# PreAct: Prediction Enhances Agent's Planning Ability arXiv: https://arxiv.org/abs/2402.11534 ยท HTML: https://mlsanity.com/paper/2402.11534/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. - Builds on 26 of its 45 references that are in the map. - First posted on arXiv 18 Feb 2024. ## Placed in - 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, 26 of 26) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022) - [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022) - [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018) - [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020) - [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022) - [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022) - [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023) - [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023) - [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017) - [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023) - [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015) - [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023) - [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020) - [Large Language Models as Commonsense Knowledge for Large-Scale Task Planning](https://mlsanity.com/paper/2305.14078/) (2023) - [ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training](https://mlsanity.com/paper/2001.04063/) (2020) - [ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models](https://mlsanity.com/paper/2305.18323/) (2023) - [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021) - [ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory](https://mlsanity.com/paper/2306.03901/) (2023) - [ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search](https://mlsanity.com/paper/2310.13227/) (2023) - [CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization](https://mlsanity.com/paper/2310.10134/) (2023) - [Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task](https://mlsanity.com/paper/2310.06504/) (2023) - [Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2210.08873/) (2022) - [DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task](https://mlsanity.com/paper/2310.10169/) (2023) - [DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extraction](https://mlsanity.com/paper/2310.10481/) (2023) ## Built on by (most cited first, 12 of 12) - [InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research](https://mlsanity.com/paper/2510.27598/) (2025) - [On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models](https://mlsanity.com/paper/2405.13966/) (2024) - [A multi-agentic framework for real-time, autonomous freeform metasurface design](https://mlsanity.com/paper/2503.20479/) (2025) - [Self-Evolving World Models for LLM Agent Planning](https://mlsanity.com/paper/2606.30639/) (2026) - [Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments](https://mlsanity.com/paper/2505.17616/) (2025) - [MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making](https://mlsanity.com/paper/2409.16686/) (2024) - [The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check](https://mlsanity.com/paper/2601.12979/) (2026) - [Aligning Agentic World Models via Knowledgeable Experience Learning](https://mlsanity.com/paper/2601.13247/) (2026) - [Declarative Techniques for NL Queries over Heterogeneous Data](https://mlsanity.com/paper/2510.16470/) (2025) - [Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training](https://mlsanity.com/paper/2510.27630/) (2025) - [Substrate-Portable Execution for Production LLM Workflows](https://mlsanity.com/paper/2609.06128/) (2026) - [Look Before You Restore: Learning to Predict Before Acting for Agentic Image Restoration](https://mlsanity.com/paper/2610.20384/) (2026) ## Abstract (arXiv) Addressing the disparity between forecasts and actual results can enable individuals to expand their thought processes and stimulate self-reflection, thus promoting accurate planning. In this research, we present **PreAct**, an agent framework that integrates **pre**diction, **rea**soning, and **act**ion. By utilizing the information derived from predictions, the large language model (LLM) agent can provide a wider range and more strategically focused reasoning. This leads to more efficient actions that aid the agent in accomplishing intricate tasks. Our experimental results show that PreAct surpasses the ReAct method in completing complex tasks and that PreAct's performance can be further improved when paired with other memory or selection strategy techniques. We presented the model with varying quantities of historical predictions and discovered that these predictions consistently enhance LLM planning.The variances in single-step reasoning between PreAct and ReAct indicate that PreAct indeed has benefits in terms of diversity and strategic orientation over ReAct.