# Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.22601 · HTML: https://mlsanity.com/paper/2509.22601/

## Key facts

- Cited by 11 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 98 of its 127 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## 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 98)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [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)
- [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)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (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)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)

## Built on by (most cited first, 11 of 11)

- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization](https://mlsanity.com/paper/2603.03078/) (2026)
- [SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents](https://mlsanity.com/paper/2512.22322/) (2025)
- [Planning with the Views](https://mlsanity.com/paper/2605.29563/) (2026)
- [EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.21946/) (2026)
- [DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents](https://mlsanity.com/paper/2604.24320/) (2026)
- [Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents](https://mlsanity.com/paper/2606.25852/) (2026)
- [RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents](https://mlsanity.com/paper/2607.04713/) (2026)
- [Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localization](https://mlsanity.com/paper/2608.29880/) (2026)
- [Success Leaves Detours: Learning Executable Walkthroughs for Long-Horizon Agents](https://mlsanity.com/paper/2609.22120/) (2026)
- [TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery](https://mlsanity.com/paper/2610.09074/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing studies stimulate exploration through the lens of policy entropy, but such mechanical entropy maximization is prone to RL instability due to the multi-turn distribution shifting. In this paper, we target the progressive exploration-exploitation balance under the guidance of the agent's own experiences without succumbing to either entropy collapsing or runaway divergence. We propose SPEAR, a self-imitation learning (SIL) recipe for training agentic LLMs. It extends the vanilla SIL, where a replay buffer stores good experience for off-policy update, by gradually steering the policy entropy across stages. Specifically, the proposed curriculum scheduling harmonizes intrinsic reward shaping and self-imitation to 1) expedite exploration via frequent tool interactions at the beginning, and 2) strengthen exploitation of successful tactics upon convergence towards familiarity with the environment. We also combine bag-of-tricks of industrial RL optimizations for a strong baseline Dr.BoT to demonstrate our effectiveness. In ALFWorld and WebShop, SPEAR increases the success rates of GRPO/GiGPO/Dr.BoT by up to 16.1%/5.1%/8.6% and 20.7%/11.8%/13.9%, respectively. In AIME24 and AIME25, SPEAR boosts Dr.BoT by up to 3.8% and 6.1%, respectively. Such gains incur only 10%-25% extra theoretical complexity and negligible runtime overhead in practice, demonstrating the plug-and-play scalability of SPEAR.