# Expanding LLM Agent Boundaries with Strategy-Guided Exploration

arXiv: https://arxiv.org/abs/2603.02045 · HTML: https://mlsanity.com/paper/2603.02045/

## Key facts

- Cited by 9 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 40 of its 54 references that are in the map.
- First posted on arXiv 2 Mar 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 40)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning](https://mlsanity.com/paper/2506.01939/) (2025)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)
- [The Option-Critic Architecture](https://mlsanity.com/paper/1609.05140/) (2016)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning](https://mlsanity.com/paper/1611.04717/) (2016)
- [Reasoning with Exploration: An Entropy Perspective](https://mlsanity.com/paper/2506.14758/) (2025)
- [Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots](https://mlsanity.com/paper/2310.13724/) (2023)
- [RT-H: Action Hierarchies Using Language](https://mlsanity.com/paper/2403.01823/) (2024)
- [Parameter Space Noise for Exploration](https://mlsanity.com/paper/1706.01905/) (2017)
- [Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models](https://mlsanity.com/paper/2508.10751/) (2025)
- [Near-Optimal Representation Learning for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1810.01257/) (2018)
- [Motif: Intrinsic Motivation from Artificial Intelligence Feedback](https://mlsanity.com/paper/2310.00166/) (2023)
- [Large Language Models as Generalizable Policies for Embodied Tasks](https://mlsanity.com/paper/2310.17722/) (2023)
- [Outcome-based Exploration for LLM Reasoning](https://mlsanity.com/paper/2509.06941/) (2025)
- [Jointly Reinforcing Diversity and Quality in Language Model Generations](https://mlsanity.com/paper/2509.02534/) (2025)
- [LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs](https://mlsanity.com/paper/2504.14655/) (2025)
- [Optimizing Language Models for Inference Time Objectives using Reinforcement Learning](https://mlsanity.com/paper/2503.19595/) (2025)
- [Semantic Exploration from Language Abstractions and Pretrained Representations](https://mlsanity.com/paper/2204.05080/) (2022)

## Built on by (most cited first, 9 of 9)

- [Agentic Trading: When LLM Agents Meet Financial Markets](https://mlsanity.com/paper/2605.19337/) (2026)
- [Exploration and Exploitation Errors Are Measurable for Language Model Agents](https://mlsanity.com/paper/2604.13151/) (2026)
- [CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V](https://mlsanity.com/paper/2604.07733/) (2026)
- [Instruction-Conditioned Exploration for Reinforcement Learning with Self-Distillation to an Unconditioned Policy](https://mlsanity.com/paper/2608.02087/) (2026)
- [RLTL;DR: Self-improvement by Internalizing Self-generated Feedback](https://mlsanity.com/paper/2609.37633/) (2026)
- [DORA Explorer: Improving the Exploration Ability of LLMs Without Training](https://mlsanity.com/paper/2604.17244/) (2026)
- [Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction](https://mlsanity.com/paper/2607.01764/) (2026)
- [Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents](https://mlsanity.com/paper/2610.02525/) (2026)
- [Structuring MoE Expert Selection for Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.07332/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) has demonstrated notable success in post-training large language models (LLMs) as agents for tasks such as computer use, tool calling, and coding. However, exploration remains a central challenge in RL for LLM agents, especially as they operate in language-action spaces with complex observations and sparse outcome rewards. In this work, we address exploration for LLM agents by leveraging the ability of LLMs to plan and reason in language about the environment to shift exploration from low-level actions to higher-level language strategies. We thus propose Strategy-Guided Exploration (SGE), which first generates a concise natural-language strategy that describes what to do to make progress toward the goal, and then generates environment actions conditioned on that strategy. By exploring in the space of strategies rather than the space of actions, SGE induces structured and diverse exploration that targets different environment outcomes. To increase strategy diversity during RL, SGE introduces mixed-temperature sampling, which explores diverse strategies in parallel, along with a strategy reflection process that grounds strategy generation on the outcomes of previous strategies in the environment. Across UI interaction, tool-calling, coding, and embodied agent environments, SGE consistently outperforms exploration-focused RL baselines, improving both learning efficiency and final performance. We show that SGE enables the agent to learn to solve tasks too difficult for the base model.