paper-with-me

Papers

Agent models: Internalizing Chain-of-Action Generation into Reasoning models

2025-03-09 · Yuxiang Zhang, YuQi Yang, Jiangming Shu, Xinyan Wen, Jitao Sang

Traditional agentic workflows rely on external prompts to manage interactions with tools and the environment, which limits the autonomy of reasoning models. We position \emph{Large Agent Models (LAMs)} that internalize the generation of \emph{Chain-of-Action (CoA)}, enabling the model to autonomously decide when and how to use external tools. Our proposed AutoCoA framework combines supervised fine-tuning (SFT) and reinforcement learning (RL), allowing the model to seamlessly switch between reasoning and action while efficiently managing environment interactions. Main components include step-level action triggering, trajectory-level CoA optimization, and an internal world model to reduce real-environment interaction costs. Evaluations on open-domain QA tasks demonstrate that AutoCoA-trained agent models significantly outperform ReAct-based workflows in task completion, especially in tasks that require long-term reasoning and multi-step actions. Code and dataset are available at https://github.com/ADaM-BJTU/AutoCoA

📄 PDF Abstract BibTeX arXiv:2503.06580

Code (1)

adam-bjtu/autocoa 공식 구현 pytorch

Tasks

Action GenerationReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generation

2025-11-25 · Xiangkai Ma, Lekai Xing, Han Zhang, Wenzhong Li 외 arxiv

Vision-Language-Action (VLA) models built upon Chain-of-Thought (CoT) have achieved remarkable success in advancing general-purpose robotic agents, owing to its significant perceptual comprehension. Recently, since text-…

Motion Planning

Internalizing LLM Reasoning via Discovery and Replay of Latent Actions

2026-02-04 · Zhenning Shi, Yijia Zhu, Junhan Shi, Xun Zhang 외 arxiv

The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering methods rely on static control vectors …

PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training

2026-02-14 · Yuhan Cheng, Hancheng Ye, Hai Helen Li, Jingwei Sun 외 arxiv

Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contex…

Zero-shot Generalization

Internalizing ASR with Implicit Chain of Thought for Efficient Speech-to-Speech Conversational LLM

2024-09-25 · Robin Shing-Hei Yuen, Timothy Tin-Long Tse, Jian Zhu

Current speech-based LLMs are predominantly trained on extensive ASR and TTS datasets, excelling in tasks related to these domains. However, their ability to handle direct speech-to-speech conversations remains notably c…

SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training

2026-06-01 · Zhongyu He, Yuanfan Li, Fei Huang, Tianyu Chen 외 arxiv

Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering comple…

Reinforcement Learning