arXiv AI By Xinhao Yao, Lu Yu, Changhao Wang, Fengwei Teng, Yuyao Zhang, Qing Cui, Jun Zhou, Yong Liu

Tracking the Moving Frontier: Long-Short Term Advantage Estimator

Read the original on arXiv AI →

The paper introduces Long-Short Term Advantage Estimator (LSTAE), a single‑stream reinforcement learning algorithm that replaces repeated within‑iteration trajectory sampling with historical experience for advantage estimation. LSTAE tracks each task anchor with a drift‑aware long‑term baseline and a short‑term state‑experience buffer, converting accumulated experience into multi‑granular credit signals while requiring only one rollout per anchor. Experiments on agentic and mathematical reasoning benchmarks show that LSTAE matches or surpasses strong group‑based baselines while significantly reducing rollout cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
Sep 4

TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM Agents

TIGPO (Temporal Instance-Graph Policy Optimization) extends graph-based credit assignment for long-horizon LLM agents by maintaining a persistent transition graph per task across policy updates. It allocates rollout budgets to both new exploration and revisiting past tasks, pairing current rollouts with earlier ones to create cross‑temporal references that stabilize advantage estimation. Experiments on ALFWorld and WebShop show TIGPO consistently outperforms previous group‑based and graph‑based policy optimization methods.

By Jinwei Gan
arXiv AI
Sep 3

PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks

The paper introduces Potential-Guided Policy Optimization (PGPO), a method for multi-turn agentic tasks that improves credit assignment by estimating empirical state potentials from anchor-state-group return statistics. PGPO derives action advantages from potential differences between adjacent states, enabling cross-trajectory credit propagation and finer-grained step-level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop demonstrate strong performance compared to recent group-based reinforcement learning methods, with negligible training overhead.

By Yuyao Zheng, Haipeng Sun, Junwei Bao, Lemao Liu, Hongfei Jiang, Yang Song, Dejing Dou
arXiv AI
Jul 20

Process Reward Informed Tree Rollout for Effective Multi-Turn RL

arXiv:2607. 15610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation.

By Xintong Li, Sha Li, Yuwei Zhang, Changlong Yu, Rongmei Lin, Hongye Jin, Shuyi Guan, Xin Liu, Linwei Li, Qingyu Yin, Jingbo Shang