# Revealing the Barriers of Language Agents in Planning

arXiv: https://arxiv.org/abs/2410.12409 · HTML: https://mlsanity.com/paper/2410.12409/

## Key facts

- Cited by 20 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 30 of its 49 references that are in the map.
- First posted on arXiv 16 Oct 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, 30 of 30)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks](https://mlsanity.com/paper/2402.08115/) (2024)
- [Large Language Models for Robotics: A Survey](https://mlsanity.com/paper/2311.07226/) (2023)
- [A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writing](https://mlsanity.com/paper/2310.08433/) (2023)
- [CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization](https://mlsanity.com/paper/2310.10134/) (2023)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [Agent Lumos: Unified and Modular Training for Open-Source Language Agents](https://mlsanity.com/paper/2311.05657/) (2023)
- [Attention Heads of Large Language Models: A Survey](https://mlsanity.com/paper/2409.03752/) (2024)
- [Did the Model Understand the Question?](https://mlsanity.com/paper/1805.05492/) (2018)
- [Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors](https://mlsanity.com/paper/2305.11159/) (2023)
- [Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments](https://mlsanity.com/paper/2402.14672/) (2024)
- [Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning](https://mlsanity.com/paper/2405.20625/) (2024)
- [VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers](https://mlsanity.com/paper/2305.13417/) (2023)
- [MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following](https://mlsanity.com/paper/2312.02436/) (2023)
- [Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2401.17686/) (2024)
- [TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation](https://mlsanity.com/paper/2402.05733/) (2024)
- [Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example](https://mlsanity.com/paper/2408.06318/) (2024)

## Built on by (most cited first, 20 of 20)

- [Agent Learning via Early Experience](https://mlsanity.com/paper/2510.08558/) (2025)
- [Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training](https://mlsanity.com/paper/2501.11425/) (2025)
- [LLM Agents for Education: Advances and Applications](https://mlsanity.com/paper/2503.11733/) (2025)
- [Large Language Models for Planning: A Comprehensive and Systematic Survey](https://mlsanity.com/paper/2505.19683/) (2025)
- [STeCa: Step-level Trajectory Calibration for LLM Agent Learning](https://mlsanity.com/paper/2502.14276/) (2025)
- [Implicit Reasoning in Transformers is Reasoning through Shortcuts](https://mlsanity.com/paper/2503.07604/) (2025)
- [Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation](https://mlsanity.com/paper/2511.12254/) (2025)
- [Surgical Action Planning with Large Language Models](https://mlsanity.com/paper/2503.18296/) (2025)
- [Weaker LLMs' Opinions Also Matter: Mixture of Opinions Enhances LLM's Mathematical Reasoning](https://mlsanity.com/paper/2502.19622/) (2025)
- [Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving](https://mlsanity.com/paper/2505.04528/) (2025)
- [Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling](https://mlsanity.com/paper/2505.22290/) (2025)
- [iCLP: Large Language Model Reasoning with Implicit Cognition Latent Planning](https://mlsanity.com/paper/2512.24014/) (2025)
- [Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions](https://mlsanity.com/paper/2511.15830/) (2025)
- [Decoupled Travel Planning with Behavior Forest](https://mlsanity.com/paper/2604.21354/) (2026)
- [A Technical Taxonomy of LLM Agent Communication Protocols](https://mlsanity.com/paper/2606.19135/) (2026)
- [World-Model Collapse as a Phase Transition](https://mlsanity.com/paper/2606.31399/) (2026)
- [Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA](https://mlsanity.com/paper/2505.16293/) (2025)
- [Agentomics-ML: Autonomous Machine Learning Experimentation Agent for Genomic and Transcriptomic Data](https://mlsanity.com/paper/2506.05542/) (2025)
- [CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs](https://mlsanity.com/paper/2607.04854/) (2026)
- [Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems](https://mlsanity.com/paper/2607.27443/) (2026)

## Abstract (arXiv)

Autonomous planning has been an ongoing pursuit since the inception of artificial intelligence. Based on curated problem solvers, early planning agents could deliver precise solutions for specific tasks but lacked generalization. The emergence of large language models (LLMs) and their powerful reasoning capabilities has reignited interest in autonomous planning by automatically generating reasonable solutions for given tasks. However, prior research and our experiments show that current language agents still lack human-level planning abilities. Even the state-of-the-art reasoning model, OpenAI o1, achieves only 15.6% on one of the complex real-world planning benchmarks. This highlights a critical question: What hinders language agents from achieving human-level planning? Although existing studies have highlighted weak performance in agent planning, the deeper underlying issues and the mechanisms and limitations of the strategies proposed to address them remain insufficiently understood. In this work, we apply the feature attribution study and identify two key factors that hinder agent planning: the limited role of constraints and the diminishing influence of questions. We also find that although current strategies help mitigate these challenges, they do not fully resolve them, indicating that agents still have a long way to go before reaching human-level intelligence.