paper-with-me

홈 › Papers

Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents

2026-06-24 · Peng Xu, Sijia Chen, Junzhuo Li, Xuming Hu arxiv

Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcomes. However, this ties a step's credit to its rollout's final outcome: semantically near-identical intermediate steps receive opposite credit depending on whether their trajectory eventually succeeded or failed. Such semantic credit inconsistency sends conflicting gradients to similar actions and wastes the partially-correct progress inside failed rollouts. Motivated by this, we propose Semantic Consistency Policy Optimization (SCPO), a value-free reward-shaping method that mitigates this inconsistency by recovering step-level credit from successful siblings in the same rollout group. Concretely, SCPO scores each failed step against a successful sibling and adds positive step-level credit for new progress along that sibling. On ALFWorld and WebShop, SCPO matches or exceeds strong group-based baselines, reaching 93.7+/-4.1 percent success on ALFWorld and 74.8+/-2.0 percent on WebShop at 1.5B parameters, with gains concentrated on the hardest multi-step tasks.

📄 PDF Abstract BibTeX arXiv:2606.25852

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning

2023-09-12 · Xiao Liu, Wubing Chen, Mao Tan

Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making problems. However, existing DRL agents make decisions in an opaque fashion, hindering the user from establishing trust and s…

Decision MakingDeep Reinforcement Learningreinforcement-learningReinforcement Learning+3

CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents

2026-05-25 · Yihong Tang, Kehai Chen, Liang Yue, Benyou Wang 외 arxiv

Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem…

Reinforcement Learning

Segment-Aligned Policy Optimization for Multi-Modal Reasoning

2026-05-02 · Lei Gao, Zhuoming Li, Mengxi Jia, Jiakang Yuan 외 arxiv

Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of individual tokens or entire response sequences. However, such formulations often misalign w…

Reinforcement Learning

Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning

2026-07-05 · Mingxuan Fan, Peiyang Liu arxiv

Group-based reinforcement learning (RL) has become an effective paradigm for improving large language model agents on long-horizon interactive tasks. To obtain finer-grained policy updates than trajectory-level optimizat…

Reinforcement Learning

Collaborative Text-to-Image Generation via Multi-Agent Reinforcement Learning and Semantic Fusion

2025-10-12 · Jiabao Shi, Minfeng Qi, Lefeng Zhang, Di Wang 외 arxiv

Multimodal text-to-image generation remains constrained by the difficulty of maintaining semantic alignment and professional-level detail across diverse visual domains. We propose a multi-agent reinforcement learning fra…

Multi-agent Reinforcement LearningText-to-Image GenerationContrastive LearningSemantic Similarity