# Fact-Augmented Lookahead Planning for LLM Agents

arXiv: https://arxiv.org/abs/2506.09171 · HTML: https://mlsanity.com/paper/2506.09171/

## Key facts

- Cited by 8 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 19 of its 51 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## 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, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models](https://mlsanity.com/paper/2408.00724/) (2024)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)
- [Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control](https://mlsanity.com/paper/2306.07863/) (2023)
- [Translating Natural Language to Planning Goals with Large-Language Models](https://mlsanity.com/paper/2302.05128/) (2023)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents](https://mlsanity.com/paper/2410.13825/) (2024)
- [Why think step by step? Reasoning emerges from the locality of experience](https://mlsanity.com/paper/2304.03843/) (2023)
- [Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification](https://mlsanity.com/paper/2502.01839/) (2025)
- [Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency](https://mlsanity.com/paper/2309.17382/) (2023)
- [In-Context Principle Learning from Mistakes](https://mlsanity.com/paper/2402.05403/) (2024)
- [Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling](https://mlsanity.com/paper/2506.15707/) (2025)
- [DISC: Dynamic Decomposition Improves LLM Inference Scaling](https://mlsanity.com/paper/2502.16706/) (2025)
- [Position: The ML Community Must Build an AI-Augmented Peer-Review Ecosystem](https://mlsanity.com/paper/2506.08134/) (2025)

## Built on by (most cited first, 8 of 8)

- [Watch and Learn: Learning to Use Computers from Online Videos](https://mlsanity.com/paper/2510.04673/) (2025)
- [When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent](https://mlsanity.com/paper/2601.07263/) (2026)
- [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025)
- [Bridging the Agent-World Gap: Text World Models for LLM-based Agents](https://mlsanity.com/paper/2606.09032/) (2026)
- [AutoContext: Instance-Level Context Learning for LLM Agents](https://mlsanity.com/paper/2510.02369/) (2025)
- [When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?](https://mlsanity.com/paper/2605.28224/) (2026)
- [Verify Claims, Not Scores: Evidence-Based Verification of Modular Agents](https://mlsanity.com/paper/2610.01348/) (2026)
- [ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents](https://mlsanity.com/paper/2610.04889/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly capable, but LLM agents still struggle to plan effectively in interactive, partially observable, long-horizon environments when search is unguided or recent history is insufficient. We introduce LWM-Planner, a fact-augmented lookahead planning framework that improves agent behavior purely through in-context learning. After each episode, the agent extracts task-critical atomic facts from its trajectories, validates candidates with a lightweight predictive-consistency filter (and optionally compresses them), and uses the resulting fact set to condition action proposal, single-step latent world-model simulation, and state-value estimation. Planning then proceeds via recursive, depth-limited lookahead over candidate trajectories conditioned on the accumulated facts and recent history, enabling online improvement without parameter updates. We provide abstraction-style motivation: treating facts as reducing state aliasing (proxy εsim) and fact-conditioned simulation as lowering one-step error (proxy δmodel), without claiming formal guarantees. Empirically, on text FrozenLake variants, CrafterMini, and ALFWorld, the approach improves cumulative return over ReAct/Reflexion and search-only baselines, suggesting that additional test-time search is most useful when grounded by compact, experience-derived facts.