mlsanityData to 7 Oct 2026

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

arXiv 2406.02791 ↗First posted 4 Jun 2024cs.AI cs.CL cs.ROcited by 8

Not on the map. Why?

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.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

16 of 37 references.

References · 16

  1. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  2. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  3. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  4. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  5. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 308
  6. 2023Large Language Models as Commonsense Knowledge for Large-Scale Task Planningcited by 231
  7. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 204
  8. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
  9. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 161
  10. 2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
  11. 2023SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledgecited by 49
  12. 2023Deploying and Evaluating LLMs to Program Service Mobile Robotscited by 36
4 more
  1. 2024InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planningcited by 31
  2. 2024PDDLEGO: Iterative Planning in Textual Environmentscited by 14
  3. 2023Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answeringcited by 8
  4. 2019Augmenting Knowledge through Statistical, Goal-oriented Human-Robot Dialogcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2026Neuro-Symbolic Synergy for World Modelingcited by 6
  2. 2025Unifying Inference-Time Planning Language Generationcited by 3
  3. 2025PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Modelscited by 1
  4. 2025Agent+P: Guiding UI Agents via Symbolic Planningcited by 1
  5. 2025Constraints-of-Thought: A Framework for Constrained Reasoning in Language-Model-Guided Searchcited by 1
  6. 2026On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RLcited by 1
  7. 2025Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMscited by 0
  8. 2026Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settingscited by 0