DISA decouples partition function estimation using offline importance sampling for distribution-matching LLM-RL, matching or exceeding online baselines like FlowRL on math and code benchmarks while retaining more strategy diversity.
Scaling up rl: Unlocking diverse reasoning in llms via prolonged training.arXiv preprint arXiv:2507.12507
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
LLMs show strong spatial generalization to unseen maps in shortest-path tasks but fail length scaling due to recursive instability, with data coverage setting hard limits.
Hallucinations in multimodal reasoners cluster at high-entropy pivot tokens due to intermediate-layer visual anchoring failure, and V-STAR mitigates this with attention rewards plus forced reflection.
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
ARES generates 100K rubric-annotated QA instances from raw documents and demonstrates superior rubric-based RL performance over baselines on open-ended benchmarks.
citing papers explorer
-
DISA: Offline Importance Sampling for Distribution-Matching LLM-RL
DISA decouples partition function estimation using offline importance sampling for distribution-matching LLM-RL, matching or exceeding online baselines like FlowRL on math and code benchmarks while retaining more strategy diversity.
-
Generalization in LLM Problem Solving: The Case of the Shortest Path
LLMs show strong spatial generalization to unseen maps in shortest-path tasks but fail length scaling due to recursive instability, with data coverage setting hard limits.
-
Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models
Hallucinations in multimodal reasoners cluster at high-entropy pivot tokens due to intermediate-layer visual anchoring failure, and V-STAR mitigates this with attention rewards plus forced reflection.
-
Trust Region On-Policy Distillation
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
-
ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning
ARES generates 100K rubric-annotated QA instances from raw documents and demonstrates superior rubric-based RL performance over baselines on open-ended benchmarks.