mlsanityData to 7 Oct 2026

PreAct: Prediction Enhances Agent's Planning Ability

arXiv 2402.11534 ↗First posted 18 Feb 2024cs.CL cs.AIcited by 11

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

Key facts. Cited by 11 papers in the map (data through 7 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.

Builds on

26 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models6 Oct
  2. 2023ExpeL: LLM Agents Are Experiential Learners20 Aug
  3. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents3 Feb

Other references · 23

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  7. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  8. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  9. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  10. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  11. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  12. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
11 more
  1. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
  2. 2020ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-trainingcited by 221
  3. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  4. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 174
  5. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  6. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  7. 2023CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalizationcited by 88
  8. 2023Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Taskcited by 23
  9. 2022Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systemscited by 15
  10. 2023DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Taskcited by 5
  11. 2023DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extractioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 4.

11 papers.

  1. 2025InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Researchcited by 18
  2. 2024On the Brittle Foundations of ReAct Prompting for Agentic Large Language Modelscited by 17
  3. 2025A multi-agentic framework for real-time, autonomous freeform metasurface designcited by 14
  4. 2025Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environmentscited by 11
  5. 2024MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Makingcited by 9
  6. 2026The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Checkcited by 6
  7. 2026Aligning Agentic World Models via Knowledgeable Experience Learningcited by 5
  8. 2026Self-Evolving World Models for LLM Agent Planningcited by 5
  9. 2025Declarative Techniques for NL Queries over Heterogeneous Datacited by 1
  10. 2025Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Trainingcited by 1
  11. 2026Substrate-Portable Execution for Production LLM Workflowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents
  2. 2026PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents
  3. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
  4. 2024One STEP at a time: Language Agents are Stepwise Planners
  5. 2026EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
  6. 2026Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning
  7. 2025Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
  8. 2025EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory