InfoPO: Information-Driven Policy Optimization for User-Centric Agents

• URL: http://arxiv.org/abs/2603.00656v1
• Date: Sat, 28 Feb 2026 13:58:14 GMT
• Title: InfoPO: Information-Driven Policy Optimization for User-Centric Agents
• Authors: Fanqi Kong, Jiayi Zhang, Mingyi Deng, Chenglin Wu, Yuyu Luo, Bang Liu,
• Abstract summary: 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.
• Score: 39.407032905771885
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downstream decisions. However, current multi-turn GRPO-based methods often rely on trajectory-level reward computation, which leads to credit assignment problems and insufficient advantage signals within rollout groups. A feasible approach is to identify valuable interaction turns at a fine granularity to drive more targeted learning. To address this, we introduce InfoPO (Information-Driven Policy Optimization), which frames multi-turn interaction as a process of active uncertainty reduction and computes an information-gain reward that credits turns whose feedback measurably changes the agent's subsequent action distribution compared to a masked-feedback counterfactual. It then combines this signal with task outcomes via an adaptive variance-gated fusion to identify information importance while maintaining task-oriented goal direction. Across diverse tasks, including intent clarification, collaborative coding, and tool-augmented decision making, InfoPO consistently outperforms prompting and multi-turn RL baselines. It also demonstrates robustness under user simulator shifts and generalizes effectively to environment-interactive tasks. Overall, InfoPO provides a principled and scalable mechanism for optimizing complex agent-user collaboration. Code is available at https://github.com/kfq20/InfoPO.

Related papers

• Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization [61.641777037967366]
  Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns.<n>Agentic reinforcement learning (RL) has emerged as a promising solution for training such agents in multi-turn settings.<n>We propose BAO, an agentic RL framework that combines behavior enhancement to enrich proactive reasoning and information-gathering capabilities.
  arXiv  Detail & Related papers  (2026-02-11T20:40:43Z)
• Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents [28.145430029174577]
  Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments.<n>Existing approaches typically rely on outcome-based rewards that are only provided at the final answer.<n>In this paper, we propose Information Gain-based Policy Optimization (IGPO), a simple yet effective RL framework that provides dense and intrinsic supervision for multi-turn agent training.
  arXiv  Detail & Related papers  (2025-10-16T17:59:32Z)
• Knowledge Base-Aware Orchestration: A Dynamic, Privacy-Preserving Method for Multi-Agent Systems [39.146761527401424]
  We introduce Knowledge Base-Aware (KBA) Orchestration, a novel approach that augments static descriptions with dynamic, privacy-preserving relevance signals.<n>By combining this novel mechanism with static descriptions, our method achieves more accurate and adaptive task routing.<n> Benchmarks show that our KBA Orchestration significantly outperforms static description-driven methods in routing precision and overall system efficiency.
  arXiv  Detail & Related papers  (2025-09-23T21:46:38Z)
• LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization [58.65395773049273]
  Location Preference Optimization (LPO) is a novel approach that leverages locational data to optimize interaction preferences.<n>LPO uses information entropy to predict interaction positions by focusing on zones rich in information.<n>Our code will be made publicly available soon, at https://github.com/AIDC-AI/LPO.
  arXiv  Detail & Related papers  (2025-06-11T03:43:30Z)
• Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents [110.25679611755962]
  Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. We introduce Intention-in-Interaction (IN3), a novel benchmark designed to inspect users' implicit intentions through explicit queries. We empirically train Mistral-Interact, a powerful model that proactively assesses task vagueness, inquires user intentions, and refines them into actionable goals.
  arXiv  Detail & Related papers  (2024-02-14T14:36:30Z)
• MASP: Scalable GNN-based Planning for Multi-Agent Navigation [18.70078556851899]
  Multi-Agent Scalable Graph-based Planner (MASP) is a goal-conditioned hierarchical planner for navigation tasks.<n>MASP employs a hierarchical framework to reduce space complexity by decomposing a large exploration space into multiple goal-conditioned subspaces.<n>For agent cooperation and the adaptation to varying team sizes, we model agents and goals as graphs to better capture their relationship.
  arXiv  Detail & Related papers  (2023-12-05T06:05:04Z)
• Asynchronous Message-Passing and Zeroth-Order Optimization Based Distributed Learning with a Use-Case in Resource Allocation in Communication Networks [11.182443036683225]
  Distributed learning and adaptation have received significant interest and found wide-ranging applications in machine learning signal processing.<n>This paper specifically focuses on a scenario where agents collaborate towards a common task.<n>Agents, acting as transmitters, collaboratively train their individual policies to maximize a global reward.
  arXiv  Detail & Related papers  (2023-11-08T11:12:27Z)
• Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning [46.28771270378047]
  Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories. In this work, we consider a multi-task setting, in which each agent has its own private reward function corresponding to different tasks, while sharing the same transition kernel of the environment. We learn a globally optimal policy that maximizes the sum of the discounted total rewards of all the agents in a decentralized manner.
  arXiv  Detail & Related papers  (2023-11-01T00:15:18Z)
• Research on Multi-Agent Communication and Collaborative Decision-Making Based on Deep Reinforcement Learning [0.0]
  This thesis studies the cooperative decision-making of multi-agent based on the Multi-Agent Proximal Policy Optimization algorithm. Different agents can alleviate the non-stationarity caused by local observations through information exchange between agents. The experimental results show that the improvement has achieved certain effects, which can better alleviate the non-stationarity of the multi-agent environment.
  arXiv  Detail & Related papers  (2023-05-23T14:20:14Z)
• Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
  This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
  arXiv  Detail & Related papers  (2021-12-03T19:23:48Z)
• Dif-MAML: Decentralized Multi-Agent Meta-Learning [54.39661018886268]
  We propose a cooperative multi-agent meta-learning algorithm, referred to as MAML or Dif-MAML. We show that the proposed strategy allows a collection of agents to attain agreement at a linear rate and to converge to a stationary point of the aggregate MAML. Simulation results illustrate the theoretical findings and the superior performance relative to the traditional non-cooperative setting.
  arXiv  Detail & Related papers  (2020-10-06T16:51:09Z)

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.