CORTEXA
← Browse
arxivcs.LGcs.AI2026-07-03

ACPO: Adaptive Credit Policy Optimization via Fine-Grained Surrogate Entropy

Zijun Xie, Yuyang You, Yongzhi Li, Enlei Gong, Zeyu Chen, Quan Chen, Yanhua Cheng, Peng Jiang, Yadong Mu

Reinforcement Learning (RL) has substantially improved the reasoning ability of large language models (LLMs), but sparse outcome rewards still make token-level credit assignment difficult. Existing scalable RL methods typically assign trajectory-level rewards uniformly across tokens, while recent entropy-aware approaches either rely on coarse detached heuristics or directly optimize true entropy, which can introduce non-local gradient components misaligned with sampled-token policy updates. We propose Adaptive Credit Policy Optimization (ACPO), a token-level credit assignment framework based on a mode-local surrogate entropy. ACPO asymmetrically modulates policy updates by emphasizing uncertain decisions in successful rollouts and overconfident tokens in failed rollouts. We show that the surrogate admits deterministic entropy bounds and, under modal alignment and proximal updates, preserves the policy-gradient direction to leading order. Experiments on mathematical reasoning and coding benchmarks, including AIME 2025 and HumanEvalPro, show that ACPO consistently improves over strong RL baselines such as DAPO, GTPO, and SAPO.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CL2026-07-16

Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization

Weiwen Xu, Jia Liu, Hou Pong Chan, Long Li, Deng Cai, Min Chen, et al.

Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy cannot distinguish useful uncertainty from detrimental confusion, limiting its effectiveness as a correctness signal. We propose Contrastive Policy Optimization (CP…

View free PDFSource page
arxiveess.AScs.AIcs.CLcs.LGcs.SD2026-07-15

Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware Large Language Models

Chun-Yi Kuan, Siwon Kim, Byeonggeun Kim, Suyoun Kim, Bo-Ru Lu, Qinming Tang, et al.

Recent text-to-audio models generate high-quality audio, but often fail to follow instructions involving multiple sound events and temporal order. This gap arises because existing evaluation and training signals mainly emphasize global similarity or perceptual quality, with limit…

View free PDFSource page
arxivcs.LGcs.AI2026-07-08

Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning

Zetian Hu, Shunyu Liu, Junjie Zhang, Yongcheng Jing, Ting-En Lin, Yongbin Li, et al.

Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, existing efforts largely focus on single-task settings, whereas real-world deployment necessitates a generalist agent capable of solvi…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-06-25

Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge

Thomas Shih-Chao Liang, Zhuoran Yu, Yong Jae Lee

Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored. In this work, we propose LaViD--Language-to-Visual Knowledge Distillation--a simple an…

View free PDFSource page
arxivcs.AIcs.CLcs.LG2026-07-20

WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

Zhaokai Wang, Tianlin Gui, Jiayuan Rao, Shangzhe Di, Yihong Tang, Dingli Liang

Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents. The 20…

View free PDFSource page