paper-with-me

홈 › Papers

Bridging LLM Planning Agents and Formal Methods: A Case Study in Plan Verification

2025-10-03 · Keshav Ramani, Vali Tawosi, Salwa Alamir, Daniel Borrajo arxiv

We introduce a novel framework for evaluating the alignment between natural language plans and their expected behavior by converting them into Kripke structures and Linear Temporal Logic (LTL) using Large Language Models (LLMs) and performing model checking. We systematically evaluate this framework on a simplified version of the PlanBench plan verification dataset and report on metrics like Accuracy, Precision, Recall and F1 scores. Our experiments demonstrate that GPT-5 achieves excellent classification performance (F1 score of 96.3%) while almost always producing syntactically perfect formal representations that can act as guarantees. However, the synthesis of semantically perfect formal models remains an area for future exploration.

📄 PDF Abstract BibTeX arXiv:2510.03469

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multi-Agent Reachability Calibration with Conformal Prediction

2023-04-02 · Anish Muthali, Haotian Shen, Sampada Deglurkar, Michael H. Lim 외

We investigate methods to provide safety assurances for autonomous agents that incorporate predictions of other, uncontrolled agents' behavior into their own trajectory planning. Given a learning-based forecasting model …

Autonomous DrivingConformal PredictionPredictionquantile regression+2

Bridging the Agent-World Gap: Text World Models for LLM-based Agents

2026-06-08 · Yixia Li, Hongru Wang, Peng Lai, Zhiwen Ruan 외 arxiv

Large language model (LLM)-based agents are increasingly used in interactive textual environments, from web navigation and code editing to tool use and long-horizon dialogue. Yet many remain largely reactive, mapping obs…

Can Coding Agents Be General Agents?

2026-04-10 · Maksim Ivanov, Abhijay Rana, Gokul Prabhakaran arxiv

As coding agents have seen rapid capability and adoption gains, users are applying them to general tasks beyond software engineering. In this post, we investigate whether coding agents can successfully generalize to end-…

A Formal Analysis of Required Cooperation in Multi-agent Planning

2014-04-22 · Yu Zhang, Subbarao Kambhampati

Research on multi-agent planning has been popular in recent years. While previous research has been motivated by the understanding that, through cooperation, multi-agent systems can achieve tasks that are unachievable by…

On the Limit of Language Models as Planning Formalizers

2024-12-13 · Cassie Huang, Li Zhang

Large Language Models have been shown to fail to create executable and verifiable plans in grounded environments. An emerging line of work shows success in using LLM as a formalizer to generate a formal representation (e…