https://www.opentrain.ai/papers/plausibility-as-commonsense-reasoning-humans-succeed-large-language-models-do-no--arxiv-2604.04825/2026-06-17T04:37:27.650Z https://www.opentrain.ai/papers/anx-protocol-first-design-for-ai-agent-interaction-with-a-supporting-3ex-decoupl--arxiv-2604.04820/2026-06-18T00:46:18.496Z https://www.opentrain.ai/papers/livefact-a-dynamic-time-aware-benchmark-for-llm-driven-fake-news-detection--arxiv-2604.04815/2026-05-22T07:49:51.369Z https://www.opentrain.ai/papers/skillx-automatically-constructing-skill-knowledge-bases-for-agents--arxiv-2604.04804/2026-06-19T10:52:39.577Z https://www.opentrain.ai/papers/how-far-are-we-systematic-evaluation-of-llms-vs-human-experts-in-mathematical-co--arxiv-2604.04791/2026-06-19T00:05:13.853Z https://www.opentrain.ai/papers/cog-drift-exploration-on-adaptively-reformulated-instances-enables-learning-from--arxiv-2604.04767/2026-06-17T22:30:39.531Z https://www.opentrain.ai/papers/your-agent-their-asset-a-real-world-safety-analysis-of-openclaw--arxiv-2604.04759/2026-06-17T06:32:41.902Z https://www.opentrain.ai/papers/ai-trust-os-a-continuous-governance-framework-for-autonomous-ai-observability-an--arxiv-2604.04749/2026-06-17T13:09:43.618Z https://www.opentrain.ai/papers/lighting-up-or-dimming-down-exploring-dark-patterns-of-llms-in-co-creativity--arxiv-2604.04735/2026-06-18T06:27:35.991Z https://www.opentrain.ai/papers/discovering-failure-modes-in-vision-language-models-using-rl--arxiv-2604.04733/2026-06-18T21:40:40.022Z https://www.opentrain.ai/papers/metaphors-we-compute-by-a-computational-audit-of-cultural-translation-vs-thinkin--arxiv-2604.04732/2026-06-16T19:26:11.918Z https://www.opentrain.ai/papers/individual-and-combined-effects-of-english-as-a-second-language-and-typos-on-llm--arxiv-2604.04723/2026-06-20T00:05:55.783Z https://www.opentrain.ai/papers/is-a-picture-worth-a-thousand-words-adaptive-multimodal-fact-checking-with-visua--arxiv-2604.04692/2026-06-19T17:57:09.346Z https://www.opentrain.ai/papers/rosclaw-a-hierarchical-semantic-physical-framework-for-heterogeneous-multi-agent--arxiv-2604.04664/2026-06-18T16:55:23.752Z https://www.opentrain.ai/papers/search-do-not-guess-teaching-small-language-models-to-be-effective-search-agents--arxiv-2604.04651/2026-06-17T21:36:12.279Z https://www.opentrain.ai/papers/one-model-for-all-multi-objective-controllable-language-models--arxiv-2604.04497/2026-04-12T23:15:27.849Z https://www.opentrain.ai/papers/a-patch-based-cross-view-regularized-framework-for-backdoor-defense-in-multimoda--arxiv-2604.04488/2026-06-12T09:37:50.453Z https://www.opentrain.ai/papers/grid2matrix-revealing-digital-agnosia-in-vision-language-models--arxiv-2604.09687/2026-06-17T22:24:26.758Z https://www.opentrain.ai/papers/explainable-autonomous-cyber-defense-using-adversarial-multi-agent-reinforcement--arxiv-2604.04442/2026-06-18T22:58:49.170Z https://www.opentrain.ai/papers/steer-structured-event-evidence-for-video-reasoning-via-multi-objective-reinforc--arxiv-2604.04415/2026-06-19T14:53:06.952Z https://www.opentrain.ai/papers/how-alignment-routes-localizing-scaling-and-controlling-policy-circuits-in-langu--arxiv-2604.04385/2026-05-30T06:17:07.379Z https://www.opentrain.ai/papers/ream-merging-improves-pruning-of-experts-in-llms--arxiv-2604.04356/2026-04-21T02:36:56.729Z https://www.opentrain.ai/papers/self-distilled-rlvr--arxiv-2604.03128/2026-06-20T07:39:33.268Z https://www.opentrain.ai/papers/skvm-compiling-skills-for-efficient-execution-everywhere--arxiv-2604.03088/2026-06-17T14:55:19.006Z https://www.opentrain.ai/papers/joyai-llm-flash-advancing-mid-scale-llms-with-token-efficiency--arxiv-2604.03044/2026-06-16T23:35:12.128Z https://www.opentrain.ai/papers/omnigui-benchmarking-gui-agents-in-omni-modal-smartphone-environments--arxiv-2605.18758/2026-06-18T13:59:43.768Z https://www.opentrain.ai/papers/mitigating-llm-biases-toward-spurious-social-contexts-using-direct-preference-op--arxiv-2604.02585/2026-06-17T09:51:14.558Z https://www.opentrain.ai/papers/actionparty-multi-subject-action-binding-in-generative-video-games--arxiv-2604.02330/2026-06-18T04:31:05.382Z https://www.opentrain.ai/papers/steerable-visual-representations--arxiv-2604.02327/2026-06-19T10:51:34.169Z https://www.opentrain.ai/papers/batched-contextual-reinforcement-a-task-scaling-law-for-efficient-reasoning--arxiv-2604.02322/2026-06-20T00:07:18.140Z https://www.opentrain.ai/papers/beyond-the-assistant-turn-user-turn-generation-as-a-probe-of-interaction-awarene--arxiv-2604.02315/2026-06-20T06:17:52.820Z https://www.opentrain.ai/papers/void-video-object-and-interaction-deletion--arxiv-2604.02296/2026-06-20T00:53:16.567Z https://www.opentrain.ai/papers/omni123-exploring-3d-native-foundation-models-with-limited-3d-data-by-unifying-t--arxiv-2604.02289/2026-06-18T03:40:43.950Z https://www.opentrain.ai/papers/unifying-group-relative-and-self-distillation-policy-optimization-via-sample-rou--arxiv-2604.02288/2026-06-20T05:29:14.452Z https://www.opentrain.ai/papers/novel-memory-forgetting-techniques-for-autonomous-ai-agents-balancing-relevance--arxiv-2604.02280/2026-06-18T04:31:52.435Z https://www.opentrain.ai/papers/crystalite-a-lightweight-transformer-for-efficient-crystal-modeling--arxiv-2604.02270/2026-06-18T11:19:19.636Z https://www.opentrain.ai/papers/answering-the-wrong-question-reasoning-trace-inversion-for-abstention-in-llms--arxiv-2604.02230/2026-06-17T04:20:46.843Z https://www.opentrain.ai/papers/when-to-ask-uncertainty-gated-language-assistance-for-reinforcement-learning--arxiv-2604.02226/2026-06-19T12:17:42.051Z https://www.opentrain.ai/papers/impact-of-multimodal-and-conversational-ai-on-learning-outcomes-and-experience--arxiv-2604.02221/2026-06-19T12:13:55.588Z https://www.opentrain.ai/papers/towards-position-robust-talent-recommendation-via-large-language-models--arxiv-2604.02200/2026-06-20T00:19:19.882Z https://www.opentrain.ai/papers/neuro-rit-neuron-guided-instruction-tuning-for-robust-retrieval-augmented-langua--arxiv-2604.02194/2026-06-18T04:53:49.990Z https://www.opentrain.ai/papers/the-expert-strikes-back-interpreting-mixture-of-experts-language-models-at-exper--arxiv-2604.02178/2026-06-19T15:47:45.825Z https://www.opentrain.ai/papers/adam-s-law-textual-frequency-law-on-large-language-models--arxiv-2604.02176/2026-06-15T16:43:56.023Z https://www.opentrain.ai/papers/quantifying-self-preservation-bias-in-large-language-models--arxiv-2604.02174/2026-06-19T05:55:01.422Z https://www.opentrain.ai/papers/mti-a-behavior-based-temperament-profiling-system-for-ai-agents--arxiv-2604.02145/2026-06-18T20:44:21.353Z https://www.opentrain.ai/papers/llm-as-a-judge-for-time-series-explanations--arxiv-2604.02118/2026-06-19T08:28:52.812Z https://www.opentrain.ai/papers/reliable-control-point-selection-for-steering-reasoning-in-large-language-models--arxiv-2604.02113/2026-06-17T22:30:31.486Z https://www.opentrain.ai/papers/optimizing-rag-rerankers-with-llm-feedback-via-reinforcement-learning--arxiv-2604.02091/2026-06-18T17:13:45.538Z https://www.opentrain.ai/papers/diff-kd-diffusion-based-knowledge-distillation-for-collaborative-perception-unde--arxiv-2604.02061/2026-06-20T06:35:18.342Z https://www.opentrain.ai/papers/atbench-a-diverse-and-realistic-trajectory-benchmark-for-long-horizon-agent-safe--arxiv-2604.02022/2026-06-20T08:27:19.358Z https://www.opentrain.ai/papers/k-nnproxy-efficient-training-free-proxy-alignment-for-black-box-zero-shot-llm-ge--arxiv-2604.02008/2026-06-18T18:59:50.441Z https://www.opentrain.ai/papers/proceedrl-process-critic-with-exploratory-demonstration-reinforcement-learning-f--arxiv-2604.02006/2026-06-18T18:47:00.182Z https://www.opentrain.ai/papers/safe-stepwise-atomic-feedback-for-error-correction-in-multi-hop-reasoning--arxiv-2604.01993/2026-06-18T23:51:20.891Z https://www.opentrain.ai/papers/ruleforge-automated-generation-and-validation-for-web-vulnerability-detection-at--arxiv-2604.01977/2026-06-20T01:50:48.287Z https://www.opentrain.ai/papers/ego-grounding-for-personalized-question-answering-in-egocentric-videos--arxiv-2604.01966/2026-06-16T16:02:14.596Z https://www.opentrain.ai/papers/lifting-unlabeled-internet-level-data-for-3d-scene-understanding--arxiv-2604.01907/2026-06-19T10:37:30.088Z https://www.opentrain.ai/papers/plot-enhancing-preference-learning-via-optimal-transport--arxiv-2604.01837/2026-06-16T01:38:32.892Z https://www.opentrain.ai/papers/deft-distribution-guided-efficient-fine-tuning-for-human-alignment--arxiv-2604.01787/2026-06-19T05:28:20.068Z https://www.opentrain.ai/papers/drivedreamer-policy-a-geometry-grounded-world-action-model-for-unified-generatio--arxiv-2604.01765/2026-06-19T12:13:31.347Z https://www.opentrain.ai/papers/fouriermoe-fourier-mixture-of-experts-adaptation-of-large-language-models--arxiv-2604.01762/2026-06-18T06:59:04.111Z https://www.opentrain.ai/papers/livemathematicianbench-a-live-benchmark-for-mathematician-level-reasoning-with-p--arxiv-2604.01754/2026-06-18T02:04:32.695Z https://www.opentrain.ai/papers/liteinception-a-lightweight-and-interpretable-deep-learning-framework-for-genera--arxiv-2604.01725/2026-06-19T14:52:35.516Z https://www.opentrain.ai/papers/human-guided-reasoning-with-large-language-models-for-vietnamese-speech-emotion--arxiv-2604.01711/2026-06-19T16:38:45.501Z https://www.opentrain.ai/papers/memory-in-the-llm-era-modular-architectures-and-strategies-in-a-unified-framewor--arxiv-2604.01707/2026-06-19T15:23:57.440Z https://www.opentrain.ai/papers/fragile-reasoning-a-mechanistic-analysis-of-llm-sensitivity-to-meaning-preservin--arxiv-2604.01639/2026-06-19T14:52:34.148Z https://www.opentrain.ai/papers/oscar-orchestrated-self-verification-and-cross-path-refinement--arxiv-2604.01624/2026-06-18T15:52:16.994Z https://www.opentrain.ai/papers/expert-choice-routing-enables-adaptive-computation-in-diffusion-language-models--arxiv-2604.01622/2026-06-20T00:00:33.571Z https://www.opentrain.ai/papers/deltamem-towards-agentic-memory-management-via-reinforcement-learning--arxiv-2604.01560/2026-06-18T14:46:52.421Z https://www.opentrain.ai/papers/read-more-think-more-revisiting-observation-reduction-for-web-agents--arxiv-2604.01535/2026-06-18T18:47:59.119Z https://www.opentrain.ai/papers/magic-madness-heaven-sin-llm-output-diversity-is-everything-everywhere-all-at-on--arxiv-2604.01504/2026-06-18T02:07:23.624Z https://www.opentrain.ai/papers/from-swe-zero-to-swe-hero-execution-free-to-execution-based-fine-tuning-for-soft--arxiv-2604.01496/2026-06-19T14:53:20.370Z https://www.opentrain.ai/papers/agentsocialbench-evaluating-privacy-risks-in-human-centered-agentic-social-netwo--arxiv-2604.01487/2026-06-19T14:52:37.259Z https://www.opentrain.ai/papers/when-reward-hacking-rebounds-understanding-and-mitigating-it-with-representation--arxiv-2604.01476/2026-06-19T12:13:54.527Z https://www.opentrain.ai/papers/adaptive-stopping-for-multi-turn-llm-reasoning--arxiv-2604.01413/2026-06-20T01:30:50.266Z https://www.opentrain.ai/papers/procedural-knowledge-at-scale-improves-reasoning--arxiv-2604.01348/2026-06-19T14:52:57.349Z https://www.opentrain.ai/papers/preference-learning-in-shades-of-gray-interpretable-and-bias-aware-reward-modeli--arxiv-2604.01312/2026-06-17T06:56:12.301Z https://www.opentrain.ai/papers/m2-verify-a-large-scale-multidomain-benchmark-for-checking-multimodal-claim-cons--arxiv-2604.01306/2026-06-18T16:16:25.055Z https://www.opentrain.ai/papers/scaling-reasoning-tokens-via-rl-and-parallel-thinking-evidence-from-competitive--arxiv-2604.01302/2026-06-18T13:22:30.478Z https://www.opentrain.ai/papers/hippocamp-benchmarking-contextual-agents-on-personal-computers--arxiv-2604.01221/2026-06-17T08:44:36.529Z https://www.opentrain.ai/papers/universal-yoco-for-efficient-depth-scaling--arxiv-2604.01220/2026-06-19T14:52:54.472Z https://www.opentrain.ai/papers/texttt-yc-bench-benchmarking-ai-agents-for-long-term-planning-and-consistent-exe--arxiv-2604.01212/2026-06-19T06:50:00.588Z https://www.opentrain.ai/papers/llm-regression-with-a-latent-iterative-state-head--arxiv-2604.01206/2026-06-19T15:01:25.842Z https://www.opentrain.ai/papers/embarrassingly-simple-self-distillation-improves-code-generation--arxiv-2604.01193/2026-06-18T18:21:56.659Z https://www.opentrain.ai/papers/true-vis-lies-analyzing-how-generative-ai-recognizes-intentionality-rhetoric-and--arxiv-2604.01181/2026-06-19T14:52:32.477Z https://www.opentrain.ai/papers/online-reasoning-calibration-test-time-training-enables-generalizable-conformal--arxiv-2604.01170/2026-06-18T08:06:46.678Z https://www.opentrain.ai/papers/brainstacks-cross-domain-cognitive-capabilities-via-frozen-moe-lora-stacks-for-c--arxiv-2604.01152/2026-06-18T11:33:48.080Z https://www.opentrain.ai/papers/care-privacy-compliant-agentic-reasoning-with-evidence-discordance--arxiv-2604.01113/2026-06-19T12:16:57.134Z https://www.opentrain.ai/papers/uncertainty-aware-variational-reward-factorization-via-probabilistic-preference--arxiv-2604.00997/2026-06-20T09:14:47.567Z https://www.opentrain.ai/papers/multimodal-analysis-of-state-funded-news-coverage-of-the-israel-hamas-war-on-you--arxiv-2604.00994/2026-06-19T12:11:28.051Z https://www.opentrain.ai/papers/dual-optimal-make-your-llm-peer-like-with-dignity--arxiv-2604.00979/2026-06-18T04:53:32.705Z https://www.opentrain.ai/papers/benchmarking-and-mechanistic-analysis-of-vision-language-models-for-cross-depict--arxiv-2604.00913/2026-06-18T15:57:14.075Z https://www.opentrain.ai/papers/beyond-symbolic-solving-multi-chain-of-thought-voting-for-geometric-reasoning-in--arxiv-2604.00890/2026-06-19T09:05:26.147Z https://www.opentrain.ai/papers/pixelprune-pixel-level-adaptive-visual-token-reduction-via-predictive-coding--arxiv-2604.00886/2026-06-18T05:05:34.924Z https://www.opentrain.ai/papers/kuet-at-stancenakba-shared-task-stancemoe-mixture-of-experts-architecture-for-st--arxiv-2604.00878/2026-06-19T14:52:46.903Z https://www.opentrain.ai/papers/agentic-tool-use-in-large-language-models--arxiv-2604.00835/2026-06-18T12:41:29.562Z https://www.opentrain.ai/papers/multimodal-language-models-cannot-spot-spatial-inconsistencies--arxiv-2604.00799/2026-06-19T14:52:42.278Z https://www.opentrain.ai/papers/langmarl-natural-language-multi-agent-reinforcement-learning--arxiv-2604.00722/2026-06-18T14:43:14.265Z https://www.opentrain.ai/papers/trims-trajectory-ranked-instruction-masked-supervision-for-diffusion-language-mo--arxiv-2604.00666/2026-06-20T09:02:14.625Z https://www.opentrain.ai/papers/a-survey-of-on-policy-distillation-for-large-language-models--arxiv-2604.00626/2026-06-20T07:47:01.413Z https://www.opentrain.ai/papers/speech-llms-are-contextual-reasoning-transcribers--arxiv-2604.00610/2026-06-19T14:52:39.689Z https://www.opentrain.ai/papers/more-human-more-efficient-aligning-annotations-with-quantized-slms--arxiv-2604.00586/2026-06-20T08:22:55.350Z https://www.opentrain.ai/papers/ontology-constrained-neural-reasoning-in-enterprise-agentic-systems-a-neurosymbo--arxiv-2604.00555/2026-06-18T11:31:45.788Z https://www.opentrain.ai/papers/moon3-0-reasoning-aware-multimodal-representation-learning-for-e-commerce-produc--arxiv-2604.00513/2026-06-19T14:52:48.566Z https://www.opentrain.ai/papers/adapting-text-llms-to-speech-via-multimodal-depth-up-scaling--arxiv-2604.00489/2026-06-18T14:49:17.222Z https://www.opentrain.ai/papers/execution-verified-reinforcement-learning-for-optimization-modeling--arxiv-2604.00442/2026-06-17T15:16:07.047Z https://www.opentrain.ai/papers/tr-icrl-test-time-rethinking-for-in-context-reinforcement-learning--arxiv-2604.00438/2026-06-17T09:51:48.610Z https://www.opentrain.ai/papers/locally-confident-globally-stuck-the-quality-exploration-dilemma-in-diffusion-la--arxiv-2604.00375/2026-06-19T12:15:12.286Z https://www.opentrain.ai/papers/signals-trajectory-sampling-and-triage-for-agentic-interactions--arxiv-2604.00356/2026-06-15T13:40:10.414Z https://www.opentrain.ai/papers/agent-q-mix-selecting-the-right-action-for-llm-multi-agent-systems-through-reinf--arxiv-2604.00344/2026-06-19T00:25:55.264Z https://www.opentrain.ai/papers/large-language-models-in-the-abuse-detection-pipeline--arxiv-2604.00323/2026-06-19T08:54:30.883Z https://www.opentrain.ai/papers/can-large-language-models-self-correct-in-medical-question-answering-an-explorat--arxiv-2604.00261/2026-06-17T06:04:20.075Z https://www.opentrain.ai/papers/a-taxonomy-of-programming-languages-for-code-generation--arxiv-2604.00239/2026-06-17T07:33:39.050Z https://www.opentrain.ai/papers/do-llms-know-what-is-private-internally-probing-and-steering-contextual-privacy--arxiv-2604.00209/2026-06-19T22:53:59.880Z https://www.opentrain.ai/papers/hierarchical-chain-of-thought-prompting-enhancing-llm-reasoning-performance-and--arxiv-2604.00130/2026-06-18T04:55:15.433Z https://www.opentrain.ai/papers/hierarchical-pre-training-of-vision-encoders-with-large-language-models--arxiv-2604.00086/2026-06-18T18:31:23.620Z https://www.opentrain.ai/papers/one-panel-does-not-fit-all-case-adaptive-multi-agent-deliberation-for-clinical-p--arxiv-2604.00085/2026-06-16T16:58:48.994Z https://www.opentrain.ai/papers/cognitive-friction-a-decision-theoretic-framework-for-bounded-deliberation-in-to--arxiv-2603.30031/2026-06-19T06:49:57.483Z https://www.opentrain.ai/papers/less-is-more-selective-visual-attention-to-high-importance-regions-for-multimoda--arxiv-2603.29901/2026-06-18T18:29:33.521Z https://www.opentrain.ai/papers/training-free-dynamic-upcycling-of-expert-language-models--arxiv-2603.29765/2026-06-18T18:53:02.072Z https://www.opentrain.ai/papers/a-comprehensive-information-decomposition-analysis-of-large-vision-language-mode--arxiv-2603.29676/2026-06-14T05:47:00.281Z https://www.opentrain.ai/papers/agenda-based-narrative-extraction-steering-pathfinding-algorithms-with-large-lan--arxiv-2603.29661/2026-06-20T03:48:34.874Z https://www.opentrain.ai/papers/learning-diagnostic-reasoning-for-decision-support-in-toxicology--arxiv-2603.29608/2026-06-18T12:56:45.291Z https://www.opentrain.ai/papers/llm-probe-evaluating-llms-for-low-resource-languages--arxiv-2603.29517/2026-06-18T21:54:12.656Z https://www.opentrain.ai/papers/memfactory-unified-inference-training-framework-for-agent-memory--arxiv-2603.29493/2026-06-18T05:22:30.648Z https://www.opentrain.ai/papers/m-minigpt4-multilingual-vllm-alignment-via-translated-data--arxiv-2603.29467/2026-06-18T08:02:34.200Z https://www.opentrain.ai/papers/elt-bench-verified-benchmark-quality-issues-underestimate-ai-agent-capabilities--arxiv-2603.29399/2026-06-19T12:15:41.086Z https://www.opentrain.ai/papers/beyond-idealized-patients-evaluating-llms-under-challenging-patient-behaviors-in--arxiv-2603.29373/2026-06-18T11:30:13.455Z https://www.opentrain.ai/papers/aligning-multimodal-sequential-recommendations-via-robust-direct-preference-opti--arxiv-2603.29259/2026-06-20T05:18:28.366Z https://www.opentrain.ai/papers/memrerank-preference-memory-for-personalized-product-reranking--arxiv-2603.29247/2026-06-15T11:24:36.295Z https://www.opentrain.ai/papers/long-document-qa-with-chain-of-structured-thought-and-fine-tuned-slms--arxiv-2603.29232/2026-06-18T18:46:36.315Z https://www.opentrain.ai/papers/syrisign-a-parallel-corpus-for-arabic-text-to-syrian-arabic-sign-language-transl--arxiv-2603.29219/2026-06-19T14:52:33.887Z https://www.opentrain.ai/papers/xuanwu-evolving-general-multimodal-models-into-an-industrial-grade-foundation-fo--arxiv-2603.29211/2026-06-16T19:21:44.187Z https://www.opentrain.ai/papers/dual-perspectives-in-emotion-attribution-a-generator-interpreter-framework-for-c--arxiv-2603.29077/2026-06-19T14:52:46.509Z https://www.opentrain.ai/papers/trojan-speak-bypassing-constitutional-classifiers-with-no-jailbreak-tax-via-adve--arxiv-2603.29038/2026-06-20T00:08:28.152Z https://www.opentrain.ai/papers/the-model-says-walk-how-surface-heuristics-override-implicit-constraints-in-llm--arxiv-2603.29025/2026-06-18T11:30:42.366Z https://www.opentrain.ai/papers/human-like-lifelong-memory-a-neuroscience-grounded-architecture-for-infinite-int--arxiv-2603.29023/2026-06-19T12:16:42.098Z https://www.opentrain.ai/papers/sole-r1-video-language-reasoning-as-the-sole-reward-for-on-robot-reinforcement-l--arxiv-2603.28730/2026-06-18T01:52:22.301Z https://www.opentrain.ai/papers/seeing-with-you-perception-reasoning-coevolution-for-multimodal-reasoning--arxiv-2603.28618/2026-06-20T00:08:17.605Z https://www.opentrain.ai/papers/resadapt-adaptive-resolution-for-efficient-multimodal-reasoning--arxiv-2603.28610/2026-06-19T11:53:00.071Z https://www.opentrain.ai/papers/moving-beyond-review-applying-language-models-to-planning-and-translation-in-ref--arxiv-2603.28596/2026-06-19T12:14:37.942Z https://www.opentrain.ai/papers/courtroom-style-multi-agent-debate-with-progressive-rag-and-role-switching-for-c--arxiv-2603.28488/2026-06-18T04:52:56.736Z https://www.opentrain.ai/papers/kernel-smith-a-unified-recipe-for-evolutionary-kernel-optimization--arxiv-2603.28342/2026-06-20T01:58:17.396Z https://www.opentrain.ai/papers/dongyuan-an-llm-based-framework-for-integrative-chinese-and-western-medicine-spl--arxiv-2603.28191/2026-06-19T04:50:42.929Z https://www.opentrain.ai/papers/moss-voicegenerator-create-realistic-voices-with-natural-language-descriptions--arxiv-2603.28086/2026-06-20T04:51:24.382Z https://www.opentrain.ai/papers/efficient-inference-of-large-vision-language-models--arxiv-2603.27960/2026-06-19T14:52:50.948Z https://www.opentrain.ai/papers/top-down-string-to-dependency-neural-machine-translation--arxiv-2603.27938/2026-06-19T14:52:36.062Z https://www.opentrain.ai/papers/atlas-rtc-closing-the-loop-on-llm-agent-output-with-token-level-runtime-control--arxiv-2603.27905/2026-06-18T18:19:42.057Z https://www.opentrain.ai/papers/effiskill-agent-skill-based-automated-code-efficiency-optimization--arxiv-2603.27850/2026-06-18T09:43:30.695Z https://www.opentrain.ai/papers/model-capability-dominates-inference-time-optimization-lessons-from-aimo-3--arxiv-2603.27844/2026-06-19T12:16:35.083Z https://www.opentrain.ai/papers/q-bridge-code-translation-for-quantum-machine-learning-via-llms--arxiv-2603.27836/2026-06-20T01:31:58.166Z https://www.opentrain.ai/papers/improving-clinical-diagnosis-with-counterfactual-multi-agent-reasoning--arxiv-2603.27820/2026-06-19T14:52:48.786Z https://www.opentrain.ai/papers/kvsculpt-kv-cache-compression-as-distillation--arxiv-2603.27819/2026-06-19T15:02:19.841Z https://www.opentrain.ai/papers/conversational-agents-and-the-understanding-of-human-language-reflections-on-ai--arxiv-2603.27809/2026-06-19T14:52:55.123Z https://www.opentrain.ai/papers/understanding-teacher-revisions-of-large-language-model-generated-feedback--arxiv-2603.27806/2026-06-18T04:53:22.050Z https://www.opentrain.ai/papers/emergent-social-intelligence-risks-in-generative-multi-agent-systems--arxiv-2603.27771/2026-06-19T14:53:01.243Z https://www.opentrain.ai/papers/kat-coder-v2-technical-report--arxiv-2603.27703/2026-06-19T14:53:41.772Z https://www.opentrain.ai/papers/can-large-language-models-simulate-human-cognition-beyond-behavioral-imitation--arxiv-2603.27694/2026-06-19T14:52:59.628Z https://www.opentrain.ai/papers/prbench-end-to-end-paper-reproduction-in-physics-research--arxiv-2603.27646/2026-06-19T14:53:30.973Z https://www.opentrain.ai/papers/longcat-next-lexicalizing-modalities-as-discrete-tokens--arxiv-2603.27538/2026-06-18T17:59:01.337Z https://www.opentrain.ai/papers/hidden-ads-behavior-triggered-semantic-backdoors-for-advertisement-injection-in--arxiv-2603.27522/2026-06-19T14:52:53.862Z https://www.opentrain.ai/papers/agentswing-adaptive-parallel-context-management-routing-for-long-horizon-web-age--arxiv-2603.27490/2026-06-20T04:51:14.579Z https://www.opentrain.ai/papers/multi-agent-dialectical-refinement-for-enhanced-argument-classification--arxiv-2603.27451/2026-06-20T05:39:21.402Z https://www.opentrain.ai/papers/improving-attributed-long-form-question-answering-with-intent-awareness--arxiv-2603.27435/2026-06-19T01:22:39.085Z https://www.opentrain.ai/papers/the-geometry-of-harmful-intent-training-free-anomaly-detection-via-angular-devia--arxiv-2603.27412/2026-06-18T18:31:06.198Z https://www.opentrain.ai/papers/heterogeneous-debate-engine-identity-grounded-cognitive-architecture-for-resilie--arxiv-2603.27404/2026-06-19T14:52:53.475Z https://www.opentrain.ai/papers/pubmed-reasoner-dynamic-reasoning-based-retrieval-for-evidence-grounded-biomedic--arxiv-2603.27335/2026-06-20T08:36:18.158Z https://www.opentrain.ai/papers/sacred-a-faithful-annotated-multimedia-multimodal-multilingual-dataset-for-class--arxiv-2603.27331/2026-06-19T14:52:31.065Z https://www.opentrain.ai/papers/mitigating-hallucination-on-hallucination-in-rag-via-ensemble-voting--arxiv-2603.27253/2026-06-19T14:52:29.251Z https://www.opentrain.ai/papers/rethinking-easy-to-hard-limits-of-curriculum-learning-in-post-training-for-deduc--arxiv-2603.27226/2026-06-18T10:52:30.732Z https://www.opentrain.ai/papers/davinci-llm-towards-the-science-of-pretraining--arxiv-2603.27164/2026-06-19T08:04:52.446Z https://www.opentrain.ai/papers/learning-to-predict-future-aligned-research-proposals-with-language-models--arxiv-2603.27146/2026-06-16T08:58:36.927Z https://www.opentrain.ai/papers/chartnet-a-million-scale-high-quality-multimodal-dataset-for-robust-chart-unders--arxiv-2603.27064/2026-06-19T09:48:44.851Z https://www.opentrain.ai/papers/debiasing-large-language-models-toward-social-factors-in-online-behavior-analyti--arxiv-2603.27057/2026-06-18T15:56:13.911Z https://www.opentrain.ai/papers/the-last-fingerprint-how-markdown-training-shapes-llm-prose--arxiv-2603.27006/2026-06-18T22:26:41.891Z https://www.opentrain.ai/papers/learning-to-commit-generating-organic-pull-requests-via-online-repository-memory--arxiv-2603.26664/2026-06-18T11:09:14.142Z https://www.opentrain.ai/papers/perceptioncomp-a-video-benchmark-for-complex-perception-centric-reasoning--arxiv-2603.26653/2026-06-19T13:44:34.020Z https://www.opentrain.ai/papers/when-perplexity-lies-generation-focused-distillation-of-hybrid-sequence-models--arxiv-2603.26556/2026-06-19T14:53:10.313Z https://www.opentrain.ai/papers/jal-turn-joint-acoustic-linguistic-modeling-for-real-time-and-robust-turn-taking--arxiv-2603.26515/2026-06-18T18:29:13.414Z https://www.opentrain.ai/papers/climatecheck-2026-scientific-fact-checking-and-disinformation-narrative-classifi--arxiv-2603.26449/2026-06-19T05:25:19.200Z https://www.opentrain.ai/papers/calrk-bench-evaluating-context-aware-legal-reasoning-in-korean-law--arxiv-2603.26332/2026-06-20T05:55:07.521Z https://www.opentrain.ai/papers/from-human-cognition-to-neural-activations-probing-the-computational-primitives--arxiv-2603.26323/2026-06-19T13:45:15.923Z https://www.opentrain.ai/papers/xpertbench-expert-level-tasks-with-rubrics-based-evaluation--arxiv-2604.02368/2026-06-19T12:16:47.727Z https://www.opentrain.ai/papers/ask-or-assume-uncertainty-aware-clarification-seeking-in-coding-agents--arxiv-2603.26233/2026-06-19T05:39:31.673Z https://www.opentrain.ai/papers/dataflex-a-unified-framework-for-data-centric-dynamic-training-of-large-language--arxiv-2603.26164/2026-06-19T03:48:20.011Z https://www.opentrain.ai/papers/vega-learning-to-drive-with-natural-language-instructions--arxiv-2603.25741/2026-06-16T02:39:42.764Z https://www.opentrain.ai/papers/packforcing-short-video-training-suffices-for-long-video-sampling-and-long-conte--arxiv-2603.25730/2026-06-19T12:16:53.251Z https://www.opentrain.ai/papers/r-c2-cycle-consistent-reinforcement-learning-improves-multimodal-reasoning--arxiv-2603.25720/2026-06-19T12:15:10.957Z https://www.opentrain.ai/papers/out-of-sight-but-not-out-of-mind-hybrid-memory-for-dynamic-video-world-models--arxiv-2603.25716/2026-06-17T13:31:40.592Z https://www.opentrain.ai/papers/s2d2-fast-decoding-for-diffusion-llms-via-training-free-self-speculation--arxiv-2603.25702/2026-06-12T04:41:20.548Z https://www.opentrain.ai/papers/self-improvement-of-large-language-models-a-technical-overview-and-future-outloo--arxiv-2603.25681/2026-06-20T05:29:14.889Z https://www.opentrain.ai/papers/is-mathematical-problem-solving-expertise-in-large-language-models-associated-wi--arxiv-2603.25633/2026-06-19T12:13:49.044Z https://www.opentrain.ai/papers/picon-a-multi-turn-interrogation-framework-for-evaluating-persona-agent-consiste--arxiv-2603.25620/2026-06-19T05:23:57.513Z https://www.opentrain.ai/papers/demographic-fairness-in-multimodal-llms-a-benchmark-of-gender-and-ethnicity-bias--arxiv-2603.25613/2026-06-20T01:22:27.421Z https://www.opentrain.ai/papers/revisiting-on-policy-distillation-empirical-failure-modes-and-simple-fixes--arxiv-2603.25562/2026-06-19T05:25:19.011Z https://www.opentrain.ai/papers/ecothink-a-green-adaptive-inference-framework-for-sustainable-and-accessible-age--arxiv-2603.25498/2026-06-18T18:59:26.533Z https://www.opentrain.ai/papers/cross-model-disagreement-as-a-label-free-correctness-signal--arxiv-2603.25450/2026-06-19T04:30:37.402Z https://www.opentrain.ai/papers/from-manipulation-to-mistrust-explaining-diverse-micro-video-misinformation-for--arxiv-2603.25423/2026-06-19T05:24:40.503Z https://www.opentrain.ai/papers/navigating-the-prompt-space-improving-llm-classification-of-social-science-texts--arxiv-2603.25422/2026-06-18T12:05:29.692Z https://www.opentrain.ai/papers/tapo-translation-augmented-policy-optimization-for-multilingual-mathematical-rea--arxiv-2603.25419/2026-06-20T06:19:47.670Z https://www.opentrain.ai/papers/beyond-content-safety-real-time-monitoring-for-reasoning-vulnerabilities-in-larg--arxiv-2603.25412/2026-06-19T05:23:47.537Z https://www.opentrain.ai/papers/system-design-for-maintaining-internal-state-consistency-in-long-horizon-robotic--arxiv-2603.25405/2026-06-19T05:24:45.515Z https://www.opentrain.ai/papers/large-language-model-as-token-compressor-and-decompressor--arxiv-2603.25340/2026-06-18T18:48:22.698Z https://www.opentrain.ai/papers/ad-care-a-guideline-grounded-modality-agnostic-llm-agent-for-real-world-alzheime--arxiv-2603.25322/2026-06-18T12:07:42.560Z https://www.opentrain.ai/papers/separate-before-you-compress-the-wwho-tokenization-architecture--arxiv-2603.25309/2026-06-18T15:55:54.687Z https://www.opentrain.ai/papers/sliderquant-accurate-post-training-quantization-for-llms--arxiv-2603.25284/2026-06-19T12:15:13.626Z https://www.opentrain.ai/papers/craft-grounded-multi-agent-coordination-under-partial-information--arxiv-2603.25268/2026-06-06T16:13:35.047Z https://www.opentrain.ai/papers/molquest-a-benchmark-for-agentic-evaluation-of-abductive-reasoning-in-chemical-s--arxiv-2603.25253/2026-06-19T05:23:54.813Z https://www.opentrain.ai/papers/probabilistic-concept-graph-reasoning-for-multimodal-misinformation-detection--arxiv-2603.25203/2026-06-18T09:46:59.313Z https://www.opentrain.ai/papers/photon-speedup-volume-understanding-with-efficient-multimodal-large-language-mod--arxiv-2603.25155/2026-06-18T08:06:32.827Z https://www.opentrain.ai/papers/omind-framework-for-knowledge-grounded-finetuning-and-multi-turn-dialogue-benchm--arxiv-2603.25105/2026-06-18T13:08:14.844Z https://www.opentrain.ai/papers/an-explainable-ensemble-learning-framework-for-crop-classification-with-optimize--arxiv-2603.25070/2026-06-19T05:23:42.103Z https://www.opentrain.ai/papers/topopilot-reliable-conversational-workflow-automation-for-topological-data-analy--arxiv-2603.25063/2026-06-19T12:13:19.111Z https://www.opentrain.ai/papers/closing-the-confidence-faithfulness-gap-in-large-language-models--arxiv-2603.25052/2026-06-17T02:38:21.427Z https://www.opentrain.ai/papers/can-mllms-read-students-minds-unpacking-multimodal-error-analysis-in-handwritten--arxiv-2603.24961/2026-06-19T01:33:56.801Z https://www.opentrain.ai/papers/reaching-beyond-the-mode-rl-for-distributional-reasoning-in-language-models--arxiv-2603.24844/2026-06-19T05:24:44.256Z https://www.opentrain.ai/papers/prune-as-you-generate-online-rollout-pruning-for-faster-and-better-rlvr--arxiv-2603.24840/2026-06-20T00:07:27.976Z https://www.opentrain.ai/papers/march-multi-agent-reinforced-self-check-for-llm-hallucination--arxiv-2603.24579/2026-06-19T08:53:23.915Z https://www.opentrain.ai/papers/vfig-vectorizing-complex-figures-in-svg-with-vision-language-models--arxiv-2603.24575/2026-06-18T08:05:44.892Z https://www.opentrain.ai/papers/evaluating-chunking-strategies-for-retrieval-augmented-generation-in-oil-and-gas--arxiv-2603.24556/2026-06-18T11:09:38.744Z https://www.opentrain.ai/papers/representation-learning-to-study-temporal-dynamics-in-tutorial-scaffolding--arxiv-2603.24535/2026-06-19T12:11:01.744Z https://www.opentrain.ai/papers/ui-voyager-a-self-evolving-gui-agent-learning-via-failed-experience--arxiv-2603.24533/2026-06-20T06:19:42.864Z https://www.opentrain.ai/papers/multi-agent-reasoning-with-consistency-verification-improves-uncertainty-calibra--arxiv-2603.24481/2026-06-17T13:38:24.566Z https://www.opentrain.ai/papers/mechanic-sorrifier-driven-formal-decomposition-workflow-for-automated-theorem-pr--arxiv-2603.24465/2026-06-18T18:08:45.134Z https://www.opentrain.ai/papers/clawkeeper-comprehensive-safety-protection-for-openclaw-agents-through-skills-pl--arxiv-2603.24414/2026-06-19T09:45:50.295Z https://www.opentrain.ai/papers/pingala-prosody-aware-decoding-for-sanskrit-poetry-generation--arxiv-2603.24413/2026-06-18T11:33:13.802Z https://www.opentrain.ai/papers/when-ai-meets-early-childhood-education-large-language-models-as-assessment-team--arxiv-2603.24389/2026-06-20T04:50:58.678Z https://www.opentrain.ai/papers/molevolve-llm-guided-evolutionary-search-for-interpretable-molecular-optimizatio--arxiv-2603.24382/2026-06-19T15:11:33.781Z https://www.opentrain.ai/papers/large-language-model-guided-incentive-aware-reward-design-for-cooperative-multi--arxiv-2603.24324/2026-06-16T16:30:38.571Z https://www.opentrain.ai/papers/semantic-alignment-across-ancient-egyptian-language-stages-via-normalization-awa--arxiv-2603.24258/2026-06-18T20:52:18.811Z https://www.opentrain.ai/papers/invisible-threats-from-model-context-protocol-generating-stealthy-injection-payl--arxiv-2603.24203/2026-06-19T05:25:34.619Z https://www.opentrain.ai/papers/alignment-reduces-expressed-but-not-encoded-gender-bias-a-unified-framework-and--arxiv-2603.24125/2026-06-20T00:32:08.208Z https://www.opentrain.ai/papers/the-alignment-tax-response-homogenization-in-aligned-llms-and-its-implications-f--arxiv-2603.24124/2026-06-19T18:33:17.352Z https://www.opentrain.ai/papers/llmpedia-a-transparent-framework-to-materialize-an-llm-s-encyclopedic-knowledge--arxiv-2603.24080/2026-06-18T07:29:28.724Z https://www.opentrain.ai/papers/thinking-with-tables-enhancing-multi-modal-tabular-understanding-via-neuro-symbo--arxiv-2603.24004/2026-06-19T05:25:11.270Z https://www.opentrain.ai/papers/the-price-reversal-phenomenon-when-cheaper-reasoning-models-cost-more--arxiv-2603.23971/2026-06-19T13:52:45.355Z https://www.opentrain.ai/papers/from-ai-assistant-to-ai-scientist-autonomous-discovery-of-llm-rl-algorithms-with--arxiv-2603.23951/2026-06-19T05:23:38.456Z https://www.opentrain.ai/papers/omniacbench-a-benchmark-for-evaluating-context-grounded-acoustic-control-in-omni--arxiv-2603.23938/2026-06-19T05:23:55.910Z https://www.opentrain.ai/papers/self-distillation-for-multi-token-prediction--arxiv-2603.23911/2026-06-20T05:50:15.719Z https://www.opentrain.ai/papers/analogagent-self-improving-analog-circuit-design-automation-with-llm-agents--arxiv-2603.23910/2026-06-19T05:25:56.640Z https://www.opentrain.ai/papers/duplex-agentic-dual-system-planning-via-llm-driven-information-extraction--arxiv-2603.23909/2026-06-15T21:42:01.579Z https://www.opentrain.ai/papers/scoop-semantic-consistent-opinion-pooling-for-uncertainty-quantification-in-mult--arxiv-2603.23853/2026-06-20T05:49:40.844Z https://www.opentrain.ai/papers/beliefshift-benchmarking-temporal-belief-consistency-and-opinion-drift-in-llm-ag--arxiv-2603.23848/2026-06-19T05:25:36.408Z https://www.opentrain.ai/papers/language-model-planners-do-not-scale-but-do-formalizers--arxiv-2603.23844/2026-06-18T11:37:35.096Z https://www.opentrain.ai/papers/vehiclemembench-an-executable-benchmark-for-multi-user-long-term-memory-in-in-ve--arxiv-2603.23840/2026-06-19T05:25:55.792Z https://www.opentrain.ai/papers/islamicmmlu-a-benchmark-for-evaluating-llms-on-islamic-knowledge--arxiv-2603.23750/2026-06-18T23:36:35.496Z https://www.opentrain.ai/papers/llms-do-not-grade-essays-like-humans--arxiv-2603.23714/2026-06-18T22:56:11.307Z https://www.opentrain.ai/papers/the-diminishing-returns-of-early-exit-decoding-in-modern-llms--arxiv-2603.23701/2026-06-18T12:28:16.752Z https://www.opentrain.ai/papers/swiss-bench-sbp-002-a-frontier-model-comparison-on-swiss-legal-and-regulatory-ta--arxiv-2603.23646/2026-06-18T15:52:09.696Z https://www.opentrain.ai/papers/evaluating-a-multi-agent-voice-enabled-smart-speaker-for-care-homes-a-safety-foc--arxiv-2603.23625/2026-06-18T18:20:36.871Z https://www.opentrain.ai/papers/vision-on-request-enhanced-vllm-efficiency-with-sparse-dynamically-selected-visi--arxiv-2603.23495/2026-06-19T14:53:49.389Z https://www.opentrain.ai/papers/speceyes-accelerating-agentic-multimodal-llms-via-speculative-perception-and-pla--arxiv-2603.23483/2026-06-18T18:11:53.068Z https://www.opentrain.ai/papers/sortedrl-accelerating-rl-training-for-llms-through-online-length-aware-schedulin--arxiv-2603.23414/2026-06-19T05:25:17.989Z https://www.opentrain.ai/papers/off-policy-value-based-reinforcement-learning-for-large-language-models--arxiv-2603.23355/2026-06-17T11:47:32.032Z https://www.opentrain.ai/papers/safeseek-universal-attribution-of-safety-circuits-in-language-models--arxiv-2603.23268/2026-06-19T05:23:48.417Z https://www.opentrain.ai/papers/is-ai-catching-up-to-human-expression-exploring-emotion-personality-authorship-a--arxiv-2603.23251/2026-06-17T21:33:27.785Z https://www.opentrain.ai/papers/decoding-ai-authorship-can-llms-truly-mimic-human-style-across-literature-and-po--arxiv-2603.23219/2026-06-19T12:13:46.369Z https://www.opentrain.ai/papers/the-illusion-of-reasoning-step-level-evaluation-reveals-decorative-chain-of-thou--arxiv-2603.22816/2026-06-18T05:38:52.164Z https://www.opentrain.ai/papers/language-models-can-explain-visual-features-via-steering--arxiv-2603.22593/2026-06-01T14:17:04.599Z https://www.opentrain.ai/papers/lie-to-me-how-faithful-is-chain-of-thought-reasoning-in-reasoning-models--arxiv-2603.22582/2026-06-19T03:52:18.550Z https://www.opentrain.ai/papers/capitu-a-benchmark-for-evaluating-instruction-following-in-brazilian-portuguese--arxiv-2603.22576/2026-06-19T05:24:46.191Z https://www.opentrain.ai/papers/ego2web-a-web-agent-benchmark-grounded-in-egocentric-videos--arxiv-2603.22529/2026-06-20T06:35:34.997Z https://www.opentrain.ai/papers/tiny-inference-time-scaling-with-latent-verifiers--arxiv-2603.22492/2026-06-20T05:21:31.948Z https://www.opentrain.ai/papers/llm-guided-headline-rewriting-for-clickability-enhancement-without-clickbait--arxiv-2603.22459/2026-06-19T05:24:51.116Z https://www.opentrain.ai/papers/sparse-but-critical-a-token-level-analysis-of-distributional-shifts-in-rlvr-fine--arxiv-2603.22446/2026-06-20T06:35:42.827Z https://www.opentrain.ai/papers/worldcache-content-aware-caching-for-accelerated-video-world-models--arxiv-2603.22286/2026-06-20T10:04:45.225Z https://www.opentrain.ai/papers/tico-time-controllable-training-for-spoken-dialogue-models--arxiv-2603.22267/2026-06-19T00:29:23.332Z https://www.opentrain.ai/papers/from-static-templates-to-dynamic-runtime-graphs-a-survey-of-workflow-optimizatio--arxiv-2603.22386/2026-06-20T05:49:37.757Z https://www.opentrain.ai/papers/memdlm-memory-enhanced-dlm-training--arxiv-2603.22241/2026-06-17T03:51:45.268Z https://www.opentrain.ai/papers/gumbel-distillation-for-parallel-text-generation--arxiv-2603.22216/2026-06-20T06:14:18.828Z https://www.opentrain.ai/papers/dual-space-knowledge-distillation-with-key-query-matching-for-large-language-mod--arxiv-2603.22056/2026-06-20T00:30:59.229Z https://www.opentrain.ai/papers/rom-real-time-overthinking-mitigation-via-streaming-detection-and-intervention--arxiv-2603.22016/2026-06-20T08:22:43.375Z https://www.opentrain.ai/papers/securebreak-a-dataset-towards-safe-and-secure-models--arxiv-2603.21975/2026-06-20T05:36:26.380Z https://www.opentrain.ai/papers/demystifying-reinforcement-learning-for-long-horizon-tool-using-agents-a-compreh--arxiv-2603.21972/2026-06-20T05:50:22.255Z https://www.opentrain.ai/papers/parameter-efficient-fine-tuning-for-medical-text-summarization-a-comparative-stu--arxiv-2603.21970/2026-06-19T05:25:50.711Z https://www.opentrain.ai/papers/p-2o-joint-policy-and-prompt-optimization--arxiv-2603.21877/2026-06-19T05:25:19.072Z https://www.opentrain.ai/papers/manifold-aware-exploration-for-reinforcement-learning-in-video-generation--arxiv-2603.21872/2026-06-19T19:05:16.919Z https://www.opentrain.ai/papers/agentic-personas-for-adaptive-scientific-explanations-with-knowledge-graphs--arxiv-2603.21846/2026-06-19T19:02:15.900Z https://www.opentrain.ai/papers/semeval-2026-task-12-abductive-event-reasoning-towards-real-world-event-causal-i--arxiv-2603.21720/2026-06-14T08:45:27.901Z https://www.opentrain.ai/papers/rethinking-token-reduction-for-large-vision-language-models--arxiv-2603.21701/2026-06-20T05:50:16.279Z https://www.opentrain.ai/papers/optimizing-multi-agent-weather-captioning-via-text-gradient-descent-a-training-f--arxiv-2603.21673/2026-06-19T19:00:34.261Z https://www.opentrain.ai/papers/agenticrec-end-to-end-tool-integrated-policy-optimization-for-ranking-oriented-r--arxiv-2603.21613/2026-06-19T19:09:44.466Z https://www.opentrain.ai/papers/cerebra-a-multidisciplinary-ai-board-for-multimodal-dementia-characterization-an--arxiv-2603.21597/2026-06-19T19:09:52.516Z https://www.opentrain.ai/papers/spatio-temporal-attention-enhanced-multi-agent-drl-for-uav-assisted-wireless-net--arxiv-2603.21594/2026-06-19T19:04:36.952Z https://www.opentrain.ai/papers/mind-over-space-can-multimodal-large-language-models-mentally-navigate--arxiv-2603.21577/2026-06-19T19:12:54.405Z https://www.opentrain.ai/papers/prism-breaking-the-o-n-memory-wall-in-long-context-llm-inference-via-o-1-photoni--arxiv-2603.21576/2026-06-19T19:04:57.758Z https://www.opentrain.ai/papers/adaptive-robust-estimator-for-multi-agent-reinforcement-learning--arxiv-2603.21574/2026-06-19T05:24:03.384Z https://www.opentrain.ai/papers/counterfactual-credit-policy-optimization-for-multi-agent-collaboration--arxiv-2603.21563/2026-06-19T19:08:44.295Z https://www.opentrain.ai/papers/what-do-world-models-learn-in-rl-probing-latent-representations-in-learned-envir--arxiv-2603.21546/2026-06-19T19:03:40.850Z https://www.opentrain.ai/papers/safepilot-a-framework-for-assuring-llm-enabled-cyber-physical-systems--arxiv-2603.21523/2026-06-20T05:23:26.079Z https://www.opentrain.ai/papers/efficient-failure-management-for-multi-agent-systems-with-reasoning-trace-repres--arxiv-2603.21522/2026-06-19T18:58:46.083Z https://www.opentrain.ai/papers/unified-mas-universally-generating-domain-specific-nodes-for-empowering-automati--arxiv-2603.21475/2026-06-19T05:25:18.234Z https://www.opentrain.ai/papers/cross-context-verification-hierarchical-detection-of-benchmark-contamination-thr--arxiv-2603.21454/2026-06-19T05:25:54.707Z https://www.opentrain.ai/papers/kg-hopper-empowering-compact-open-llms-with-knowledge-graph-reasoning-via-reinfo--arxiv-2603.21440/2026-06-19T05:25:58.950Z https://www.opentrain.ai/papers/llm-powered-workflow-optimization-for-multidisciplinary-software-development-an--arxiv-2603.21439/2026-06-19T06:42:21.571Z https://www.opentrain.ai/papers/domagent-leveraging-knowledge-graphs-and-case-based-reasoning-for-domain-specifi--arxiv-2603.21430/2026-06-19T19:06:15.539Z https://www.opentrain.ai/papers/pivotrl-high-accuracy-agentic-post-training-at-low-compute-cost--arxiv-2603.21383/2026-06-19T05:23:56.370Z https://www.opentrain.ai/papers/a-transformer-architecture-alteration-to-incentivise-externalised-reasoning--arxiv-2603.21376/2026-06-19T18:59:13.790Z https://www.opentrain.ai/papers/adarubric-task-adaptive-rubrics-for-llm-agent-evaluation--arxiv-2603.21362/2026-06-20T07:53:36.011Z https://www.opentrain.ai/papers/roboalign-learning-test-time-reasoning-for-language-action-alignment-in-vision-l--arxiv-2603.21341/2026-06-19T05:23:42.606Z https://www.opentrain.ai/papers/coinbench-moving-beyond-individual-perspectives-to-collective-intent-understandi--arxiv-2603.21329/2026-06-19T18:58:22.258Z