https://www.opentrain.ai/papers/loomvideo-unifying-multimodal-inputs-into-video-generation-and-editing--arxiv-2606.06042/2026-06-19T08:40:32.516Z https://www.opentrain.ai/papers/compress-distill-reasoning-trace-compression-for-efficient-knowledge-distillatio--arxiv-2606.05988/2026-06-19T08:39:21.261Z https://www.opentrain.ai/papers/world-language-action-model-for-unified-world-modeling-language-reasoning-and-ac--arxiv-2606.05979/2026-06-19T12:18:38.508Z https://www.opentrain.ai/papers/llm-explainability-with-counterfactual-chains-and-causal-graphs--arxiv-2606.05972/2026-06-19T08:41:36.225Z https://www.opentrain.ai/papers/retrospective-harness-optimization-improving-llm-agents-via-self-preference-over--arxiv-2606.05922/2026-06-19T08:40:19.284Z https://www.opentrain.ai/papers/learning-geometric-representations-from-videos-for-spatial-intelligent-multimoda--arxiv-2606.05833/2026-06-14T15:49:57.392Z https://www.opentrain.ai/papers/imagine-before-you-predict-interleaved-latent-visual-reasoning-for-video-event-p--arxiv-2606.05769/2026-06-19T01:34:44.566Z https://www.opentrain.ai/papers/subtlememory-a-benchmark-for-fine-grained-relational-memory-discrimination-in-lo--arxiv-2606.05761/2026-06-19T08:40:32.997Z https://www.opentrain.ai/papers/cosine-misleads-auxiliary-losses-reshape-vision-language-models-not-their-latent--arxiv-2606.05753/2026-06-19T08:39:59.766Z https://www.opentrain.ai/papers/answer-presence-drives-rag-rewriting-gains--arxiv-2606.05633/2026-06-18T04:29:21.895Z https://www.opentrain.ai/papers/adaplanbench-evaluating-adaptive-planning-in-large-language-model-agents-under-w--arxiv-2606.05622/2026-06-19T08:40:18.771Z https://www.opentrain.ai/papers/worldbench-a-challenging-and-visually-diverse-multimodal-reasoning-benchmark--arxiv-2606.06538/2026-06-19T12:21:31.381Z https://www.opentrain.ai/papers/aura-intent-directed-probing-for-implicit-need-surfacing-in-situated-llm-agents--arxiv-2606.05557/2026-06-19T01:34:58.167Z https://www.opentrain.ai/papers/brepclip-contrastive-multimodal-pretraining-on-brep-primitives-for-cad-understan--arxiv-2606.05515/2026-06-18T19:02:37.717Z https://www.opentrain.ai/papers/agents-last-exam--arxiv-2606.05405/2026-06-19T09:00:19.846Z https://www.opentrain.ai/papers/what-should-agents-say-action-state-communication-for-efficient-multi-agent-syst--arxiv-2606.05304/2026-06-19T08:54:19.835Z https://www.opentrain.ai/papers/self-evaluation-is-already-there-eliciting-latent-judge-calibration-in-base-llms--arxiv-2606.05122/2026-06-19T08:39:36.679Z https://www.opentrain.ai/papers/evaluating-large-language-models-in-dynamic-clinical-decision-making-with-standa--arxiv-2606.05112/2026-06-18T05:06:15.244Z https://www.opentrain.ai/papers/videokr-towards-knowledge-and-reasoning-intensive-video-understanding--arxiv-2606.05259/2026-06-19T23:27:29.225Z https://www.opentrain.ai/papers/flash-wam-modality-aware-distillation-for-world-action-models--arxiv-2606.05254/2026-06-19T12:21:51.846Z https://www.opentrain.ai/papers/probing-outcome-level-resemblance-and-mechanism-level-alignment-in-llm-risk-deci--arxiv-2606.04978/2026-06-19T08:41:27.408Z https://www.opentrain.ai/papers/reproducing-analyzing-and-detecting-reward-hacking-in-rubric-based-reinforcement--arxiv-2606.04923/2026-06-18T19:02:15.101Z https://www.opentrain.ai/papers/grail-gradient-reweighted-advantages-for-reinforcement-learning-with-verifiable--arxiv-2606.04889/2026-06-19T08:40:20.435Z https://www.opentrain.ai/papers/rethinking-continual-experience-internalization-for-self-evolving-llm-agents--arxiv-2606.04703/2026-06-19T12:21:31.567Z https://www.opentrain.ai/papers/echo-infinity-learning-evolving-memory-for-real-time-infinite-video-generation--arxiv-2606.04527/2026-06-19T01:36:30.770Z https://www.opentrain.ai/papers/mapagent-an-industrial-grade-agentic-framework-for-city-scale-lane-level-map-gen--arxiv-2606.04513/2026-06-17T15:56:17.004Z https://www.opentrain.ai/papers/sparda-sparse-decoupled-attention-for-efficient-long-context-llm-inference--arxiv-2606.04511/2026-06-19T08:41:22.276Z https://www.opentrain.ai/papers/sepo-self-evolving-prompt-agent-for-system-prompt-optimization--arxiv-2606.04465/2026-06-19T19:21:39.751Z https://www.opentrain.ai/papers/stateful-visual-encoders-for-vision-language-models--arxiv-2606.04433/2026-06-19T22:10:15.170Z https://www.opentrain.ai/papers/online-skill-learning-for-web-agents-via-state-grounded-dynamic-retrieval--arxiv-2606.04391/2026-06-19T08:39:59.672Z https://www.opentrain.ai/papers/video2lora-parametric-video-internalization-for-vision-language-models--arxiv-2606.04351/2026-06-18T05:59:45.850Z https://www.opentrain.ai/papers/can-generalist-agents-automate-data-curation--arxiv-2606.04261/2026-06-18T21:26:42.192Z https://www.opentrain.ai/papers/lean4agent-formal-modeling-and-verification-for-agent-workflow-and-trajectory--arxiv-2606.06523/2026-06-19T10:31:23.023Z https://www.opentrain.ai/papers/skill-rm-unifying-heterogeneous-evaluation-criteria-via-agent-skill--arxiv-2606.03980/2026-06-19T01:00:48.179Z https://www.opentrain.ai/papers/language-models-need-sleep-learning-to-self-modify-and-consolidate-memories--arxiv-2606.03979/2026-06-19T08:39:20.179Z https://www.opentrain.ai/papers/agentic-chain-of-thought-steering-for-efficient-and-controllable-llm-reasoning--arxiv-2606.03965/2026-06-19T11:33:51.574Z https://www.opentrain.ai/papers/seaotter-sensor-embedded-autoencoding-with-one-time-transcode-for-efficient-reco--arxiv-2606.03940/2026-06-19T08:41:37.103Z https://www.opentrain.ai/papers/value-aware-stochastic-kv-cache-eviction-for-reasoning-models--arxiv-2606.03928/2026-06-19T02:11:25.076Z https://www.opentrain.ai/papers/benchmarking-visual-state-tracking-in-multimodal-video-understanding--arxiv-2606.03920/2026-06-19T08:54:44.705Z https://www.opentrain.ai/papers/agent-libos-a-library-os-inspired-runtime-for-long-running-capability-controlled--arxiv-2606.03895/2026-06-19T12:51:43.302Z https://www.opentrain.ai/papers/ovo-s-bench-a-hierarchical-benchmark-for-streaming-spatial-intelligence-in-multi--arxiv-2606.03890/2026-06-18T17:02:19.464Z https://www.opentrain.ai/papers/evods-self-evolving-autonomous-data-science-agent-with-skill-learning-and-contex--arxiv-2606.03841/2026-06-19T20:28:41.867Z https://www.opentrain.ai/papers/reasoning-over-grammar-can-synthetic-linguistic-reasoning-traces-enhance-low-res--arxiv-2606.03782/2026-06-19T08:40:21.053Z https://www.opentrain.ai/papers/ultralytics-yolo26-unified-real-time-end-to-end-vision-models--arxiv-2606.03748/2026-06-19T12:20:20.137Z https://www.opentrain.ai/papers/qwen-image-flash-beyond-objective-design--arxiv-2606.03746/2026-06-19T08:41:27.743Z https://www.opentrain.ai/papers/text-to-image-models-need-less-from-text-encoders-than-you-think--arxiv-2606.03715/2026-06-18T15:08:35.441Z https://www.opentrain.ai/papers/when-graph-tokens-sink-a-mechanistic-analysis-of-graph-language-models--arxiv-2606.03712/2026-06-19T21:12:25.005Z https://www.opentrain.ai/papers/world-models-meet-language-models-on-the-complementarity-of-concrete-and-abstrac--arxiv-2606.03603/2026-06-19T12:19:38.498Z https://www.opentrain.ai/papers/eliciting-complex-spatial-reasoning-in-mllms-through-wide-baseline-matching--arxiv-2606.03577/2026-06-20T02:00:51.182Z https://www.opentrain.ai/papers/kvarn-variance-normalized-kv-cache-quantization-mitigates-error-accumulation-in--arxiv-2606.03458/2026-06-19T12:19:41.135Z https://www.opentrain.ai/papers/large-language-models-are-overconfident-in-their-own-responses--arxiv-2606.03437/2026-06-11T07:47:56.981Z https://www.opentrain.ai/papers/memtrain-self-supervised-context-memory-training--arxiv-2606.03197/2026-06-20T02:36:43.734Z https://www.opentrain.ai/papers/evotrainer-co-evolving-llm-policies-and-training-harnesses-for-autonomous-agenti--arxiv-2606.03108/2026-06-19T12:51:49.122Z https://www.opentrain.ai/papers/small-rl-controller-large-language-model-rl-guided-adaptive-sampling-for-test-ti--arxiv-2606.03102/2026-06-18T07:07:51.501Z https://www.opentrain.ai/papers/the-shadow-price-of-reasoning-economic-perspective-on-optimal-budget-allocation--arxiv-2606.03092/2026-06-19T08:41:38.003Z https://www.opentrain.ai/papers/self-distilled-policy-gradient--arxiv-2606.04036/2026-06-19T08:54:21.611Z https://www.opentrain.ai/papers/auditflow-executable-symbolic-environments-for-structured-financial-reporting-ve--arxiv-2606.03031/2026-06-18T19:53:00.829Z https://www.opentrain.ai/papers/the-road-ahead-in-autonomous-driving-the-kitscenes-multimodal-dataset--arxiv-2606.02956/2026-06-19T00:43:59.400Z https://www.opentrain.ai/papers/cosmos-3-omnimodal-world-models-for-physical-ai--arxiv-2606.02800/2026-06-18T04:06:43.949Z https://www.opentrain.ai/papers/aura-action-gated-memory-for-robot-policies-at-constant-vram--arxiv-2606.02775/2026-06-19T08:41:22.752Z https://www.opentrain.ai/papers/mitigating-perceptual-judgment-bias-in-multimodal-llm-as-a-judge-via-perceptual--arxiv-2606.02578/2026-06-18T05:15:16.009Z https://www.opentrain.ai/papers/filter-then-reweight-rethinking-optimization-granularity-in-on-policy-distillati--arxiv-2606.02684/2026-06-12T08:00:34.898Z https://www.opentrain.ai/papers/adacodec-a-predictive-visual-code-for-video-mllms--arxiv-2606.02569/2026-06-19T12:22:09.323Z https://www.opentrain.ai/papers/vlms-are-good-teachers-for-video-reasoning-via-adaptive-test-time-optimization--arxiv-2606.02564/2026-06-19T12:22:26.163Z https://www.opentrain.ai/papers/mcp-persona-benchmarking-llm-agents-on-real-world-personal-applications-via-envi--arxiv-2606.02470/2026-06-19T08:57:51.849Z https://www.opentrain.ai/papers/k-browsecomp-a-web-browsing-agent-benchmark-grounded-in-korean-contexts--arxiv-2606.02404/2026-06-17T10:57:53.134Z https://www.opentrain.ai/papers/a-local-perturbation-theory-for-cross-domain-interference-and-recovery-in-multi--arxiv-2606.02398/2026-06-18T11:18:01.511Z https://www.opentrain.ai/papers/policy-and-world-modeling-co-training-for-language-agents--arxiv-2606.02388/2026-06-19T08:39:50.911Z https://www.opentrain.ai/papers/robosemanticbench-diagnosing-semantic-grounding-in-action-prediction-for-vla-mod--arxiv-2606.02277/2026-06-19T08:39:22.070Z https://www.opentrain.ai/papers/geometric-latent-reasoning-induces-shorter-generations-in-llms--arxiv-2606.02248/2026-06-19T12:21:35.576Z https://www.opentrain.ai/papers/openwebrl-demystifying-online-multi-turn-reinforcement-learning-for-visual-web-a--arxiv-2606.02031/2026-06-19T12:20:33.033Z https://www.opentrain.ai/papers/wall-wm-carving-world-action-modeling-at-the-event-joints--arxiv-2606.01955/2026-06-19T08:39:35.752Z https://www.opentrain.ai/papers/absorbing-complexity-an-interaction-native-knowledge-harness-for-financial-llm-a--arxiv-2606.01886/2026-06-18T17:41:42.095Z https://www.opentrain.ai/papers/layerroute-input-conditioned-adaptive-layer-skipping-via-lora-fine-tuning-for-ag--arxiv-2606.01838/2026-06-19T12:18:51.482Z https://www.opentrain.ai/papers/decentralized-instruction-tuning-conflict-aware-splitting-and-weight-merging--arxiv-2606.01717/2026-06-18T13:05:57.293Z https://www.opentrain.ai/papers/off-the-shelf-llms-as-process-scorers-training-free-alternative-to-prms-for-math--arxiv-2606.01682/2026-06-19T15:33:20.167Z https://www.opentrain.ai/papers/dot-moe-differentiable-optimal-transport-for-moefication--arxiv-2606.01666/2026-06-19T12:19:57.229Z https://www.opentrain.ai/papers/clawhub-security-signals-when-virustotal-static-analysis-and-skillspector-disagr--arxiv-2606.01494/2026-06-19T08:39:35.577Z https://www.opentrain.ai/papers/agent-skills-should-go-beyond-text-the-case-for-visual-skills--arxiv-2606.01414/2026-06-19T12:18:32.864Z https://www.opentrain.ai/papers/longattncomp-cross-family-context-compression-for-long-context-reasoning--arxiv-2606.01336/2026-06-09T02:49:47.364Z https://www.opentrain.ai/papers/saber-benchmarking-operational-safety-of-llm-coding-agents-in-stateful-project-w--arxiv-2606.01317/2026-06-19T08:39:22.799Z https://www.opentrain.ai/papers/skilladaptor-self-adapting-skills-for-llm-agents-from-trajectories--arxiv-2606.01311/2026-06-19T08:54:06.724Z https://www.opentrain.ai/papers/benchevolver-frontier-task-synthesis-via-solution-centric-evolution--arxiv-2606.01286/2026-06-19T08:39:46.085Z https://www.opentrain.ai/papers/trust-region-on-policy-distillation--arxiv-2606.01249/2026-06-19T10:58:55.239Z https://www.opentrain.ai/papers/where-to-look-can-foundation-models-reach-a-target-viewpoint-through-active-expl--arxiv-2606.01247/2026-06-18T11:13:38.364Z https://www.opentrain.ai/papers/braveguard-from-open-world-threats-to-safer-computer-use-agents--arxiv-2606.01166/2026-06-18T04:10:53.361Z https://www.opentrain.ai/papers/0-wm-a-unified-video-action-world-model-for-robotic-manipulation--arxiv-2606.01027/2026-06-19T08:54:42.668Z https://www.opentrain.ai/papers/fvspec-real-world-property-based-tests-as-lean-challenges--arxiv-2606.01008/2026-06-19T22:05:54.719Z https://www.opentrain.ai/papers/robostressbench-benchmarking-vlm-robustness-to-physical-visual-stress-in-embodie--arxiv-2606.00828/2026-06-18T06:01:42.905Z https://www.opentrain.ai/papers/supermemory-vqa-an-egocentric-visual-question-answering-benchmark-for-long-horiz--arxiv-2606.00825/2026-06-05T02:33:52.065Z https://www.opentrain.ai/papers/fineverify-scaling-test-time-compute-with-fine-grained-self-verification-for-age--arxiv-2606.00660/2026-06-19T21:40:02.070Z https://www.opentrain.ai/papers/critic-r-improving-agentic-search-using-instruction-tuned-retrievers-with-natura--arxiv-2606.00590/2026-06-19T21:40:14.978Z https://www.opentrain.ai/papers/on-the-limits-of-llm-adaptability-impact-of-model-internalized-priors-on-annotat--arxiv-2606.00467/2026-06-19T21:39:32.676Z https://www.opentrain.ai/papers/sdr-set-distance-rewards-for-radiology-report-generation--arxiv-2606.00440/2026-06-19T21:39:31.090Z https://www.opentrain.ai/papers/stressdream-steering-video-world-models-for-robust-policy-evaluation-and-improve--arxiv-2606.00267/2026-06-19T21:39:31.481Z https://www.opentrain.ai/papers/mindzero-learning-online-mental-reasoning-with-zero-annotations--arxiv-2606.00240/2026-06-19T21:39:28.952Z https://www.opentrain.ai/papers/lumos-nexus-efficient-frequency-bridging-with-homogeneous-latent-space-for-video--arxiv-2605.31603/2026-06-19T12:21:58.979Z https://www.opentrain.ai/papers/linear-scaling-video-vlms-for-long-video-understanding--arxiv-2605.31598/2026-06-19T21:39:37.035Z https://www.opentrain.ai/papers/longtracerl-learning-long-context-reasoning-from-search-agent-trajectories-with--arxiv-2605.31584/2026-06-19T21:40:14.933Z https://www.opentrain.ai/papers/mellum2-technical-report--arxiv-2605.31268/2026-06-19T21:39:51.946Z https://www.opentrain.ai/papers/colleague-skill-automated-ai-skill-generation-via-expert-knowledge-distillation--arxiv-2605.31264/2026-06-17T15:05:51.344Z https://www.opentrain.ai/papers/ivgr-internalizing-visually-grounded-reasoning-for-mllms-with-reinforcement-lear--arxiv-2605.31096/2026-06-19T21:39:36.709Z https://www.opentrain.ai/papers/combinatorial-synthesis-scaling-code-rlvr-via-atomic-decomposition-and-recombina--arxiv-2605.31058/2026-06-19T21:39:35.882Z https://www.opentrain.ai/papers/from-prompt-injection-to-persistent-control-defending-agentic-harness-against-tr--arxiv-2605.31042/2026-06-19T21:40:16.469Z https://www.opentrain.ai/papers/towards-streaming-synchronized-spatial-audio-generation-via-autoregressive-diffu--arxiv-2605.30940/2026-06-19T11:52:32.609Z https://www.opentrain.ai/papers/mineexplorer-evaluating-open-world-exploration-of-mllm-agents-in-minecraft--arxiv-2605.30931/2026-06-19T11:53:43.690Z https://www.opentrain.ai/papers/the-flip-side-of-rlhf-on-policy-feedback-for-reward-model-self-supervised-improv--arxiv-2605.30888/2026-06-19T08:11:51.950Z https://www.opentrain.ai/papers/dmoe-dllms-with-learnable-block-experts--arxiv-2605.30876/2026-06-19T09:49:42.911Z https://www.opentrain.ai/papers/distilling-llm-feedback-for-lean-theorem-proving--arxiv-2605.30861/2026-06-19T21:39:50.059Z https://www.opentrain.ai/papers/hide-and-seek-in-trajectories-discovering-failure-signals-for-vla-runtime-monito--arxiv-2605.30834/2026-06-19T11:52:34.702Z https://www.opentrain.ai/papers/function2scene-3d-indoor-scene-layout-from-functional-specifications--arxiv-2605.30819/2026-06-19T21:39:30.538Z https://www.opentrain.ai/papers/mechvqa-benchmarking-and-enhancing-multimodal-llms-on-comprehensive-mechanical-d--arxiv-2605.30794/2026-06-18T23:36:57.046Z https://www.opentrain.ai/papers/skill-is-not-one-size-fits-all-model-aware-skill-alignment-for-llm-agents--arxiv-2605.30723/2026-06-19T21:39:23.364Z https://www.opentrain.ai/papers/a-multi-ai-agent-framework-enabling-end-to-end-finite-element-analysis-for-solid--arxiv-2606.00138/2026-06-19T21:54:28.592Z https://www.opentrain.ai/papers/harness-updating-is-not-harness-benefit-disentangling-evolution-capabilities-in--arxiv-2605.30621/2026-06-19T21:46:30.118Z https://www.opentrain.ai/papers/prior-availability-in-industrial-visual-sim-to-real-a-review-of-cad-guided-and-c--arxiv-2605.30581/2026-06-19T21:16:55.384Z https://www.opentrain.ai/papers/memory-bound-but-not-bandwidth-limited-the-physical-ai-inference-gap-in-batch-1--arxiv-2605.30571/2026-06-19T21:03:23.019Z https://www.opentrain.ai/papers/tiny-but-trusted-efficient-vision-language-reasoning-for-time-series-anomaly-det--arxiv-2605.30344/2026-06-19T11:51:39.032Z https://www.opentrain.ai/papers/schgen-pcb-schematic-generation-with-semantic-grounded-code-representations--arxiv-2605.30345/2026-06-19T04:38:43.617Z https://www.opentrain.ai/papers/unlocking-the-working-memory-of-large-language-models-for-latent-reasoning--arxiv-2605.30343/2026-06-19T11:52:37.670Z https://www.opentrain.ai/papers/soundnessbench-can-your-ai-scientist-really-tell-good-research-ideas-from-bad-on--arxiv-2605.30329/2026-06-19T21:15:17.917Z https://www.opentrain.ai/papers/reasoning-with-sampling-cutting-at-decision-points--arxiv-2605.30327/2026-06-19T21:18:47.744Z https://www.opentrain.ai/papers/exploring-autonomous-agentic-data-engineering-for-model-specialization--arxiv-2605.30407/2026-06-18T22:27:49.793Z https://www.opentrain.ai/papers/medcase-structured-a-text-to-fhir-dataset-for-benchmarking-diagnostic-reasoning--arxiv-2605.30295/2026-06-19T21:01:46.362Z https://www.opentrain.ai/papers/qwen-vla-unifying-vision-language-action-modeling-across-tasks-environments-and--arxiv-2605.30280/2026-06-19T21:20:28.481Z https://www.opentrain.ai/papers/loong-a-human-like-long-document-translation-agent-with-observe-and-act-adaptive--arxiv-2605.30274/2026-06-19T21:17:21.604Z https://www.opentrain.ai/papers/llumi-improving-llm-writing-assistance-for-mental-health-support-with-online-com--arxiv-2605.30273/2026-06-19T15:27:02.071Z https://www.opentrain.ai/papers/phygenhoi-physically-aware-4d-generation-of-dynamic-human-object-interactions--arxiv-2605.30268/2026-06-19T11:13:44.974Z https://www.opentrain.ai/papers/minwm-a-full-stack-open-source-framework-for-real-time-interactive-video-world-m--arxiv-2605.30263/2026-06-19T14:42:24.740Z https://www.opentrain.ai/papers/how-lora-remembers-a-parametric-memory-law-for-llm-finetuning--arxiv-2605.30260/2026-06-19T01:26:35.731Z https://www.opentrain.ai/papers/stable-layers-fine-tuning-image-layer-decomposition-models-with-vlm-scored-reinf--arxiv-2605.30257/2026-06-19T11:53:37.106Z https://www.opentrain.ai/papers/same-evidence-different-answers-canonical-context-on-policy-distillation-for-mul--arxiv-2605.30251/2026-06-19T06:31:50.589Z https://www.opentrain.ai/papers/knowing-what-to-solve-before-how-preplan-empowered-llm-mathematical-reasoning--arxiv-2605.30245/2026-06-19T01:26:26.925Z https://www.opentrain.ai/papers/do-language-models-track-entities-across-state-changes--arxiv-2605.30233/2026-06-19T11:18:23.760Z https://www.opentrain.ai/papers/how-s-it-going-reinforcement-learning-in-language-models-recruits-a-functional-w--arxiv-2605.30232/2026-06-19T21:17:20.277Z https://www.opentrain.ai/papers/beyond-3d-vqas-injecting-3d-spatial-priors-into-vision-language-models-for-enhan--arxiv-2605.30231/2026-06-19T21:04:43.523Z https://www.opentrain.ai/papers/gruff-llm-pronoun-fidelity-reasoning-and-biases-in-german--arxiv-2605.30214/2026-06-19T01:51:36.431Z https://www.opentrain.ai/papers/meta-cognitive-memory-policy-optimization-for-long-horizon-llm-agents--arxiv-2605.30159/2026-06-19T02:41:38.416Z https://www.opentrain.ai/papers/seal-can-saturated-benchmarks-be-revived-by-llm-as-a-meta-judge--arxiv-2605.30104/2026-06-19T11:53:00.791Z https://www.opentrain.ai/papers/when-cloud-agents-meet-device-agents-lessons-from-hybrid-multi-agent-systems--arxiv-2605.30102/2026-06-18T23:01:32.307Z https://www.opentrain.ai/papers/token-inflation-how-dishonest-providers-can-overcharge-for-large-language-model--arxiv-2605.30040/2026-06-19T21:04:59.637Z https://www.opentrain.ai/papers/domain-specific-data-synthesis-for-llms-via-minimal-sufficient-representation-le--arxiv-2605.30039/2026-06-19T21:16:43.397Z https://www.opentrain.ai/papers/teaching-values-to-machines-simulating-human-like-behavior-in-llms--arxiv-2605.30036/2026-06-19T21:20:00.161Z https://www.opentrain.ai/papers/give-it-space-explicit-disentangling-of-positional-and-semantic-representations--arxiv-2605.30022/2026-06-19T14:08:18.924Z https://www.opentrain.ai/papers/recovering-diversity-without-losing-alignment-a-dpo-recipe-for-post-trained-llms--arxiv-2605.30021/2026-06-19T07:25:00.429Z https://www.opentrain.ai/papers/latent-performance-profiling-of-large-language-models--arxiv-2605.30018/2026-06-19T21:20:24.464Z https://www.opentrain.ai/papers/visualthink-vla-visual-intermediate-reasoning-for-effective-and-low-latency-visi--arxiv-2605.30011/2026-06-19T21:14:31.866Z https://www.opentrain.ai/papers/earlytom-early-token-compression-completes-fast-video-understanding--arxiv-2605.30010/2026-06-19T21:10:31.404Z https://www.opentrain.ai/papers/lara-layer-wise-representation-analysis-for-detecting-data-contamination-in-rl-p--arxiv-2605.29888/2026-06-19T21:11:24.324Z https://www.opentrain.ai/papers/critic-r1-learning-structured-critics-for-retrieval-augmented-generation--arxiv-2605.29886/2026-06-19T01:26:23.713Z https://www.opentrain.ai/papers/towards-verifiable-multimodal-deep-research-a-multi-agent-harness-for-interleave--arxiv-2605.29861/2026-06-19T21:09:09.353Z https://www.opentrain.ai/papers/espo-early-stopping-proximal-policy-optimization--arxiv-2605.29860/2026-06-19T21:10:16.042Z https://www.opentrain.ai/papers/evorubric-self-evolving-rubric-driven-rl-for-open-ended-generation--arxiv-2605.29847/2026-06-19T21:12:13.704Z https://www.opentrain.ai/papers/towards-localized-and-disentangled-knowledge-editing-for-multimodal-large-langua--arxiv-2605.29826/2026-06-19T21:39:42.346Z https://www.opentrain.ai/papers/agentdog-1-5-a-lightweight-and-scalable-alignment-framework-for-ai-agent-safety--arxiv-2605.29801/2026-06-19T21:04:48.093Z https://www.opentrain.ai/papers/saas-self-aware-reinforcement-learning-for-over-search-mitigation-in-agentic-sea--arxiv-2605.29796/2026-06-19T21:39:24.245Z https://www.opentrain.ai/papers/acttraitbench-quantifying-the-knowledge-decision-gap-in-large-language-models-vi--arxiv-2605.29791/2026-06-19T23:37:17.217Z https://www.opentrain.ai/papers/domino-decoupling-causal-modeling-from-autoregressive-drafting-in-speculative-de--arxiv-2605.29707/2026-06-19T21:15:15.655Z https://www.opentrain.ai/papers/verifiable-rewards-beyond-math-and-code-lightweight-corpus-grounded-process-supe--arxiv-2605.29648/2026-06-19T07:28:35.868Z https://www.opentrain.ai/papers/brain-it-vqa-from-brain-signals-to-answers--arxiv-2605.29588/2026-06-18T21:47:10.558Z https://www.opentrain.ai/papers/litecoder-terminal-scaling-long-horizon-terminal-environments-for-learning-langu--arxiv-2605.29559/2026-06-19T21:04:16.413Z https://www.opentrain.ai/papers/phoneworld-scaling-phone-use-agent-environments--arxiv-2605.29486/2026-06-19T21:07:27.758Z https://www.opentrain.ai/papers/towards-human-like-interactive-speech-recognition-with-agentic-correction-and-se--arxiv-2605.29430/2026-06-19T21:08:21.880Z https://www.opentrain.ai/papers/gdsd-reinforcement-learning-as-guided-denoiser-self-distillation-for-diffusion-l--arxiv-2605.29398/2026-06-19T21:40:16.249Z https://www.opentrain.ai/papers/worldmemarena-evaluating-multimodal-agent-memory-through-action-world-interactio--arxiv-2605.29341/2026-06-19T15:26:26.014Z https://www.opentrain.ai/papers/grepseek-training-search-agents-for-direct-corpus-interaction--arxiv-2605.29307/2026-06-19T21:14:27.220Z https://www.opentrain.ai/papers/diagnosing-harmful-continuation-in-answer-correct-long-cot-training-traces--arxiv-2605.29288/2026-06-19T21:17:29.909Z https://www.opentrain.ai/papers/beyond-recall-behavioral-specification-as-an-interpretive-layer-for-ai-personali--arxiv-2605.28969/2026-06-19T21:40:23.428Z https://www.opentrain.ai/papers/gamma-world-generative-multi-agent-world-modeling-beyond-two-players--arxiv-2605.28816/2026-06-19T01:14:19.459Z https://www.opentrain.ai/papers/omniverifier-m1-multimodal-meta-verifier-with-explicit-structured-recalibration--arxiv-2605.28805/2026-06-19T10:17:50.369Z https://www.opentrain.ai/papers/rethinking-memory-as-continuously-evolving-connectivity--arxiv-2605.28773/2026-06-19T14:30:57.830Z https://www.opentrain.ai/papers/memtrace-tracing-and-attributing-errors-in-large-language-model-memory-systems--arxiv-2605.28732/2026-06-19T21:02:30.270Z https://www.opentrain.ai/papers/livebrowsecomp-are-search-agents-searching-or-just-verifying-what-they-already-k--arxiv-2605.28721/2026-06-19T05:09:23.818Z https://www.opentrain.ai/papers/the-importance-of-being-statistically-earnest-a-critical-re-evaluation-of-gsm-sy--arxiv-2605.28700/2026-06-19T21:18:34.336Z https://www.opentrain.ai/papers/gui-cider-mid-training-gui-agents-via-causal-internalization-and-density-aware-e--arxiv-2605.28534/2026-06-19T12:06:52.225Z https://www.opentrain.ai/papers/skill0-5-joint-skill-internalization-and-utilization-for-out-of-distribution-gen--arxiv-2605.28424/2026-06-19T21:10:33.330Z https://www.opentrain.ai/papers/denoiserl-bootstrapping-reasoning-models-to-recover-from-noisy-prefixes--arxiv-2605.28421/2026-06-19T11:52:49.639Z https://www.opentrain.ai/papers/hrbench-benchmarking-and-understanding-thinking-mode-switch-strategies-in-hybrid--arxiv-2605.28398/2026-06-19T21:17:55.386Z https://www.opentrain.ai/papers/pruning-and-distilling-mixture-of-experts-into-dense-language-models--arxiv-2605.28207/2026-06-19T21:06:28.261Z https://www.opentrain.ai/papers/joint-training-of-multi-token-prediction-in-reinforcement-learning-via-optimal-c--arxiv-2605.28184/2026-06-19T21:15:05.820Z https://www.opentrain.ai/papers/when-confidence-misleads-suffix-anchoring-and-anchor-proximity-confidence-modula--arxiv-2605.28181/2026-06-18T00:37:33.546Z https://www.opentrain.ai/papers/or-space-a-full-lifecycle-workspace-benchmark-for-industrial-optimization-agents--arxiv-2605.28158/2026-06-19T21:19:28.149Z https://www.opentrain.ai/papers/long-live-the-balance-information-bottleneck-driven-tree-based-policy-optimizati--arxiv-2605.28109/2026-06-19T21:11:16.485Z https://www.opentrain.ai/papers/asynctool-evaluating-the-asynchronous-function-calling-capability-under-multi-ta--arxiv-2605.27995/2026-06-19T21:11:31.752Z https://www.opentrain.ai/papers/pressure-testing-deception-probes-in-llms-scaling-robustness-and-the-geometry-of--arxiv-2605.27958/2026-06-19T21:06:12.324Z https://www.opentrain.ai/papers/ai-research-agents-narrow-scientific-exploration--arxiv-2605.27905/2026-06-19T21:01:48.111Z https://www.opentrain.ai/papers/vibesearchbench-benchmarking-long-horizon-proactive-search-in-the-wild--arxiv-2605.27882/2026-06-19T21:19:30.553Z https://www.opentrain.ai/papers/revealing-algorithmic-deductive-circuits-for-logical-reasoning--arxiv-2605.27824/2026-06-19T21:03:23.898Z https://www.opentrain.ai/papers/got-a-secret-llm-agents-can-t-keep-it-evaluating-privacy-in-multi-agent-systems--arxiv-2605.27766/2026-06-19T09:58:46.056Z https://www.opentrain.ai/papers/muse-autoskill-self-evolving-agents-via-skill-creation-memory-management-and-eva--arxiv-2605.27366/2026-06-19T02:42:44.518Z https://www.opentrain.ai/papers/mobilemoe-scaling-on-device-mixture-of-experts--arxiv-2605.27358/2026-06-19T21:11:16.408Z https://www.opentrain.ai/papers/alignment-tampering-how-reinforcement-learning-from-human-feedback-is-exploited--arxiv-2605.27355/2026-06-19T21:08:31.571Z https://www.opentrain.ai/papers/sia-self-improving-ai-with-harness-weight-updates--arxiv-2605.27276/2026-06-19T21:09:30.940Z https://www.opentrain.ai/papers/lost-in-sampling-assessing-lexical-reachability-in-llms-via-the-word-coverage-sc--arxiv-2605.27268/2026-06-19T13:37:35.281Z https://www.opentrain.ai/papers/benchmarks-are-not-enough-ramp-for-runtime-assessing-of-agentic-models-in-produc--arxiv-2605.27492/2026-06-19T21:20:15.108Z https://www.opentrain.ai/papers/ge-sim-2-0-a-roadmap-towards-comprehensive-closed-loop-video-world-simulators-fo--arxiv-2605.27491/2026-06-19T21:12:25.934Z https://www.opentrain.ai/papers/mrt-masked-region-transformer-for-layered-image-generation-and-editing-at-scale--arxiv-2605.27235/2026-06-19T21:10:22.048Z https://www.opentrain.ai/papers/learning-to-act-under-noise-enhancing-agent-robustness-via-noisy-environments--arxiv-2605.27209/2026-06-19T21:12:13.425Z https://www.opentrain.ai/papers/vitabench-2-0-evaluating-personalized-and-proactive-agents-in-long-term-user-int--arxiv-2605.27141/2026-06-19T11:51:18.352Z https://www.opentrain.ai/papers/quack-questioning-understanding-and-auditing-communicated-knowledge-in-multimoda--arxiv-2605.27068/2026-06-19T21:14:14.334Z https://www.opentrain.ai/papers/share-more-search-less-collaborative-parallel-thinking-for-efficient-test-time-s--arxiv-2605.27030/2026-06-19T19:45:30.358Z https://www.opentrain.ai/papers/efficient-agentic-reinforcement-learning-with-on-policy-intrinsic-knowledge-boun--arxiv-2605.26952/2026-06-19T18:12:30.711Z https://www.opentrain.ai/papers/balancing-fidelity-and-diversity-in-diffusion-models-via-symmetric-attention-dec--arxiv-2605.27476/2026-06-19T21:13:26.341Z https://www.opentrain.ai/papers/agensflow-a-coordination-policy-substrate-for-multi-agent-systems--arxiv-2605.27466/2026-06-19T11:53:21.638Z https://www.opentrain.ai/papers/rt-lynx-putting-the-gemm-sparsity-in-a-right-way-for-diffusion-models--arxiv-2605.26632/2026-06-19T21:04:24.703Z https://www.opentrain.ai/papers/the-minimax-m2-series-mini-activations-unleashing-max-real-world-intelligence--arxiv-2605.26494/2026-06-19T21:10:13.266Z https://www.opentrain.ai/papers/omniinteract-benchmarking-real-world-streaming-interaction-for-real-time-omnimod--arxiv-2605.26485/2026-06-19T11:53:43.403Z https://www.opentrain.ai/papers/mobilegym-a-verifiable-and-highly-parallel-simulation-platform-for-mobile-gui-ag--arxiv-2605.26114/2026-06-19T03:29:55.354Z https://www.opentrain.ai/papers/from-model-scaling-to-system-scaling-scaling-the-harness-in-agentic-ai--arxiv-2605.26112/2026-06-18T04:16:45.036Z https://www.opentrain.ai/papers/squeezing-capacity-from-multimodal-large-language-models-for-subject-driven-gene--arxiv-2605.26111/2026-06-19T19:28:15.809Z https://www.opentrain.ai/papers/reinforcing-few-step-generators-via-reward-tilted-distribution-matching--arxiv-2605.26108/2026-06-18T22:41:35.682Z https://www.opentrain.ai/papers/instructsam-segment-any-instance-with-any-instructions--arxiv-2605.26102/2026-06-19T11:51:58.905Z https://www.opentrain.ai/papers/language-models-need-sleep--arxiv-2605.26099/2026-06-19T19:42:27.370Z https://www.opentrain.ai/papers/claw-anything-benchmarking-always-on-personal-assistants-with-broader-access-to--arxiv-2605.26086/2026-06-19T11:22:47.968Z https://www.opentrain.ai/papers/when-gradients-collide-failure-modes-of-multi-objective-prompt-optimization-for--arxiv-2605.26046/2026-06-19T21:15:25.315Z https://www.opentrain.ai/papers/llava-onevision-2-towards-next-generation-perceptual-intelligence--arxiv-2605.25979/2026-06-19T03:45:47.058Z https://www.opentrain.ai/papers/anticipate-and-learn-unleashing-idle-time-compute-in-proactive-agents--arxiv-2605.25971/2026-06-19T03:31:58.530Z https://www.opentrain.ai/papers/triplet-block-diffusion-rwkv--arxiv-2605.25969/2026-06-19T21:11:10.992Z https://www.opentrain.ai/papers/agenthijack-benchmarking-computer-use-agent-robustness-to-common-environment-cor--arxiv-2605.25707/2026-06-19T12:46:52.628Z https://www.opentrain.ai/papers/cua-gym-scaling-verifiable-training-environments-and-tasks-for-computer-use-agen--arxiv-2605.25624/2026-06-19T11:53:35.437Z https://www.opentrain.ai/papers/dvao-dynamic-variance-adaptive-advantage-optimization-for-multi-reward-reinforce--arxiv-2605.25604/2026-06-19T21:21:45.750Z https://www.opentrain.ai/papers/personalize-then-store-benchmarking-and-learning-personalized-memory-for-long-ho--arxiv-2605.25535/2026-06-19T11:53:25.155Z https://www.opentrain.ai/papers/not-only-where-but-when-temporal-scheduling-for-rlvr--arxiv-2605.25381/2026-06-19T21:20:17.300Z https://www.opentrain.ai/papers/injecting-image-guidance-into-text-conditioned-diffusion-models-at-inference--arxiv-2605.25191/2026-06-19T12:14:16.319Z https://www.opentrain.ai/papers/directional-alignment-mitigates-reward-hacking-in-reinforcement-learning-for-lan--arxiv-2605.25189/2026-06-19T03:29:42.866Z https://www.opentrain.ai/papers/stream-a-data-centric-framework-for-mining-high-value-task-oriented-dialogues-fr--arxiv-2605.25162/2026-06-19T18:06:35.995Z https://www.opentrain.ai/papers/simuwob-simulating-real-world-mobile-apps-for-fast-and-faithful-gui-agent-benchm--arxiv-2605.25160/2026-06-19T11:53:38.621Z https://www.opentrain.ai/papers/nitp-next-implicit-token-prediction-for-llm-pre-training--arxiv-2605.24956/2026-06-19T21:14:14.735Z https://www.opentrain.ai/papers/macaron-a2ui-a-model-for-generative-ui-in-personal-agents--arxiv-2605.24830/2026-06-19T21:17:15.146Z https://www.opentrain.ai/papers/conf-kv-confidence-aware-kv-cache-eviction-with-mixed-precision-storage-for-long--arxiv-2605.24786/2026-06-19T11:50:54.934Z https://www.opentrain.ai/papers/mix-moe-improving-multilingual-machine-translation-of-large-language-models-thro--arxiv-2605.24681/2026-06-19T03:33:58.672Z https://www.opentrain.ai/papers/vaawit-visual-aware-adaptation-of-large-language-models-for-multilingual-web-ima--arxiv-2605.24675/2026-06-19T21:14:49.906Z https://www.opentrain.ai/papers/silent-failures-in-physical-ai-a-literature-review-of-runtime-action-authorizati--arxiv-2606.00090/2026-06-19T11:52:59.981Z https://www.opentrain.ai/papers/echo-terminal-agents-learn-world-models-for-free--arxiv-2605.24517/2026-06-19T21:17:49.703Z https://www.opentrain.ai/papers/sam-state-adaptive-memory-for-long-horizon-reasoning-agent--arxiv-2605.24468/2026-06-18T08:52:40.737Z https://www.opentrain.ai/papers/seal-synergistic-co-evolution-of-agents-and-learning-environments--arxiv-2605.24426/2026-06-19T21:16:58.757Z https://www.opentrain.ai/papers/beyond-final-answers-auditing-trajectory-level-hallucinations-in-multi-agent-ind--arxiv-2605.24219/2026-06-19T03:37:18.959Z https://www.opentrain.ai/papers/when-does-multi-agent-rl-improve-llm-workflows-workflow-scale-and-policy-sharing--arxiv-2605.24202/2026-06-19T11:47:19.578Z https://www.opentrain.ai/papers/skillevolbench-benchmarking-the-evolution-from-episodic-experience-to-procedural--arxiv-2605.24117/2026-06-19T16:08:41.896Z https://www.opentrain.ai/papers/geo-align-video-generation-alignment-via-metric-geometry-reward--arxiv-2605.23903/2026-06-19T21:14:42.895Z https://www.opentrain.ai/papers/photoflow-agentic-3d-virtual-photography-missions--arxiv-2605.23771/2026-06-19T21:05:12.090Z https://www.opentrain.ai/papers/openskilleval-automatically-auditing-the-open-skill-ecosystem-for-llm-agents--arxiv-2605.23657/2026-06-19T21:20:44.474Z https://www.opentrain.ai/papers/cosplay-cooperative-self-play-at-test-time-with-self-generated-code-and-unit-tes--arxiv-2605.23491/2026-06-19T21:18:21.239Z https://www.opentrain.ai/papers/stepaudio-2-5-technical-report--arxiv-2605.23463/2026-06-19T13:57:52.423Z https://www.opentrain.ai/papers/ssdau-structured-semantic-data-augmentation-for-joint-entity-and-relation-extrac--arxiv-2605.23440/2026-06-19T20:35:57.598Z https://www.opentrain.ai/papers/contrastive-distribution-matching-for-amortized-sequential-monte-carlo-in-discre--arxiv-2605.23346/2026-06-19T21:16:38.959Z https://www.opentrain.ai/papers/scope-simulating-cross-game-operations-in-playable-environments-for-fps-world-mo--arxiv-2605.23345/2026-06-19T21:03:51.267Z https://www.opentrain.ai/papers/evalverse-pipeline-aware-and-expert-calibrated-benchmarking-for-professional-cin--arxiv-2605.23271/2026-06-19T03:30:48.170Z https://www.opentrain.ai/papers/fastkernels-benchmarking-gpu-kernel-generation-in-production--arxiv-2605.23215/2026-06-18T21:57:49.934Z https://www.opentrain.ai/papers/vector-policy-optimization-training-for-diversity-improves-test-time-search--arxiv-2605.22817/2026-06-19T21:01:56.040Z https://www.opentrain.ai/papers/gated-deltanet-2-decoupling-erase-and-write-in-linear-attention--arxiv-2605.22791/2026-06-19T19:40:14.228Z https://www.opentrain.ai/papers/beyond-acoustic-emotion-recognition-multimodal-pathos-analysis-in-political-spee--arxiv-2605.22732/2026-06-19T21:12:21.764Z https://www.opentrain.ai/papers/worldkv-efficient-world-memory-with-world-retrieval-and-compression--arxiv-2605.22718/2026-06-19T11:32:20.162Z https://www.opentrain.ai/papers/swift-sampling-selecting-temporal-surprises-via-taylor-series--arxiv-2605.22678/2026-06-19T11:51:39.719Z https://www.opentrain.ai/papers/self-policy-distillation-via-capability-selective-subspace-projection--arxiv-2605.22675/2026-06-19T03:36:57.862Z https://www.opentrain.ai/papers/sega-spectral-energy-guided-attention-for-resolution-extrapolation-in-diffusion--arxiv-2605.22668/2026-06-19T11:50:47.324Z https://www.opentrain.ai/papers/moral-semantics-survive-machine-translation-cross-lingual-evidence-from-moral-fo--arxiv-2605.22660/2026-06-19T18:58:31.740Z https://www.opentrain.ai/papers/boiling-the-frog-a-multi-turn-benchmark-for-agentic-safety--arxiv-2605.22643/2026-06-19T21:06:50.945Z https://www.opentrain.ai/papers/spreadsheet-rl-advancing-large-language-model-agents-on-realistic-spreadsheet-ta--arxiv-2605.22642/2026-06-19T21:20:11.279Z https://www.opentrain.ai/papers/two-is-better-than-one-a-collapse-free-multi-reward-rlif-training-framework--arxiv-2605.22620/2026-06-19T22:13:59.875Z https://www.opentrain.ai/papers/agentic-clear-automating-multi-level-evaluation-of-llm-agents--arxiv-2605.22608/2026-06-19T08:54:03.797Z https://www.opentrain.ai/papers/beyond-temperature-hyperfitting-as-a-late-stage-geometric-expansion--arxiv-2605.22579/2026-06-19T18:56:48.838Z https://www.opentrain.ai/papers/vgenst-bench-a-benchmark-for-spatio-temporal-reasoning-via-active-video-synthesi--arxiv-2605.22570/2026-06-19T18:58:47.181Z https://www.opentrain.ai/papers/lang-reinforcement-learning-for-multilingual-reasoning-with-language-adaptive-hi--arxiv-2605.22567/2026-06-19T11:53:41.219Z https://www.opentrain.ai/papers/synae-a-framework-for-measuring-the-quality-of-synthetic-data-for-tool-calling-a--arxiv-2605.22564/2026-06-19T21:14:26.680Z https://www.opentrain.ai/papers/fashionlens-toward-versatile-fashion-image-retrieval-via-task-adaptive-learning--arxiv-2605.22552/2026-06-19T21:04:54.842Z https://www.opentrain.ai/papers/spacedg-benchmarking-spatial-intelligence-under-visual-degradation--arxiv-2605.22536/2026-06-19T21:22:00.727Z https://www.opentrain.ai/papers/polite-on-the-surface-wrong-in-practice-a-curated-dataset-for-fixing-honorific-f--arxiv-2605.22487/2026-06-19T21:13:56.304Z https://www.opentrain.ai/papers/defermem-query-time-evidence-distillation-via-reinforcement-learning-for-long-te--arxiv-2605.22411/2026-06-19T01:16:18.025Z https://www.opentrain.ai/papers/unified-data-selection-for-llm-reasoning--arxiv-2605.22389/2026-06-19T11:56:49.792Z https://www.opentrain.ai/papers/bernini-latent-semantic-planning-for-video-diffusion--arxiv-2605.22344/2026-06-19T21:06:37.924Z https://www.opentrain.ai/papers/survive-or-collapse-the-asymmetric-roles-of-data-gating-and-reward-grounding-in--arxiv-2605.22217/2026-06-19T21:04:28.867Z https://www.opentrain.ai/papers/maestro-reinforcement-learning-to-orchestrate-hierarchical-model-skill-ensembles--arxiv-2605.22177/2026-06-19T21:16:21.328Z https://www.opentrain.ai/papers/ratchet-a-minimal-hygiene-recipe-for-self-evolving-llm-agents--arxiv-2605.22148/2026-06-19T13:00:55.772Z https://www.opentrain.ai/papers/psy-chronicle-a-structured-pipeline-for-synthesizing-long-horizon-campus-psychol--arxiv-2605.22140/2026-06-19T21:13:46.796Z https://www.opentrain.ai/papers/efficient-agentic-reasoning-through-self-regulated-simulative-planning--arxiv-2605.22138/2026-06-19T21:18:46.279Z https://www.opentrain.ai/papers/cross-lingual-consensus-aligning-multilingual-cultural-knowledge-via-multilingua--arxiv-2605.22137/2026-06-19T01:12:50.152Z https://www.opentrain.ai/papers/perception-or-prejudice-can-mllms-go-beyond-first-impressions-of-personality--arxiv-2605.22109/2026-06-19T21:22:15.338Z https://www.opentrain.ai/papers/from-reasoning-chains-to-verifiable-subproblems-curriculum-reinforcement-learnin--arxiv-2605.22074/2026-06-19T11:52:45.259Z https://www.opentrain.ai/papers/faithful-mr1-faithful-multimodal-reasoning-via-anchoring-and-reinforcing-visual--arxiv-2605.22072/2026-06-19T12:05:43.085Z https://www.opentrain.ai/papers/latentomni-rethinking-omni-modal-understanding-via-unified-audio-visual-latent-r--arxiv-2605.22012/2026-06-18T21:16:34.871Z https://www.opentrain.ai/papers/rit-vanilla-diffusion-transformers-suffice-in-representation-space--arxiv-2605.21981/2026-06-19T11:53:19.974Z https://www.opentrain.ai/papers/the-illusion-of-reasoning-exposing-evasive-data-contamination-in-llms-via-zero-c--arxiv-2605.21856/2026-06-19T21:06:53.523Z https://www.opentrain.ai/papers/acc-compiling-agent-trajectories-for-long-context-training--arxiv-2605.21850/2026-06-19T21:05:26.199Z https://www.opentrain.ai/papers/reflective-prompt-tuning-through-language-model-function-calling--arxiv-2605.21781/2026-06-19T11:53:49.993Z https://www.opentrain.ai/papers/how-far-will-they-go-red-teaming-online-influence-with-large-language-models--arxiv-2605.22880/2026-06-19T21:07:28.808Z https://www.opentrain.ai/papers/flat-pack-bench-evaluating-spatio-temporal-understanding-in-large-vision-languag--arxiv-2605.21625/2026-06-19T21:14:33.829Z https://www.opentrain.ai/papers/uni-edit-intelligent-editing-is-a-general-task-for-unified-model-tuning--arxiv-2605.21487/2026-06-19T21:08:58.166Z https://www.opentrain.ai/papers/you-only-need-minimal-rlvr-training-extrapolating-llms-via-rank-1-trajectories--arxiv-2605.21468/2026-06-18T23:18:33.902Z https://www.opentrain.ai/papers/delta-discriminative-token-credit-assignment-for-reinforcement-learning-from-ver--arxiv-2605.21467/2026-06-19T21:12:47.753Z https://www.opentrain.ai/papers/mem-adaptive-memory-through-learning-when-and-what-to-generate--arxiv-2605.21463/2026-06-19T21:14:55.017Z https://www.opentrain.ai/papers/occlusionformer-arranging-z-order-for-layout-grounded-image-generation--arxiv-2605.21343/2026-06-19T21:08:38.468Z https://www.opentrain.ai/papers/q-arvd-quantizing-autoregressive-video-diffusion-models--arxiv-2605.21072/2026-06-18T08:15:29.591Z https://www.opentrain.ai/papers/rethinking-cross-layer-information-routing-in-diffusion-transformers--arxiv-2605.20708/2026-06-19T21:20:47.286Z https://www.opentrain.ai/papers/indusagent-reinforcing-open-vocabulary-industrial-anomaly-detection-with-agentic--arxiv-2605.20682/2026-06-19T21:10:57.806Z https://www.opentrain.ai/papers/evaluating-temporal-semantic-caching-and-workflow-optimization-in-agentic-plan-e--arxiv-2605.20630/2026-06-19T21:11:29.779Z https://www.opentrain.ai/papers/hrm-text-efficient-pretraining-beyond-scaling--arxiv-2605.20613/2026-06-19T11:05:57.366Z https://www.opentrain.ai/papers/msavbench-towards-comprehensive-and-reliable-evaluation-of-multi-shot-audio-vide--arxiv-2605.20183/2026-06-19T21:09:24.751Z https://www.opentrain.ai/papers/from-seeing-to-thinking-decoupling-perception-and-reasoning-improves-post-traini--arxiv-2605.20177/2026-06-19T21:16:47.296Z https://www.opentrain.ai/papers/clinseekagent-automating-multimodal-evidence-seeking-for-agentic-clinical-reason--arxiv-2605.20176/2026-06-19T21:16:35.015Z