# Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations

arXiv: https://arxiv.org/abs/2607.04235 · HTML: https://mlsanity.com/paper/2607.04235/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 41 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 31)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [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)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning](https://mlsanity.com/paper/1810.08272/) (2018)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis](https://mlsanity.com/paper/2412.19723/) (2024)
- [Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making](https://mlsanity.com/paper/2410.07166/) (2024)
- [AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials](https://mlsanity.com/paper/2412.09605/) (2024)
- [From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data](https://mlsanity.com/paper/2210.10047/) (2022)
- [SafeArena: Evaluating the Safety of Autonomous Web Agents](https://mlsanity.com/paper/2503.04957/) (2025)
- [Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement](https://mlsanity.com/paper/2406.11176/) (2024)
- [The Wisdom of Hindsight Makes Language Models Better Instruction Followers](https://mlsanity.com/paper/2302.05206/) (2023)
- [BAGEL: Bootstrapping Agents by Guiding Exploration with Language](https://mlsanity.com/paper/2403.08140/) (2024)
- [Plancraft: an evaluation dataset for planning with LLM agents](https://mlsanity.com/paper/2412.21033/) (2024)
- [SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2502.03283/) (2025)

## Built on by (most cited first, 5 of 5)

- [ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs](https://mlsanity.com/paper/2608.25992/) (2026)
- [AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories](https://mlsanity.com/paper/2609.05837/) (2026)
- [EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making](https://mlsanity.com/paper/2609.38334/) (2026)
- [Learning to Act with Task Progress: Distilling Small Agents from Compact Teacher Supervision](https://mlsanity.com/paper/2610.10332/) (2026)
- [Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics](https://mlsanity.com/paper/2610.13000/) (2026)

## Abstract (arXiv)

Large language model agents operate in partially observable, long-horizon settings where obtaining supervision remains a major bottleneck. We address this by utilizing a source of supervision overlooked in existing post-training methods: unintended yet successful goals embedded within agent rollouts. Specifically, we introduce Hindsight Supervised Learning (HSL), where an auxiliary LLM reviews each completed trajectory and relabels it with all of the natural-language goals the agent actually achieved. HSL then pairs the trajectory with its relabeled goals and uses these pairs for additional fine-tuning. To mitigate suboptimality in the relabeled data, we propose two learning techniques for HSL, irrelevant-action masking and sample reweighting. Our experiments show that HSL is flexible and compatible with existing post-training pipelines. It improves both SFT and DPO, with larger gains on long-horizon tasks with more diverse goal spaces. Moreover, HSL is sample-efficient: on ALFWorld, it surpasses baselines trained on the full dataset while using only one quarter of the ground-truth demonstrations.