# Milestone-Guided Policy Learning for Long-Horizon Language Agents

arXiv: https://arxiv.org/abs/2605.06078 · HTML: https://mlsanity.com/paper/2605.06078/

## Key facts

- Cited by 19 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 25 of its 34 references that are in the map.
- First posted on arXiv 7 May 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, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [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)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024)
- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents](https://mlsanity.com/paper/2507.22844/) (2025)
- [CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution](https://mlsanity.com/paper/2603.17775/) (2026)
- [GroundAct: Can LLM Agents Ground Actions in Environmental States?](https://mlsanity.com/paper/2508.05614/) (2025)

## Built on by (most cited first, 19 of 19)

- [UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents](https://mlsanity.com/paper/2607.04425/) (2026)
- [SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution](https://mlsanity.com/paper/2607.26784/) (2026)
- [ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL](https://mlsanity.com/paper/2606.31650/) (2026)
- [Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements](https://mlsanity.com/paper/2608.17310/) (2026)
- [MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments](https://mlsanity.com/paper/2606.19893/) (2026)
- [Agent-G2: Gaussian Guidance for Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.23318/) (2026)
- [Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design](https://mlsanity.com/paper/2609.22086/) (2026)
- [When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning](https://mlsanity.com/paper/2605.09860/) (2026)
- [Trajectories That Segment Themselves: Agent-Declared Boundaries as a Training Unit](https://mlsanity.com/paper/2608.02302/) (2026)
- [When Metrics Reward the Worst Translations: Internalizing Cultural Reasoning for Social Media Translation Evaluation](https://mlsanity.com/paper/2609.08156/) (2026)
- [Learning to Act with Task Progress: Distilling Small Agents from Compact Teacher Supervision](https://mlsanity.com/paper/2610.10332/) (2026)
- [ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills](https://mlsanity.com/paper/2610.12403/) (2026)
- [Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents](https://mlsanity.com/paper/2610.13058/) (2026)
- [Matched-Context Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2610.13755/) (2026)
- [PTGPO: Prefix Tree Group Policy Optimization](https://mlsanity.com/paper/2610.14737/) (2026)
- [DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter](https://mlsanity.com/paper/2610.17666/) (2026)
- [ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.18683/) (2026)
- [Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards](https://mlsanity.com/paper/2610.19868/) (2026)
- [Co-Evolving Acting and Forecasting for Language Agents](https://mlsanity.com/paper/2610.20597/) (2026)

## Abstract (arXiv)

While long-horizon agentic tasks require language agents to perform dozens of sequential decisions, training such agents with reinforcement learning remains challenging. We identify two root causes: credit misattribution, where correct early actions are penalized due to terminal failures, and sample inefficiency, where scarce successful trajectories result in near-total loss of learning signal. We introduce a milestone-guided policy learning framework, BEACON, that leverages the compositional structure of long-horizon tasks to ensure precise credit assignment. BEACON partitions trajectories at milestone boundaries, applies temporal reward shaping within segments to credit partial progress, and estimates advantages at dual scales to prevent distant failures from corrupting the evaluation of local actions. On ALFWorld, WebShop, and ScienceWorld, BEACON consistently outperforms GRPO and GiGPO. Notably, on long-horizon ALFWorld tasks, BEACON achieves 92.9% success rate, nearly doubling GRPO's 53.5%, while improving effective sample utilization from 23.7% to 82.0%. These results establish milestone-anchored credit assignment as an effective paradigm for training long-horizon language agents. Code is available at https://github.com/ZJU-REAL/BEACON.