Cover Image

Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Yiqun, Feng, Jinyuan, Yang, Wei, Zhong, Meizhi, Shi, Zhengliang, Li, Rui, Wei, Xiaochi, Gao, Yan, Wu, Yi, Hu, Yao, Pu, Zhiqiang, Mao, Jiaxin
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast
by: Feng, Jinyuan, et al.
Published: (2026)

JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG
by: Chen, Yiqun, et al.
Published: (2026)

Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
by: Yang, Zixuan, et al.
Published: (2026)

OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
by: Zhang, Erhan, et al.
Published: (2026)

Knowledge-Graph Paths as Intermediate Supervision for Self-Evolving Search Agents
by: Wu, Huyu, et al.
Published: (2026)

UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
by: Chen, Yiqun, et al.
Published: (2026)

MA2RL: Masked Autoencoders for Generalizable Multi-Agent Reinforcement Learning
by: Feng, Jinyuan, et al.
Published: (2025)

Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction
by: Feng, Jinyuan, et al.
Published: (2024)

CoMoE: Contrastive Representation for Mixture-of-Experts in Parameter-Efficient Fine-tuning
by: Feng, Jinyuan, et al.
Published: (2025)

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
by: Shen, Zhenyi, et al.
Published: (2025)

PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning
by: Chen, Yiqun, et al.
Published: (2022)

Self-Harmonized Chain of Thought
by: Jin, Ziqi, et al.
Published: (2024)

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty
by: Zhong, Meizhi, et al.
Published: (2024)

Self-Clustering Hierarchical Multi-Agent Reinforcement Learning with Extensible Cooperation Graph
by: Fu, Qingxu, et al.
Published: (2024)

Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization
by: Li, Hanyu, et al.
Published: (2025)

Measuring Policy Distance for Multi-Agent Reinforcement Learning
by: Hu, Tianyi, et al.
Published: (2024)

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
by: Chen, Yiqun, et al.
Published: (2025)

R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search
by: Wang, Yibo, et al.
Published: (2025)

ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
by: Zhong, Linqing, et al.
Published: (2026)

Causal Mean Field Multi-Agent Reinforcement Learning
by: Ma, Hao, et al.
Published: (2025)

MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification
by: Chen, Yiqun, et al.
Published: (2024)

Reasoning Efficiently Through Adaptive Chain-of-Thought Compression: A Self-Optimizing Framework
by: Huang, Kerui, et al.
Published: (2025)

Knowledge Editing through Chain-of-Thought
by: Wang, Changyue, et al.
Published: (2024)

Upfront Chain-of-Thought: A Cooperative Framework for Chain-of-Thought Compression
by: Li, Chengzhengxu, et al.
Published: (2025)

Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics
by: Sheng, Leheng, et al.
Published: (2026)

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training
by: Wei, Tong, et al.
Published: (2025)

OMoE: Diversifying Mixture of Low-Rank Adaptation by Orthogonal Finetuning
by: Feng, Jinyuan, et al.
Published: (2025)

Heterogeneity in Multi-Agent Reinforcement Learning
by: Hu, Tianyi, et al.
Published: (2025)

ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
by: Bian, Tingcheng, et al.
Published: (2026)

Activation Steering for Chain-of-Thought Compression
by: Azizi, Seyedarmin, et al.
Published: (2025)

Reinforcing Structured Chain-of-Thought for Video Understanding
by: Wang, Peiyao, et al.
Published: (2026)

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
by: Wang, Tianduo, et al.
Published: (2024)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
by: Ye, Jiacheng, et al.
Published: (2024)

Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
by: Tzannetos, Georgios, et al.
Published: (2025)

RaCT: Ranking-aware Chain-of-Thought Optimization for LLMs
by: Liu, Haowei, et al.
Published: (2024)

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks
by: Hu, Jinchao, et al.
Published: (2026)

Rethinking Chain-of-Thought Reasoning for Videos
by: Zhong, Yiwu, et al.
Published: (2025)

Android in the Zoo: Chain-of-Action-Thought for GUI Agents
by: Zhang, Jiwen, et al.
Published: (2024)

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
by: Zhang, Xuan, et al.
Published: (2024)

Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective
by: Zhong, Meizhi, et al.
Published: (2024)