Communication Policy Evolution for Proactive LLM Agents

• URL: http://arxiv.org/abs/2606.14314v1
• Date: Fri, 12 Jun 2026 09:54:01 GMT
• Title: Communication Policy Evolution for Proactive LLM Agents
• Abstract summary: This paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments.<n>We propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving.
• Score: 58.4960889232199
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication [0.0]
  We propose a self-supervised framework for learning compact, stable, and policy-relevant communication representations.<n>We show that the learned communication space yields improved stability, sample efficiency, and throughput under policy fine-tuning.
  arXiv  Detail & Related papers  (2026-05-26T18:06:19Z)
• InfoPO: Information-Driven Policy Optimization for User-Centric Agents [39.407032905771885]
  We introduce InfoPO, which frames multi-turn interaction as a process of active uncertainty reduction.<n>It computes an information-gain reward that credits turns whose feedback changes the agent's subsequent action distribution.<n>It then combines this signal with task outcomes via an adaptive variance-gated fusion.
  arXiv  Detail & Related papers  (2026-02-28T13:58:14Z)
• When Numbers Start Talking: Implicit Numerical Coordination Among LLM-Based Agents [45.43445469098021]
  This paper presents a game-theoretic study of covert communication in multi-agent systems.<n>We analyse interactions across four canonical game-theoretic settings under different communication regimes.<n>Considering heterogeneous agent personalities and both one-shot and repeated games, we characterise when covert signals emerge and how they shape coordination and strategic outcomes.
  arXiv  Detail & Related papers  (2026-01-07T12:07:48Z)
• AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence [4.638507244153875]
  This paper introduces AgentRec, a next-generation multi-agent collaborative recommendation framework.<n>Our approach employs specialized LLM-powered agents for conversation understanding, preference modeling, context awareness, and dynamic ranking.<n>Experiments on three real-world datasets demonstrate that AgentRec achieves consistent improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-10-02T02:47:11Z)
• AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction [77.62279834617475]
  We propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.<n>Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection, which enables each agent to selectively access relevant information from any previous step.
  arXiv  Detail & Related papers  (2025-06-21T18:34:43Z)
• Communication Learning in Multi-Agent Systems from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. We introduce a temporal gating mechanism for each agent, enabling dynamic decisions on whether to receive shared information at a given time.
  arXiv  Detail & Related papers  (2024-11-01T05:56:51Z)
• Learning Multi-Agent Communication from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. Our proposed approach, CommFormer, efficiently optimize the communication graph and concurrently refines architectural parameters through gradient descent in an end-to-end manner.
  arXiv  Detail & Related papers  (2024-05-14T12:40:25Z)
• AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems [112.76941157194544]
  We propose AgentCF for simulating user-item interactions in recommender systems through agent-based collaborative filtering. We creatively consider not only users but also items as agents, and develop a collaborative learning approach that optimize both kinds of agents together. Overall, the optimized agents exhibit diverse interaction behaviors within our framework, including user-item, user-user, item-item, and collective interactions.
  arXiv  Detail & Related papers  (2023-10-13T16:37:14Z)
• On the Role of Emergent Communication for Social Learning in Multi-Agent Reinforcement Learning [0.0]
  Social learning uses cues from experts to align heterogeneous policies, reduce sample complexity, and solve partially observable tasks. This paper proposes an unsupervised method based on the information bottleneck to capture both referential complexity and task-specific utility.
  arXiv  Detail & Related papers  (2023-02-28T03:23:27Z)
• Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel [81.39444892747512]
  In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another. We propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents' collective performance.
  arXiv  Detail & Related papers  (2022-05-21T14:11:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.