# Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents

arXiv: https://arxiv.org/abs/2505.09970 · HTML: https://mlsanity.com/paper/2505.09970/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 15 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 13 of 13)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning](https://mlsanity.com/paper/2402.18865/) (2024)
- [Continual Learning with Low Rank Adaptation](https://mlsanity.com/paper/2311.17601/) (2023)
- [AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents](https://mlsanity.com/paper/2404.06411/) (2024)
- [Automated test generation to evaluate tool-augmented LLMs as conversational AI agents](https://mlsanity.com/paper/2409.15934/) (2024)
- [Position Paper: Agent AI Towards a Holistic Intelligence](https://mlsanity.com/paper/2403.00833/) (2024)

## Built on by (most cited first, 24 of 24)

- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios](https://mlsanity.com/paper/2509.21766/) (2025)
- [The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems](https://mlsanity.com/paper/2507.02097/) (2025)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents](https://mlsanity.com/paper/2601.07577/) (2026)
- [PDE-Agent: A toolchain-augmented multi-agent framework for PDE solving](https://mlsanity.com/paper/2512.16214/) (2025)
- [PolyServe: Efficient Multi-SLO Serving at Scale](https://mlsanity.com/paper/2507.17769/) (2025)
- [Plantain: Plan-Answer Interleaved Reasoning](https://mlsanity.com/paper/2512.03176/) (2025)
- [The Six Sigma Agent: Achieving Enterprise-Grade Reliability in LLM Systems Through Consensus-Driven Decomposed Execution](https://mlsanity.com/paper/2601.22290/) (2026)
- [Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs](https://mlsanity.com/paper/2604.03870/) (2026)
- [IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents](https://mlsanity.com/paper/2605.22154/) (2026)
- [Model-First Reasoning LLM Agents: Reducing Hallucinations through Explicit Problem Modeling](https://mlsanity.com/paper/2512.14474/) (2025)
- [RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution](https://mlsanity.com/paper/2605.00798/) (2026)
- [From Table to Cell: Attention for Better Reasoning with TABALIGN](https://mlsanity.com/paper/2605.14465/) (2026)
- [How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study](https://mlsanity.com/paper/2604.00005/) (2026)
- [TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents](https://mlsanity.com/paper/2608.00967/) (2026)
- [Automating Complex Document Workflows via Stepwise and Rollback-Enabled Operation Orchestration](https://mlsanity.com/paper/2512.04445/) (2025)
- [OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows](https://mlsanity.com/paper/2602.04144/) (2026)
- [How Far Are We? Systematic Evaluation of LLMs vs. Human Experts in Mathematical Contest in Modeling](https://mlsanity.com/paper/2604.04791/) (2026)
- [NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability](https://mlsanity.com/paper/2607.28942/) (2026)
- [SGG-ReflAct: Sub-Goal Guided ReflAct with Structured Planning for Reliable Long-Horizon Reasoning](https://mlsanity.com/paper/2609.34548/) (2026)
- [ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation](https://mlsanity.com/paper/2610.09163/) (2026)
- [MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents](https://mlsanity.com/paper/2610.12757/) (2026)
- [Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement](https://mlsanity.com/paper/2610.15661/) (2026)

## Abstract (arXiv)

The ReAct (Reasoning + Action) capability in large language models (LLMs) has become the foundation of modern agentic systems. Recent LLMs, such as DeepSeek-R1 and OpenAI o1/o3, exemplify this by emphasizing reasoning through the generation of ample intermediate tokens, which help build a strong premise before producing the final output tokens. In this paper, we introduce Pre-Act, a novel approach that enhances the agent's performance by creating a multi-step execution plan along with the detailed reasoning for the given user input. This plan incrementally incorporates previous steps and tool outputs, refining itself after each step execution until the final response is obtained. Our approach is applicable to both conversational and non-conversational agents. To measure the performance of task-oriented agents comprehensively, we propose a two-level evaluation framework: (1) turn level and (2) end-to-end. Our turn-level evaluation, averaged across five models, shows that our approach, Pre-Act, outperforms ReAct by 70% in Action Recall on the Almita dataset. While this approach is effective for larger models, smaller models crucial for practical applications, where latency and cost are key constraints, often struggle with complex reasoning tasks required for agentic systems. To address this limitation, we fine-tune relatively small models such as Llama 3.1 (8B & 70B) using the proposed Pre-Act approach. Our experiments show that the fine-tuned 70B model outperforms GPT-4, achieving a 69.5% improvement in action accuracy (turn-level) and a 28% improvement in goal completion rate (end-to-end) on the Almita (out-of-domain) dataset.