arXiv AI
Matched-Context Group Policy Optimization for LLM Agent Training
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
6d ago
RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents
arXiv:2610.07349v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) avoids a separate critic by estimating advantages from rollout groups. For multi-turn agents, however, traj...
arXiv AI
Sep 30
Targeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning
arXiv:2609.36178v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents. However, its uniform assignment o...
arXiv AI
Jul 14
Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories
arXiv:2607. 10601v1 Announce Type: new Abstract: Large Language Model (LLM) agents are commonly trained from expert trajectories using supervised fine-tuning (SFT), which treats multi-turn agent behavior as ordinary text imitation.
arXiv Machine Learning
Jun 5
When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training
arXiv:2606. 05885v1 Announce Type: new Abstract: Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards.
arXiv AI
Jul 1
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
arXiv:2606. 32017v1 Announce Type: cross Abstract: Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions.
arXiv Machine Learning
Aug 26
IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents
The paper introduces Influence-Aware Policy Optimization (IAPO), a method that models multi‑turn agent rollouts as typed influence‑dependency graphs to better assign credit to actions based on how information and errors flow through user and tool interactions. IAPO transforms the structure of support and failure usage into routing weights that redistribute trajectory‑level advantage, enabling more effective learning from sparse final rewards. Experiments with Qwen3‑4B and Qwen3‑8B on three service‑agent benchmarks show that IAPO outperforms existing multi‑turn reinforcement learning baselines without harming function‑calling performance.