Visual CoT agents exhibit tool-use collapse where tool usage declines but task accuracy rises, and adding entropy regularization for rollout diversity produces the strongest performance.
Your group-relative advantage is biased
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
CurveRL derives a quantile-coordinate reweighting rule from a utility functional on pass rates and shows it outperforms GRPO on reasoning benchmarks.
FADE is a self-adapting advantage for policy-gradient RL that reads training dynamics to balance positive/negative gradient mass and difficulty focus, yielding faster peak performance and better accuracy-diversity trade-offs than static baselines on LLM reasoning benchmarks.
GRPO suffers advantage collapse on uniform-reward groups; ACR quantifies it and AVSPO adds virtual samples to restore gradients, yielding 4-6% accuracy gains on math benchmarks across 0.5B-14B models.
AutoSearch applies RL with a self-answering reward to adaptively determine minimal sufficient search depth in agentic RAG, reducing over-searching while maintaining answer quality on complex questions.
The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.
PIPO adds closed-loop policy-improvement feedback to RL post-training so updates that raise measured performance are reinforced and those that drop it are suppressed.
citing papers explorer
-
Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents
Visual CoT agents exhibit tool-use collapse where tool usage declines but task accuracy rises, and adding entropy regularization for rollout diversity produces the strongest performance.
-
CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
CurveRL derives a quantile-coordinate reweighting rule from a utility functional on pass rates and shows it outperforms GRPO on reasoning benchmarks.
-
Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL
FADE is a self-adapting advantage for policy-gradient RL that reads training dynamics to balance positive/negative gradient mass and difficulty focus, yielding faster peak performance and better accuracy-diversity trade-offs than static baselines on LLM reasoning benchmarks.
-
Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation
GRPO suffers advantage collapse on uniform-reward groups; ACR quantifies it and AVSPO adds virtual samples to restore gradients, yielding 4-6% accuracy gains on math benchmarks across 0.5B-14B models.
-
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
AutoSearch applies RL with a self-answering reward to adaptively determine minimal sufficient search depth in agentic RAG, reducing over-searching while maintaining answer quality on complex questions.
-
LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning
The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.
-
Policy Improvement Reinforcement Learning
PIPO adds closed-loop policy-improvement feedback to RL post-training so updates that raise measured performance are reinforced and those that drop it are suppressed.