HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation

• URL: http://arxiv.org/abs/2606.11559v1
• Date: Wed, 10 Jun 2026 01:35:34 GMT
• Title: HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation
• Abstract summary: HERO is a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback.<n> HERO improves task success and reduces unnecessary turns over environment-feedback-only self-distillation and GRPO.
• Score: 50.53459634301361
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning typically improves multi-turn agent capabilities through the terminal outcome of the trajectories, which makes it difficult to determine credit assignments for each intermediate turns. Recent on-policy self-distillation methods offer a promising alternative by converting privileged feedback into dense token-level supervision through a self-teacher. Our study is motivated by the unexpected performance degradation observed when naively extending this paradigm to multi-turn settings, which we attribute to a lack of alignment between privileged feedback, such as successful trajectories or terminal outcomes, and the student's current decision context. We introduce HERO, a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback. After each rollout, HERO reflects on the completed interaction to convert each observation into a compact turn-level diagnosis, that captures actionable feedback about the original action such as its necessity, validity or failure cause. On TauBench and WebShop, HERO improves task success and reduces unnecessary turns over environment-feedback-only self-distillation and GRPO. It is especially effective under limited training turn budgets, where successful rollouts are rare and GRPO provides weak reward-contrast signals.

Related papers

• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• Adaptive Supervised Anchoring for On-Policy Self-Distillation [15.445625053566244]
  On-policy self-distillation adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student.<n>We show that when student rollouts drift from target trajectories, conditioning the teacher on off-target prefixes substantially weakens its task-relevant supervision.<n>We propose a unified training framework that separates two complementary supervision pathways.
  arXiv  Detail & Related papers  (2026-08-08T05:46:32Z)
• Group-Reflective Self-Distillation for Agentic Reinforcement Learning [8.041052886037766]
  Group-Reflective Self-Distillation (GRSD) derives capability-aligned and outcome-discriminative guidance from the policy's own verified rollouts.<n>GRSD consistently outperforms competitive baselines and generalizes more effectively to unseen tasks.
  arXiv  Detail & Related papers  (2026-07-30T11:49:46Z)
• Contrastive Reinforced Policy Optimization via Privileged Self-Distillation [23.840537431318296]
  We introduce Contrastive Reinforced Policy Optimization (CRPO), which reformulates agentic On-Policy Self-Distillation (OPSD) from a contrastive learning perspective.<n>CRPO consistently outperforms existing reinforcement learning and self-distillation baselines.
  arXiv  Detail & Related papers  (2026-07-30T11:14:11Z)
• Purified OPSD: On-Policy Self-Distillation Without Losing How to Think [52.879387744920415]
  We find that on-policy self-distillation (OPSD) consistently fails on long chain-of-thought (long-CoT) reasoning models.<n>We propose a two-step solution: first, we construct a reference-only teacher to isolate the non-transferable component of the supervision signal.<n>Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution.
  arXiv  Detail & Related papers  (2026-07-02T14:33:07Z)
• Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation [60.55792673956761]
  We propose textbfRubric-Conditioned Self-Distillation, a framework that incorporates rubrics as structured, fine-grained feedback for on-policy self-distillation.<n>We evaluate on a diverse suite of science reasoning benchmarks and results show that rubric-conditioned self-distillation effectively converts rubric-level criteria into token-level guidance.
  arXiv  Detail & Related papers  (2026-06-17T17:54:04Z)
• 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)
• HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents [45.00250014235802]
  Training long-horizon LLM agents with reinforcement learning is challenging because sparse outcome rewards reveal whether a task succeeds, but not which intermediate actions caused the outcome or how they should be corrected.<n>Recent methods alleviate this issue by generating rewards or textual hints from turn-level action-output signals, or by using feedback-conditioned self-distillation.<n>We propose HINT-SD, a targeted self-distillation framework that uses full-trajectory hindsight to select failure-relevant actions and applies feedback-conditioned distillation only on targeted action spans.
  arXiv  Detail & Related papers  (2026-05-18T05:34:03Z)
• Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation [71.16738415436458]
  We introduce Reflection-Enhanced Self-Distillation (RESD), a framework that transforms raw failure feedback into an active source of corrective supervision.<n>RESD interprets failed trajectories by generating retrospective reflections to diagnose local errors, and curates a persistent global playbook.<n> Empirical evaluations on multiple continual learning tasks demonstrate that RESD substantially outperforms standard self-distillation baselines.
  arXiv  Detail & Related papers  (2026-05-12T20:46:05Z)
• TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents [55.27396165691312]
  We identify a key limitation of vanilla OPD in multi-turn agent settings, which we term Trajectory-Level KL Instability.<n>We propose TCOD, a framework that controls the trajectory depth exposed to the student and progressively expands it with a curriculum schedule.<n> Experimental results across four student-teacher pairs show that TCOD mitigates KL escalation and enhances KL stability throughout training, improving agent performance by up to 18 points over vanilla OPD.
  arXiv  Detail & Related papers  (2026-04-27T03:38:27Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Internalizing Agency from Reflective Experience [20.650609947690196]
  LEAFE is a framework that internalizes recovery agency from reflective experience.<n>It consistently improves Pass@1 over the base model and achieves higher Pass@k than outcome-driven baselines.
  arXiv  Detail & Related papers  (2026-03-17T17:50:47Z)
• Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning [11.084321518414226]
  We adapt existing importance-sampling ratio estimation techniques for off-policy evaluation to drastically improve the stability and efficiency of so-called hindsight policy methods. Our hindsight distribution correction facilitates stable, efficient learning across a broad range of environments where credit assignment plagues baseline methods.
  arXiv  Detail & Related papers  (2023-07-21T20:54:52Z)

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.