paper-with-me

홈 › Papers

Communication Policy Evolution for Proactive LLM Agents

2026-06-12 · Xinbei Ma, Jiyang Qiu, Yao Yao, Zheng Wu, Yijie Lu, Xiangmou Qu, Jiaxin Yin, Xingyu Lou, Jun Wang, Weiwen Liu, Weinan Zhang, Zhuosheng Zhang, Hai Zhao arxiv

LLM agents have rapidly evolved into autonomous systems, yet a persistent information gap remains between users and agents: communication is costly, while users' identical preferences further limit information exchange. To investigate how agents should communicate across modalities, this paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments, personas, and model combinations. Building information asymmetry for proactive agents, we set up two complementary settings, User-Agent and Planner-Executor. Experimental results reveal complementary strengths between interaction channels: text-based interaction often facilitates task performance, while structured UI improves agents' response quality and persona compliance. Motivated by that, a hybrid method combines these advantages. We further propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving. Without model modification, CPE achieves the best task success across multiple settings using prompt refinement alone. Our findings identify communication behavior as a critical yet underexplored design dimension for LLM agents.

📄 PDF Abstract BibTeX arXiv:2606.14314

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Coordinated Pandemic Control with Large Language Model Agents as Policymaking Assistants

2026-01-14 · Ziyi Shi, Xusen Guo, Hongliang Lu, Mingxing Peng 외 arxiv

Effective pandemic control requires timely and coordinated policymaking across administrative regions that are intrinsically interdependent. However, human-driven responses are often fragmented and reactive, with policie…

PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent

2026-04-08 · Prince Zizhuang Wang, Shuli Jiang arxiv

The development of autonomous tool-use agents for complex, long-horizon tasks in collaboration with human users has become the frontier of agentic research. During multi-turn Human-AI interactions, the dynamic and uncert…

Reinforcement Learning

Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency

2026-08-23 · Zhihong Cao, Chen Huang arxiv

In the context of information seeking, conversational agents are undergoing an evolution from reactive tools to proactive, personalized assistants. A critical aspect of this evolution is the ability to tailor strategic i…

GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective

2025-07-13 · Hang Wang, Junshan Zhang arxiv

Multi-agent reinforcement learning faces fundamental challenges that conventional approaches have failed to overcome: exponentially growing joint action spaces, non-stationary environments where simultaneous learning cre…

Multi-agent Reinforcement Learning

Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution

2026-03-04 · Zixun Luo, Yuhang Fan, Hengyu Lin, Yufei Li 외 arxiv

Large Language model (LLM)-based Multi-Agent Systems (MAS) are prone to cascading risks, where early-stage interactions remain semantically fluent and policy-compliant, yet the underlying interaction dynamics begin to di…