arXiv AI

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

HINT-SD introduces a targeted self‑distillation framework for long‑horizon language‑model agents that uses full‑trajectory hindsight to identify failure‑relevant actions and applies feedback‑conditioned distillation only to those action spans. This selective approach reduces the need for per‑turn feedback, improving training efficiency and effectiveness. Experiments on BFCL v3 and AppWorld demonstrate that HINT‑SD outperforms dense per‑turn feedback baselines by up to 13.60 percentage points on average while cutting training time per step by 2.26×.

arXiv AI
Aug 26

AHEAD: Adaptive Hindsight with Environment-Augmented Distillation for Agentic RL

AHEAD is a step‑aware framework that augments reinforcement learning for multi‑turn LLM agents by matching different supervision sources to different step types. The teacher receives environment feedback on all steps and LLM‑generated corrective hints only on error steps, providing finer‑grained guidance than uniform trajectory‑level rewards. Across ALFWorld, WebShop, and Search‑based QA, AHEAD improves task success by 13.3 points on ALFWorld and 11.0 on WebShop at 7B, reaches target success rates faster, and solves tasks within tighter interaction budgets compared to outcome‑only RL and prior self‑distillation baselines.

By Xiaolong Jin, Dingmin Wang, Vijay Lingam, Varun Kumar
arXiv AI
Aug 20

RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training

The paper introduces Reverse‑Turn Policy Optimization (RTPO), a method that restructures multi‑turn agentic reinforcement learning rollouts into sparse reverse trees and updates policies in temporal reverse order. This approach addresses three key instability sources—context mismatch, weak turn‑level credit assignment, and asynchronous policy drift—by aligning each decision with its downstream continuation. Theoretical analysis shows RTPO eliminates context mismatch and drift, reduces credit bias, and converges to recursive optimality, while experiments demonstrate performance gains of 21.50% over trajectory‑level and 10.76% over turn‑level baselines on multi‑turn agentic RL benchmarks.

By Yugu Li, Jimmy Cao, Jianglin Qiao, Siyi Hu