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

arXiv: https://arxiv.org/abs/2406.02791 · HTML: https://mlsanity.com/paper/2406.02791/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 16 of 16)

- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Large Language Models as Commonsense Knowledge for Large-Scale Task Planning](https://mlsanity.com/paper/2305.14078/) (2023)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [ADaPT: As-Needed Decomposition and Planning with Language Models](https://mlsanity.com/paper/2311.05772/) (2023)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [Learning to Synthesize Programs as Interpretable and Generalizable Policies](https://mlsanity.com/paper/2108.13643/) (2021)
- [SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledge](https://mlsanity.com/paper/2308.12682/) (2023)
- [Deploying and Evaluating LLMs to Program Service Mobile Robots](https://mlsanity.com/paper/2311.11183/) (2023)
- [InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning](https://mlsanity.com/paper/2405.19758/) (2024)
- [PDDLEGO: Iterative Planning in Textual Environments](https://mlsanity.com/paper/2405.19793/) (2024)
- [Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering](https://mlsanity.com/paper/2305.14901/) (2023)
- [Augmenting Knowledge through Statistical, Goal-oriented Human-Robot Dialog](https://mlsanity.com/paper/1907.03390/) (2019)

## Built on by (most cited first, 8 of 8)

- [Neuro-Symbolic Synergy for World Modeling](https://mlsanity.com/paper/2602.10480/) (2026)
- [Unifying Inference-Time Planning Language Generation](https://mlsanity.com/paper/2505.14763/) (2025)
- [PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models](https://mlsanity.com/paper/2506.20097/) (2025)
- [Agent+P: Guiding UI Agents via Symbolic Planning](https://mlsanity.com/paper/2510.06042/) (2025)
- [Constraints-of-Thought: A Framework for Constrained Reasoning in Language-Model-Guided Search](https://mlsanity.com/paper/2510.08992/) (2025)
- [On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL](https://mlsanity.com/paper/2601.14456/) (2026)
- [Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs](https://mlsanity.com/paper/2508.14564/) (2025)
- [Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings](https://mlsanity.com/paper/2601.06505/) (2026)

## Abstract (arXiv)

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.