2606.12384v1 Jun 10, 2026 cs.LG

APPO: Agentic Procedural Policy Optimization

Yong Wang
Yong Wang
Citations: 472
h-index: 12
Xiangxiang Chu
Xiangxiang Chu
Citations: 278
h-index: 9
Shidong Yang
Shidong Yang
Citations: 42
h-index: 2
Yuxiang Ji
Yuxiang Ji
Citations: 164
h-index: 7
Ziyu Ma
Ziyu Ma
Citations: 96
h-index: 4
Pengkun Wang
Pengkun Wang
Citations: 723
h-index: 16
Xucong Wang
Xucong Wang
Citations: 38
h-index: 2
Guanhua Chen
Guanhua Chen
Citations: 53
h-index: 5

Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing methods assign credit over coarse heuristic units, such as tool-call boundaries or fixed workflows, making it difficult to identify which intermediate decisions influence downstream outcomes. In this work, we study agentic RL from two perspectives: \textit{where to branch and how to assign credit after branching}. Our pilot analysis shows that influential decision points are broadly distributed throughout the generated sequence rather than concentrated at tool calls, while token entropy alone does not reliably reflect their impact on final outcomes. Motivated by these observations, we propose \textbf{Agentic Procedural Policy Optimization (APPO)}, which shifts branching and credit assignment from coarse interaction units to fine-grained decision points in the sequence. APPO selects branching locations using a Branching Score that combines token uncertainty with policy-induced likelihood gains of subsequent continuations, enabling more targeted exploration while filtering out spurious high-entropy positions. It further introduces procedure-level advantage scaling to better distribute credit across branched rollouts. Experiments on 13 benchmarks show that APPO consistently improves strong agentic RL baselines by nearly 4 points, while keeping efficient tool-calls and maintaining behavior interpretability.

0 Citations
0 Influential
8 Altmetric
40.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!