IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents

• URL: http://arxiv.org/abs/2608.24588v2
• Date: Wed, 26 Aug 2026 16:29:06 GMT
• Title: IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents
• Abstract summary: This work advances the understanding of credit assignment in multi-turn user interactions.<n>It provides a principled approach to training service agents from sparse outcome feedback.
• Score: 10.577620258047665
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information often unfolds over time rather than being fully specified at the initial prompt. Service agents make this challenge especially concrete: users may clarify or revise their goals, while tool responses provide information needed for subsequent decisions. Thus, a final reward alone cannot indicate which actions contributed to resolving the task. Recent methods rely on comparative evidence from other trajectories or resampled continuations, or on separately constructed step-level learning signals, to refine credit. However, a completed rollout already records how information and errors flow between agent actions. We introduce Influence-Aware Policy Optimization (IAPO), which represents each rollout as a typed influence-dependency graph over trainable agent actions, with user and tool observations serving as evidence. IAPO converts support-use and failed-use structure into routing weights that redistribute the same trajectory-level advantage. Experiments with Qwen3-4B and Qwen3-8B demonstrate superior performance over multi-turn reinforcement learning (RL) baselines across three service-agent benchmarks: ${τ^2}$-Bench, UserBench, and AgentChangeBench. BFCL-v4 Multi-Turn further shows that these gains do not compromise multi-turn function-calling performance. This work advances the understanding of credit assignment in multi-turn user interactions and provides a principled approach to training service agents from sparse outcome feedback.

Related papers

• APPO: Agentic Procedural Policy Optimization [28.730334202611257]
  We study agentic RL from two perspectives: textitwhere to branch and how to assign credit after branching<n>We propose APPO, which shifts branching and credit assignment from coarse interaction units to fine-grained decision points in the sequence.<n>APPO consistently improves strong agentic RL baselines by nearly 4 points, while keeping efficient tool-calls and maintaining behavior interpretability.
  arXiv  Detail & Related papers  (2026-06-10T17:47:07Z)
• TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents [54.08846865906602]
  We characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents.<n>We propose Tool-Aware Policy Optimization (TAPO), which exploits the parameter-determinism property of information-acquisition tools.
  arXiv  Detail & Related papers  (2026-06-04T07:15:43Z)
• 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)
• 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)
• DLLM Agent: See Farther, Run Faster [94.74432470237817]
  Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties.<n>We study this in a controlled setting by instantiatingDLLM and AR backbones within the same agent workflow.<n>We find thatDLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup.
  arXiv  Detail & Related papers  (2026-02-07T09:01:18Z)
• AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress [71.02263260394261]
  Large language models (LLMs) still encounter challenges in multi-turn decision-making tasks.<n>We build process reward models (PRMs) to evaluate each decision and guide the agent's decision-making process.<n>AgentPRM captures both the interdependence between sequential decisions and their contribution to the final goal.
  arXiv  Detail & Related papers  (2025-11-11T14:57:54Z)
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
  tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
  arXiv  Detail & Related papers  (2025-10-06T23:20:49Z)
• Multi-Agent Tool-Integrated Policy Optimization [67.12841355267678]
  Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks.<n>Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses.<n>No existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks.
  arXiv  Detail & Related papers  (2025-10-06T10:44:04Z)
• $C^3$-Bench: The Things Real Disturbing LLM based Agent in Multi-Tasking [12.218102495632937]
  We present an open-source benchmark $C3$-Bench to assess agent robustness.<n>In concrete, we design three challenges: navigate complex tool relationships, handle critical hidden information and manage dynamic decision paths.<n>In essence, $C3$-Bench aims to expose model vulnerabilities through these challenges and drive research into the interpretability of agent performance.
  arXiv  Detail & Related papers  (2025-05-24T15:25:44Z)
• Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design [35.544075583073685]
  We present the first systematic study of textitturn-level reward design for multi-turn RL algorithms and agent applications.<n>We conduct case studies on multi-turn reasoning-augmented search agents, where we carefully design two types of turn-level rewards: verifiable and LLM-as-judge.<n>Our experiments on multi-turn search tasks demonstrate that incorporating well-designed turn-level rewards enables RL algorithms to significantly outperform baseline methods with trajectory-level rewards.
  arXiv  Detail & Related papers  (2025-05-17T04:09:46Z)
• Learning From Good Trajectories in Offline Multi-Agent Reinforcement Learning [98.07495732562654]
  offline multi-agent reinforcement learning (MARL) aims to learn effective multi-agent policies from pre-collected datasets. One agent learned by offline MARL often inherits this random policy, jeopardizing the performance of the entire team. We propose a novel framework called Shared Individual Trajectories (SIT) to address this problem.
  arXiv  Detail & Related papers  (2022-11-28T18:11:26Z)

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.