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

arXiv:2608.24588 · cs.LG · Submitted 2026-08-25 · Read on arXiv

cs.LG

Submitted: 2026-08-25

Updated: 2026-08-26

Terminology

• GRPO — 37× in this paper · explained in 6 episodes
• Credit assignment — 26× in this paper · explained in 3 episodes
• Influence-Aware Policy Optimization — 14× in this paper
• Benchmark — 11× in this paper · explained in 2 episodes
• Reinforcement Learning — 8× in this paper · explained in 4 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Large Language Model — 4× in this paper
• Grounding — 2× in this paper · explained in 3 episodes
• Provenance — 2× in this paper · explained in 4 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• Process Reinforcement through Implicit Rewards
• DeepSeek-V3 Technical Report
• Tree Search for LLM Agent Reinforcement Learning
• Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
• Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning
• Understanding R1-Zero-Like Training: A Critical Perspective
• GPT-4 Technical Report
• GRPO-$\lambda$: Credit Assignment improves LLM Reasoning
• UserBench: An Interactive Gym Environment for User-Centric Agents
• UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
• AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI
• Credit Assignment with Resets in Language Model Reasoning
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Hindsight Credit Assignment for Long-Horizon LLM Agents
• Gemini: A Family of Highly Capable Multimodal Models
• MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
• Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks