# Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents

arXiv: https://arxiv.org/abs/2601.22311 · HTML: https://mlsanity.com/paper/2601.22311/

## Key facts

- Cited by 23 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 46 of its 123 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## 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, 30 of 46)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Reinforcement Learning for Reasoning in Large Language Models with One Training Example](https://mlsanity.com/paper/2504.20571/) (2025)
- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Large Language Model Guided Tree-of-Thought](https://mlsanity.com/paper/2305.08291/) (2023)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://mlsanity.com/paper/2508.07976/) (2025)
- [StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models](https://mlsanity.com/paper/2403.07714/) (2024)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning](https://mlsanity.com/paper/2406.09187/) (2024)
- [AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2509.08755/) (2025)
- [Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation](https://mlsanity.com/paper/2407.10805/) (2024)
- [Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning](https://mlsanity.com/paper/2312.05230/) (2023)
- [Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2305.16582/) (2023)
- [FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents](https://mlsanity.com/paper/2406.14884/) (2024)
- [Monte Carlo Tree Diffusion for System 2 Planning](https://mlsanity.com/paper/2502.07202/) (2025)

## Built on by (most cited first, 23 of 23)

- [Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents](https://mlsanity.com/paper/2605.06908/) (2026)
- [Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization](https://mlsanity.com/paper/2605.21801/) (2026)
- [TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering](https://mlsanity.com/paper/2605.05980/) (2026)
- [W2T: LoRA Weights Already Know What They Can Do](https://mlsanity.com/paper/2603.15990/) (2026)
- [PreScam: A Benchmark for Predicting Scam Progression from Early Conversations](https://mlsanity.com/paper/2605.12243/) (2026)
- [ProPlay: Procedural World Models for Self-Evolving LLM Agents](https://mlsanity.com/paper/2606.12780/) (2026)
- [MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback](https://mlsanity.com/paper/2606.12916/) (2026)
- [AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents](https://mlsanity.com/paper/2607.02255/) (2026)
- [Learning Stateful Predictive Knowledge From Experience](https://mlsanity.com/paper/2607.28638/) (2026)
- [The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to Coordinate](https://mlsanity.com/paper/2608.22152/) (2026)
- [CAFE: Self-Improving Search Agents Need Co-Evolving Feedback](https://mlsanity.com/paper/2608.24794/) (2026)
- [Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling](https://mlsanity.com/paper/2609.00949/) (2026)
- [Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework](https://mlsanity.com/paper/2604.22119/) (2026)
- [Skill Reuse as Compression in Agentic RL](https://mlsanity.com/paper/2605.31509/) (2026)
- [Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework](https://mlsanity.com/paper/2606.27757/) (2026)
- [Ask the World Before Acting: Environment Probing for Calibrated Agent World Models](https://mlsanity.com/paper/2606.31422/) (2026)
- [Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents](https://mlsanity.com/paper/2609.00823/) (2026)
- [MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents](https://mlsanity.com/paper/2603.13131/) (2026)
- [Temporal Preference Concepts and their Functions in a Large Language Model](https://mlsanity.com/paper/2606.05194/) (2026)
- [Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms](https://mlsanity.com/paper/2609.27321/) (2026)
- [Verification as an Architectural Layer for LLM Agents: A V-Model Design, and a Pilot Study of Its Deterministic Core](https://mlsanity.com/paper/2609.31937/) (2026)
- [HyperMCTS: Hypergraph-Augmented MCTS for Long-Horizon LLM Agents](https://mlsanity.com/paper/2609.33920/) (2026)
- [Marathoner: Ultra-Long-Horizon Autonomous Intelligence](https://mlsanity.com/paper/2609.34378/) (2026)

## Abstract (arXiv)

Large language model (LLM)-based agents exhibit strong step-by-step reasoning capabilities over short horizons, yet often fail to sustain coherent behavior over long planning horizons. We argue that this failure reflects a fundamental mismatch: step-wise reasoning induces a form of step-wise greedy policy that is adequate for short horizons but fails in long-horizon planning, where early actions must account for delayed consequences. From this planning-centric perspective, we study LLM-based agents in deterministic, fully structured environments with explicit state transitions and evaluation signals. Our analysis reveals a core failure mode of reasoning-based policies: locally optimal choices induced by step-wise scoring lead to early myopic commitments that are systematically amplified over time and difficult to recover from. We introduce FLARE (Future-aware Lookahead with Reward Estimation) as a minimal instantiation of future-aware planning to enforce explicit lookahead, value propagation, and limited commitment in a single model, allowing downstream outcomes to influence early decisions. Across multiple benchmarks, agent frameworks, and LLM backbones, FLARE consistently improves task performance and planning-level behavior, frequently allowing LLaMA-8B with FLARE to outperform GPT-4o with standard step-by-step reasoning. These results establish a clear distinction between reasoning and planning.