{"ID":2875126,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.03581","arxiv_id":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","abstract":"Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action; however, we demonstrate that always planning is computationally expensive and degrades performance on long-horizon tasks, while never planning further limits performance. To address this, we introduce a conceptual framework formalizing dynamic planning for LLM agents, enabling them to flexibly decide when to allocate test-time compute for planning. We propose a simple two-stage training pipeline: (1) supervised fine-tuning on diverse synthetic data to prime models for dynamic planning, and (2) RL to refine this capability in long-horizon environments. Experiments on the Crafter environment show that dynamic planning agents trained with this approach are more sample-efficient and consistently achieve more complex objectives. Additionally, we demonstrate that these agents can be effectively steered by human-written plans, surpassing their independent capabilities and highlighting the potential for safer and more collaborative agentic systems.","short_abstract":"Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action; however, we demonstrate that always planning is computationally expensive and de...","url_abs":"https://arxiv.org/abs/2509.03581","url_pdf":"https://arxiv.org/pdf/2509.03581v3","authors":"[\"Davide Paglieri\",\"Bartłomiej Cupiał\",\"Jonathan Cook\",\"Ulyana Piterbarg\",\"Jens Tuyls\",\"Edward Grefenstette\",\"Jakob Nicolaus Foerster\",\"Jack Parker-Holder\",\"Tim Rocktäschel\"]","published":"2025-09-03T18:00:13Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}