paper-with-me

홈 › Papers

Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback

2024-06-04 · Wang Zhu, Ishika Singh, Robin Jia, Jesse Thomason

Symbolic planners can discover a sequence of actions from initial to goal states given expert-defined, domain-specific logical action semantics. Large Language Models (LLMs) can directly generate such sequences, but limitations in reasoning and state-tracking often result in plans that are insufficient or unexecutable. We propose Predicting Semantics of Actions with Language Models (PSALM), which automatically learns action semantics by leveraging the strengths of both symbolic planners and LLMs. PSALM repeatedly proposes and executes plans, using the LLM to partially generate plans and to infer domain-specific action semantics based on execution outcomes. PSALM maintains a belief over possible action semantics that is iteratively updated until a goal state is reached. Experiments on 7 environments show that when learning just from one goal, PSALM boosts plan success rate from 36.4% (on Claude-3.5) to 100%, and explores the environment more efficiently than prior work to infer ground truth domain action semantics.

📄 PDF Abstract BibTeX arXiv:2406.02791

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models

2025-06-25 · Wang Bill Zhu, Miaosen Chai, Ishika Singh, Robin Jia 외

We propose PSALM-V, the first autonomous neuro-symbolic learning system able to induce symbolic action semantics (i.e., pre- and post-conditions) in visual environments through interaction. PSALM-V bootstraps reliable sy…

Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs

2026-06-22 · Xiangbo Gao, Xiukun Huang, Boyu Lu, Junge Zhang 외 arxiv

Driving VLA models incorporating Chain-of-Thought (CoT) reasoning are attractive because they leverage pretrained VLM representations and expose intermediate decisions in natural language, yet current rationales often la…

NSP: A Neuro-Symbolic Natural Language Navigational Planner

2024-09-10 · William English, Dominic Simon, Sumit Jha, Rickard Ewetz

Path planners that can interpret free-form natural language instructions hold promise to automate a wide range of robotics applications. These planners simplify user interactions and enable intuitive control over complex…

valid

Learning First-Order Symbolic Representations for Planning from the Structure of the State Space

2019-09-12 · Blai Bonet, Hector Geffner

One of the main obstacles for developing flexible AI systems is the split between data-based learners and model-based solvers. Solvers such as classical planners are very flexible and can deal with a variety of problem i…

Representation Learning

Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation

2025-03-03 · Yongchao Chen, Yilun Hao, Yang Zhang, Chuchu Fan

Recent works have shown great potentials of Large Language Models (LLMs) in robot task and motion planning (TAMP). Current LLM approaches generate text- or code-based reasoning chains with sub-goals and action plans. How…

Code GenerationCommon Sense ReasoningMotion PlanningTask and Motion Planning