# Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents

arXiv: https://arxiv.org/abs/2609.33391 · HTML: https://mlsanity.com/paper/2609.33391/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in On-policy and self-distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)

## Builds on (most cited first, 25 of 25)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [RUDDER: Return Decomposition for Delayed Rewards](https://mlsanity.com/paper/1806.07857/) (2018)
- [Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents](https://mlsanity.com/paper/2604.10674/) (2026)
- [Hindsight Credit Assignment for Long-Horizon LLM Agents](https://mlsanity.com/paper/2603.08754/) (2026)
- [TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents](https://mlsanity.com/paper/2604.24005/) (2026)
- [Rethinking On-Policy Self-Distillation for Thinking Models](https://mlsanity.com/paper/2607.05184/) (2026)
- [OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning](https://mlsanity.com/paper/2606.26790/) (2026)
- [StepOPSD: Step-Aware Online Preference Self-Distillation for Agent Reinforcement Learning](https://mlsanity.com/paper/2605.27140/) (2026)
- [What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents](https://mlsanity.com/paper/2605.19447/) (2026)
- [Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance](https://mlsanity.com/paper/2606.00305/) (2026)
- [GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation](https://mlsanity.com/paper/2605.11853/) (2026)
- [Latent On-Policy Self-Distillation](https://mlsanity.com/paper/2608.13040/) (2026)
- [TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents](https://mlsanity.com/paper/2608.16156/) (2026)

## Abstract (arXiv)

Reinforcement learning with verifiable rewards (RLVR) often relies on sparse outcome rewards, providing coarse supervision for long-horizon agents. On-policy self-distillation (OPSD) complements this signal with dense privileged feedback. However, we identify Decision--Timestamp Mismatch: privileged guidance may be misaligned with the student's functional decision because the corresponding decision can occur at a different timestep, while the student's decision itself may span multiple timesteps rather than being tied to a single timestamp. Thus, timestamp-local supervision can misalign both the context and the temporal scope of credit. To address this mismatch, we introduce textscAlignOPSD, following the principle of aligning supervision before assigning credit. Decision-Aligned Supervision Rectification re-scores the same student-sampled response in functionally matched contexts across sibling rollouts to calibrate local teacher evidence. Semi-Markov Hierarchical Credit Assignment then derives variable-duration decision spans from correspondence changes and uses rectified evidence to allocate outcome-grounded credit across spans and their constituent turns. We evaluate textscAlignOPSD with Qwen2.5-3B and Qwen2.5-7B on ALFWorld, WebShop, and Search-QA against representative baselines. textscAlignOPSD outperforms both GRPO and StepOPSD across all eight backbone--aggregate-metric comparisons, improving on GRPO by 5.5--8.7 % and ranking first in six. Additional analyzes examine the two alignment stages and hyperparameter sensitivity between tasks. Our code is avaliable at https://github.com/mingju-c/Align-OPSD