localization--arxiv-2604.16021/2026-06-19T04:35:19.639Z https://www.opentrain.ai/papers/hierarchical-codec-diffusion-for-video-to-speech-generation--arxiv-2604.15923/2026-06-18T19:22:35.045Z https://www.opentrain.ai/papers/coevolve-training-llm-agents-via-agent-data-mutual-evolution--arxiv-2604.15840/2026-06-19T04:17:16.198Z https://www.opentrain.ai/papers/qwen3-5-omni-technical-report--arxiv-2604.15804/2026-06-19T12:21:37.671Z https://www.opentrain.ai/papers/kwbench-measuring-unprompted-problem-recognition-in-knowledge-work--arxiv-2604.15760/2026-06-18T19:21:04.897Z https://www.opentrain.ai/papers/gta-2-benchmarking-general-tool-agents-from-atomic-tool-use-to-open-ended-workfl--arxiv-2604.15715/2026-04-20T21:18:46.066Z https://www.opentrain.ai/papers/why-fine-tuning-encourages-hallucinations-and-how-to-fix-it--arxiv-2604.15574/2026-06-19T04:27:57.618Z https://www.opentrain.ai/papers/mm-webagent-a-hierarchical-multimodal-web-agent-for-webpage-generation--arxiv-2604.15309/2026-06-18T21:26:54.307Z https://www.opentrain.ai/papers/rad-2-scaling-reinforcement-learning-in-a-generator-discriminator-framework--arxiv-2604.15308/2026-06-19T04:20:52.002Z https://www.opentrain.ai/papers/generalization-in-llm-problem-solving-the-case-of-the-shortest-path--arxiv-2604.15306/2026-06-18T18:31:34.262Z https://www.opentrain.ai/papers/why-do-vision-language-models-struggle-to-recognize-human-emotions--arxiv-2604.15280/2026-06-19T04:46:13.686Z https://www.opentrain.ai/papers/scaling-test-time-compute-for-agentic-coding--arxiv-2604.16529/2026-06-19T04:22:37.144Z https://www.opentrain.ai/papers/from-tokens-to-steps-verification-aware-speculative-decoding-for-efficient-multi--arxiv-2604.15244/2026-06-16T14:33:37.312Z https://www.opentrain.ai/papers/made-a-living-benchmark-for-multi-label-text-classification-with-uncertainty-qua--arxiv-2604.15203/2026-06-19T04:38:53.984Z https://www.opentrain.ai/papers/scepsy-serving-agentic-workflows-using-aggregate-llm-pipelines--arxiv-2604.15186/2026-06-18T13:16:42.290Z https://www.opentrain.ai/papers/compressing-sequences-in-the-latent-embedding-space-k-token-merging-for-large-la--arxiv-2604.15153/2026-06-19T04:44:42.598Z https://www.opentrain.ai/papers/quantcode-bench-a-benchmark-for-evaluating-the-ability-of-large-language-models--arxiv-2604.15151/2026-06-19T04:18:55.739Z https://www.opentrain.ai/papers/ig-search-step-level-information-gain-rewards-for-search-augmented-reasoning--arxiv-2604.15148/2026-06-19T12:41:30.903Z https://www.opentrain.ai/papers/blinded-multi-rater-comparative-evaluation-of-a-large-language-model-and-clinici--arxiv-2604.15124/2026-06-19T04:44:38.556Z https://www.opentrain.ai/papers/openmobile-building-open-mobile-agents-with-task-and-trajectory-synthesis--arxiv-2604.15093/2026-06-12T09:39:58.165Z https://www.opentrain.ai/papers/autonomous-evolution-of-eda-tools-multi-agent-self-evolved-abc--arxiv-2604.15082/2026-06-19T04:34:48.406Z https://www.opentrain.ai/papers/autogenesis-a-self-evolving-agent-protocol--arxiv-2604.15034/2026-06-19T04:39:30.675Z https://www.opentrain.ai/papers/towards-faster-language-model-inference-using-mixture-of-experts-flow-matching--arxiv-2604.15009/2026-06-17T14:35:31.067Z https://www.opentrain.ai/papers/unidoc-rl-coarse-to-fine-visual-rag-with-hierarchical-actions-and-dense-rewards--arxiv-2604.14967/2026-06-19T04:15:47.974Z https://www.opentrain.ai/papers/rata-tool-retrieval-based-tool-selection-with-multimodal-large-language-models--arxiv-2604.14951/2026-06-18T14:14:22.136Z https://www.opentrain.ai/papers/longact-harnessing-intrinsic-activation-patterns-for-long-context-reinforcement--arxiv-2604.14922/2026-06-19T04:27:47.694Z https://www.opentrain.ai/papers/racer-retrieval-augmented-contextual-rapid-speculative-decoding--arxiv-2604.14885/2026-06-19T04:42:18.033Z https://www.opentrain.ai/papers/modeling-llm-unlearning-as-an-asymmetric-two-task-learning-problem--arxiv-2604.14808/2026-06-19T04:28:53.478Z https://www.opentrain.ai/papers/is-this-edit-correct-a-multi-dimensional-benchmark-for-reasoning-aware-image-edi--arxiv-2606.05172/2026-06-19T04:21:46.572Z https://www.opentrain.ai/papers/dr-3-eval-towards-realistic-and-reproducible-deep-research-evaluation--arxiv-2604.14683/2026-06-19T04:40:28.642Z https://www.opentrain.ai/papers/storycoder-narrative-reformulation-for-structured-reasoning-in-llm-code-generati--arxiv-2604.14631/2026-06-19T20:01:32.566Z https://www.opentrain.ai/papers/tracer-trace-based-adaptive-cost-efficient-routing-for-llm-classification--arxiv-2604.14531/2026-06-20T03:22:27.628Z https://www.opentrain.ai/papers/europemedqa-study-protocol-a-multilingual-multimodal-medical-examination-dataset--arxiv-2604.14306/2026-06-18T05:11:36.622Z https://www.opentrain.ai/papers/rose-retrieval-oriented-segmentation-enhancement--arxiv-2604.14147/2026-04-16T08:08:20.628Z https://www.opentrain.ai/papers/from-p-y-x-to-p-y-investigating-reinforcement-learning-in-pre-train-space--arxiv-2604.14142/2026-06-19T04:44:20.059Z https://www.opentrain.ai/papers/hivla-a-visual-grounded-centric-hierarchical-embodied-manipulation-system--arxiv-2604.14125/2026-06-19T04:46:16.965Z https://www.opentrain.ai/papers/trex-automating-llm-fine-tuning-via-agent-driven-tree-based-exploration--arxiv-2604.14116/2026-06-16T23:44:23.366Z https://www.opentrain.ai/papers/tip-token-importance-in-on-policy-distillation--arxiv-2604.14084/2026-06-19T04:42:39.379Z https://www.opentrain.ai/papers/feed-forward-3d-scene-modeling-a-problem-driven-perspective--arxiv-2604.14025/2026-06-17T22:24:40.414Z https://www.opentrain.ai/papers/memory-transfer-learning-how-memories-are-transferred-across-domains-in-coding-a--arxiv-2604.14004/2026-06-19T03:54:45.310Z https://www.opentrain.ai/papers/dipo-disentangled-perplexity-policy-optimization-for-fine-grained-exploration-ex--arxiv-2604.13902/2026-06-19T04:32:50.842Z https://www.opentrain.ai/papers/sparsebalance-load-balanced-long-context-training-with-dynamic-sparse-attention--arxiv-2604.13847/2026-06-19T04:45:00.412Z https://www.opentrain.ai/papers/an-empirical-investigation-of-practical-llm-as-a-judge-improvement-techniques-on--arxiv-2604.13717/2026-06-20T02:51:44.987Z https://www.opentrain.ai/papers/indicdb-benchmarking-multilingual-text-to-sql-capabilities-in-indian-languages--arxiv-2604.13686/2026-06-19T04:22:40.788Z https://www.opentrain.ai/papers/time-series-causal-discovery-with-variable-lags--arxiv-2605.04081/2026-06-18T16:20:02.318Z https://www.opentrain.ai/papers/reward-hacking-in-the-era-of-large-models-mechanisms-emergent-misalignment-chall--arxiv-2604.13602/2026-06-19T04:28:57.665Z https://www.opentrain.ai/papers/toolspec-accelerating-tool-calling-via-schema-aware-and-retrieval-augmented-spec--arxiv-2604.13519/2026-06-18T22:58:51.008Z https://www.opentrain.ai/papers/representation-over-routing-overcoming-surrogate-hacking-in-multi-timescale-ppo--arxiv-2604.13517/2026-06-19T04:38:20.851Z https://www.opentrain.ai/papers/agentspex-an-agent-specification-and-execution-language--arxiv-2604.13346/2026-06-19T04:21:18.459Z https://www.opentrain.ai/papers/webxskill-skill-learning-for-autonomous-web-agents--arxiv-2604.13318/2026-06-18T18:44:12.153Z https://www.opentrain.ai/papers/kv-packet-recomputation-free-context-independent-kv-caching-for-llms--arxiv-2604.13226/2026-06-19T04:57:57.016Z https://www.opentrain.ai/papers/infinitesciencegym-an-unbounded-procedurally-generated-benchmark-for-scientific--arxiv-2604.13201/2026-06-18T16:02:42.913Z https://www.opentrain.ai/papers/rethinking-on-policy-distillation-of-large-language-models-phenomenology-mechani--arxiv-2604.13016/2026-06-19T10:22:53.192Z https://www.opentrain.ai/papers/lightning-opd-efficient-post-training-for-large-reasoning-models-with-offline-on--arxiv-2604.13010/2026-06-19T04:22:49.835Z https://www.opentrain.ai/papers/one-token-away-from-collapse-the-fragility-of-instruction-tuned-helpfulness--arxiv-2604.13006/2026-06-19T04:41:15.814Z https://www.opentrain.ai/papers/boosting-visual-instruction-tuning-with-self-supervised-guidance--arxiv-2604.12966/2026-06-18T23:12:47.820Z https://www.opentrain.ai/papers/towards-long-horizon-agentic-multimodal-search--arxiv-2604.12890/2026-06-19T04:43:30.068Z https://www.opentrain.ai/papers/knowrl-boosting-llm-reasoning-via-reinforcement-learning-with-minimal-sufficient--arxiv-2604.12627/2026-06-19T02:44:44.666Z https://www.opentrain.ai/papers/balanced-aggregation-understanding-and-fixing-aggregation-bias-in-grpo--arxiv-2605.04077/2026-06-18T14:17:41.823Z https://www.opentrain.ai/papers/latent-condensed-transformer-for-efficient-long-context-modeling--arxiv-2604.12452/2026-06-19T04:48:40.796Z https://www.opentrain.ai/papers/nemotron-3-super-open-efficient-mixture-of-experts-hybrid-mamba-transformer-mode--arxiv-2604.12374/2026-06-19T04:30:17.069Z https://www.opentrain.ai/papers/self-adversarial-one-step-generation-via-condition-shifting--arxiv-2604.12322/2026-06-19T09:57:52.029Z https://www.opentrain.ai/papers/self-distillation-zero-self-revision-turns-binary-rewards-into-dense-supervision--arxiv-2604.12002/2026-06-19T04:17:27.678Z https://www.opentrain.ai/papers/clawgui-a-unified-framework-for-training-evaluating-and-deploying-gui-agents--arxiv-2604.11784/2026-06-18T08:17:39.148Z https://www.opentrain.ai/papers/towards-autonomous-mechanistic-reasoning-in-virtual-cells--arxiv-2604.11661/2026-06-18T16:50:14.703Z https://www.opentrain.ai/papers/self-evolving-llm-memory-extraction-across-heterogeneous-tasks--arxiv-2604.11610/2026-06-19T04:25:55.585Z https://www.opentrain.ai/papers/a-triadic-suffix-tokenization-scheme-for-numerical-reasoning--arxiv-2604.11582/2026-06-17T23:39:24.837Z