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

TL;DR

PSALM-V is an autonomous neuro-symbolic system that uses large language models to induce symbolic action semantics in visual environments, significantly improving planning success rates without expert input.

Contribution

It introduces PSALM-V, the first system to dynamically infer symbolic action semantics in visual environments through interaction and iterative refinement using LLMs.

Findings

Increases plan success rate from 37% to 74% in ALFRED.

Improves step efficiency in 2D game environments.

Successfully induces PDDL semantics for real-world robot tasks.

Abstract

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 symbolic planning without expert action definitions, using LLMs to generate heuristic plans and candidate symbolic semantics. Previous work has explored using large language models to generate action semantics for Planning Domain Definition Language (PDDL)-based symbolic planners. However, these approaches have primarily focused on text-based domains or relied on unrealistic assumptions, such as access to a predefined problem file, full observability, or explicit error messages. By contrast, PSALM-V dynamically infers PDDL problem files and domain action semantics by analyzing execution outcomes and synthesizing possible error explanations. The system iteratively generates and executes plans while maintaining a tree-structured belief over possible action semantics for each action, iteratively refining these beliefs until a goal state is reached. Simulated experiments of task completion in ALFRED demonstrate that PSALM-V increases the plan success rate from 37% (Claude-3.7) to 74% in partially observed setups. Results on two 2D game environments, RTFM and Overcooked-AI, show that PSALM-V improves step efficiency and succeeds in domain induction in multi-agent settings. PSALM-V correctly induces PDDL pre- and post-conditions for real-world robot BlocksWorld tasks, despite low-level manipulation failures from the robot.