# Plan Verification for LLM-Based Embodied Task Completion Agents

arXiv: https://arxiv.org/abs/2509.02761 · HTML: https://mlsanity.com/paper/2509.02761/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 18 of 18)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [Building Cooperative Embodied Agents Modularly with Large Language Models](https://mlsanity.com/paper/2307.02485/) (2023)
- [TEACh: Task-driven Embodied Agents that Chat](https://mlsanity.com/paper/2110.00534/) (2021)
- [Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment](https://mlsanity.com/paper/2402.14016/) (2024)
- [Embodied Task Planning with Large Language Models](https://mlsanity.com/paper/2307.01848/) (2023)
- [PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks](https://mlsanity.com/paper/2411.00081/) (2024)
- [LLatrieval: LLM-Verified Retrieval for Verifiable Generation](https://mlsanity.com/paper/2311.07838/) (2023)
- [VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robots](https://mlsanity.com/paper/2507.05118/) (2025)
- [Dialog Acts for Task-Driven Embodied Agents](https://mlsanity.com/paper/2209.12953/) (2022)
- [Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue](https://mlsanity.com/paper/2210.04443/) (2022)
- [Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristic](https://mlsanity.com/paper/2412.09666/) (2024)

## Built on by (most cited first, 4 of 4)

- [Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts](https://mlsanity.com/paper/2510.21557/) (2025)
- [Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement](https://mlsanity.com/paper/2608.14590/) (2026)
- [HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios](https://mlsanity.com/paper/2603.11975/) (2026)
- [GNNVerifier: Graph-based Verifier for LLM Task Planning](https://mlsanity.com/paper/2603.14730/) (2026)

## Abstract (arXiv)

Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative verification framework in which a Judge LLM critiques action sequences and a Planner LLM applies the revisions, yielding progressively cleaner and more spatially coherent trajectories. Unlike rule-based approaches, our method relies on natural language prompting, enabling broad generalization across error types including irrelevant actions, contradictions, and missing steps. On a set of manually annotated actions from the TEACh embodied AI dataset, our framework achieves up to 90% recall and 100% precision across four state-of-the-art LLMs (GPT o4-mini, DeepSeek-R1, Gemini 2.5, LLaMA 4 Scout). The refinement loop converges quickly, with 96.5% of sequences requiring at most three iterations, while improving both temporal efficiency and spatial action organization. Crucially, the method preserves human error-recovery patterns rather than collapsing them, supporting future work on robust corrective behavior. By establishing plan verification as a reliable LLM capability for spatial planning and action refinement, we provide a scalable path to higher-quality training data for imitation learning in embodied AI.