Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning

• URL: http://arxiv.org/abs/2608.07371v1
• Date: Fri, 07 Aug 2026 16:12:58 GMT
• Title: Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning
• Abstract summary: We introduce TRIAL, a trajectory-relative hindsight distillation framework with a unified turn-aligned scoring protocol.<n>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.<n>Experiments on WebShop and ALFWorld with different backbones show that TRIAL outperforms GRPO across all eight combinations of backbone, environment, and evaluation metric.
• Score: 22.776663901175663
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts [61.695980784491475]
  Test-time scaling produces cohorts of reasoning rollouts, yet there is no standard label-free account of how their internal computation reorganizes as inference unfolds.<n>We introduce routing effective rank deff, the entropy-effective dimensionality of a cross-rollout graph built from MoE expert-routing similarity.
  arXiv  Detail & Related papers  (2026-09-06T05:43:22Z)
• On-Policy Self-Distillation in Diffusion Models [89.32656931795293]
  Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change.<n>We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries.<n>Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators.
  arXiv  Detail & Related papers  (2026-08-25T14:55:24Z)
• RecGPT-Mobile-V2 Technical Report [22.10290138930905]
  RecGPT-Mobile-V2 is an end-to-end framework that treats intent quality and execution efficiency as coupled objectives within a staged design.<n>The framework transforms heterogeneous interactions into an evidence-preserving trajectory, establishes a recommendation-native foundation through domain adaptation and supervised alignment.<n>Online retrieval analysis indicates that the Query recall channel retrieves inventory complementary to that surfaced by established recall channels.
  arXiv  Detail & Related papers  (2026-08-25T09:23:17Z)
• ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment [66.45065414461274]
  Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.<n>We propose Answer-Backtracked Credit Assignment (ABC), a fine-grained credit assignment framework for training long-horizon search agents.<n>ABC converts sparse trajectory-level outcomes into dense step-level supervision that rewards useful actions (even in failed trajectories) while suppressing erroneous or redundant actions.
  arXiv  Detail & Related papers  (2026-08-05T17:41:31Z)
• GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning [61.67411833252235]
  We introduce GradCuit, which inserts optimizable latent states at a selected Transformer layer between the hidden representations of the prompt and the generated continuation.<n>Across five instruction-tuned backbones, three reasoning benchmarks, and two answer formats, GradCuit achieves an average accuracy of 64.5%.<n>For interpretability, token-level gradient attribution reveals that latent influence concentrates on reasoning-connector tokens, while layer analysis identifies early-to-middle Transformer layers as the most effective optimization space.
  arXiv  Detail & Related papers  (2026-08-03T17:55:24Z)
• TrAC: Trace-Conditioned Answer Consistency for Efficient Uncertainty Quantification in LLMs [5.676157325165344]
  Large language models (LLMs) can generate fluent reasoning traces that nevertheless lead to incorrect answers.<n>TrAC is a correctness-supervised uncertainty quantification framework that combines active and passive signals anchored to one completed reasoning trace.<n>TrAC improves macro AUROC by 1.8% and reduces AURC by 3.4% relative to eight-sample self-consistency.
  arXiv  Detail & Related papers  (2026-08-01T03:43:31Z)
• Outcome-Confounded Local Supervision in On-Policy Distillation [0.5937989874256571]
  On-policy distillation trains a student on its own trajectories while a teacher supplies dense token-level likelihoods at student-visited prefixes.<n>We show that both readings are confounded by the outcome of the completed trajectory.<n>We introduce an outcome-resolved diagnostic that crosses pointwise teacher-student divergence with final-answer correctness.
  arXiv  Detail & Related papers  (2026-07-26T16:03:33Z)
• ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning [75.26064451955199]
  ExTra is a framework that extracts exploration signals from the model's own rollouts.<n>It improves Qwen3-1.7B over GRPO by about +5 points on pass@1 and +7 points on pass@16.
  arXiv  Detail & Related papers  (2026-06-23T15:51:39Z)
• Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning [55.264863369127774]
  Current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states.<n>We propose Hidden-Align, an auxiliary loss function that aligns the last-layer hidden states of correct rollouts at the anchor token during RL training, with zero overhead in both training and inference.<n>On eight mathematical reasoning benchmarks, Hidden-Align improves average pass@1 over the DAPO baseline by 3.8, 6.2, and 5.4 percentage points on Qwen3-1.7B, 4B, and 14B respectively, with consistent pass@k gains across all three scales.
  arXiv  Detail & Related papers  (2026-06-02T06:51:15Z)
• StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning [6.365332042924078]
  We present StepOPSD, a post-rollout preference self-distillation framework that takes the agent step as the unit of credit redistribution.<n>StepOPSD decomposes trajectories into action-centered step segments, rescoring them under hindsight-enriched teacher contexts.<n>Results reveal a consistent two-knob law: smaller _clip acts as a broadly stabilizing local trust region, whereas the optimal global mixing strength _mix remains task-dependent.
  arXiv  Detail & Related papers  (2026-05-26T15:07:03Z)
• What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents [70.6980022118038]
  Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging.<n>Existing methods rely on trajectory-level rewards or proxy signals, without fully leveraging per-step environmental feedback.<n>We introduce SERL, a selective environment-reweighted learning framework.
  arXiv  Detail & Related papers  (2026-05-19T07:00:55Z)
• Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization [37.59050823977757]
  Supervised fine-tuning (SFT) on chain-of-thought (CoT) trajectories demonstrations is a common approach for enabling reasoning in large language models.<n>Standard practices typically only retain trajectories with correct final answers (positives) while ignoring the rest (negatives)<n>We argue that this paradigm discards substantial supervision and exacerbates overfitting, limiting out-of-domain (OOD) generalization.<n>We propose Gain-based LOss Weighting (GLOW), an adaptive, sample-aware scheme that exploits such distinctive training dynamics by rescaling per-sample loss based on inter-epoch progress
  arXiv  Detail & Related papers  (2026-01-08T14:49:10Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.