Researchers have developed Influence-Aware Policy Optimization (IAPO), a new method for training large language model agents that interact with users and tools over multiple turns. IAPO represents agent rollouts as influence-dependency graphs, using user and tool observations to route advantages and improve credit assignment from sparse outcome feedback. Experiments with Qwen3-4B and Qwen3-8B models showed IAPO outperformed existing multi-turn reinforcement learning baselines on benchmarks like tau^2-Bench, UserBench, and AgentChangeBench, without sacrificing multi-turn function-calling capabilities. AI
IMPACT Enhances training of multi-turn LLM agents by improving credit assignment from sparse feedback.
RANK_REASON The cluster contains an academic paper detailing a new method for LLM agents. [lever_c_demoted from research: ic=1 ai=1.0]
- AgentChangeBench
- arXiv
- BFCL-v4 Multi-Turn
- Influence-Aware Policy Optimization
- Qwen3-4B
- Qwen3_8B
- tau^2-Bench
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
