This work proposes AHEAD, a step-aware framework that matches different supervision sources to different step types and solves tasks within tighter interaction budgets than outcome-only RL and prior self-distillation baselines.
Abstract
Training multi-turn LLM agents with reinforcement learning typically relies on trajectory-level rewards, which assign a uniform advantage to every step and cannot identify which decisions led to success or failure. Self-distillation methods can provide finer-grained supervision by augmenting RL with privileged information. However, existing approaches usually apply the same type of privileged information to every step in an indistinguishable manner, ignoring a key asymmetry: routine steps need little additional guidance, while critical error steps require corrective direction that environment feedback alone cannot provide. We propose AHEAD, a step-aware framework that matches different supervision sources to different step types. The teacher receives environment feedback on all steps as a grounded dense signal, and additionally receives LLM-generated corrective hints on error steps to supply the direction that environment feedback lacks. The method introduces minimal changes to the standard GRPO algorithm. Across ALFWorld, WebShop, and Search-based QA, and across three model scales, AHEAD raises task success (+13.3 points on ALFWorld and +11.0 on WebShop at 7B over GRPO), reaches a given success rate in fewer training steps, and solves tasks within tighter interaction budgets than outcome-only RL and prior self-distillation baselines.
Experiments on challenging reasoning benchmarks show that H$^2$SD achieves the strongest overall performance among representative RLVR and self-distillation baselines, with stable optimization and a favorable accuracy-efficiency trade-off.
Qi Cai, Yi-Chuan Ma, Linyang Li et al.· arXiv.org· 2 citations
Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards. However, a completed rollout can yield many such signals, leaving their appropriate allocation across turns unclear. We introduce TRIAL, a trajectory-relative hindsight distillation framework with a unified turn-aligned scoring protocol. For each decision turn, TRIAL extracts an outcome view of that decision's realized consequence and evaluates the same response under ordinary and hindsight-conditioned contexts. The signed log-probability gap determines the direction and local strength of token-level supervision, while turn-level magnitudes are normalized jointly over the realized trajectory. The resulting allocation multipliers have an eligible-token-weighted mean of one, redistributing dense supervision across turns while fixing its average multiplier. Experiments on WebShop and ALFWorld with different backbones show that TRIAL outperforms GRPO across all eight combinations of backbone, environment, and evaluation metric, while achieving the best or tied-best performance among six methods on six of them. On WebShop with Qwen3-1.7B, TRIAL improves the success rate from 56.4% to 75.2% and the task score from 78.7% to 85.7%. Controlled ablations further show that trajectory-relative turn allocation provides substantial gains beyond those of dense hindsight distillation alone.
Haoyu Zheng, Yun Zhu, Qing Wang et al.· 0 citations
This work proposes AgentOPSD, a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning that aggregates token-level teacher-student log-probability gaps into turn-level evidence and recursively updates a Bayesian belief state in log-odds space.
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao et al.· 1 citation
EviSD is proposed, an evidence-conditioned self-distillation framework that uses instance-level supporting evidence as privileged information for search actions and golden answers as complementary privilege for answer actions, and achieves the highest macro-average Exact Match in all evaluated settings.
Jianan Xie, Xin Sun, Zhongqi Chen et al.· 0 citations
Observation-Calibrated Self-Distillation (OCSD), which contrasts two structurally matched replay views, Full and Observation-Ablated, to derive an observation residual that discounts score changes shared by the replay scaffold, and applies this residual to modulate token-level GRPO updates at high-uncertainty steps, while preserving the trajectory-level update direction.
Y. Yang, Congming Qin, Xiaodan Liu et al.· 1 citation
Group-Reflective Self-Distillation (GRSD), which derives capability-aligned and outcome-discriminative guidance from the policy's own verified rollouts, and refines turn-level credit assignment by modulating outcome-based advantages while preserving the verifier-determined learning direction.
