FaSTA*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing

ICLR 2026 Conference Submission14607 Authors

Keywords: Multi-turn Image Editing, Neurosymbolic Agent, Fast-Slow Planning, Subroutine Mining, Toolpath Optimization, Cost-Efficient

TL;DR: FaSTA*: neurosymbolic agent for multi-turn image editing. Learns reusable LLM subroutines for its "fast plan"; uses "slow" A* search if needed. Cuts computational cost, keeps high success rates.

Abstract: We develop a cost-efficient neurosymbolic agent to address challenging multi-turn image editing tasks such as "Detect the bench in the image while recoloring it to pink. Also, remove the cat for a clearer view and recolor the wall to yellow." It combines the fast, high-level subtask planning by large language models (LLMs) with the slow, accurate, tool-use, and local A* search per subtask to find a cost-efficient toolpath---a sequence of calls to AI tools. To save the cost of A* on similar subtasks, we perform inductive reasoning on previously successful toolpaths via LLMs to continuously extract/refine frequently used subroutines and reuse them as new tools for future tasks in an adaptive fast-slow planning, where the higher-level subroutines are explored first, and only when they fail, the low-level A* search is activated. The reusable symbolic subroutines considerably save exploration cost on the same types of subtasks applied to similar images, yielding a human-like fast-slow toolpath agent ``FaSTA*'': fast subtask planning followed by rule-based subroutine selection per subtask is attempted by LLMs at first, which is expected to cover most tasks, while slow A* search is only triggered for novel and challenging subtasks. By comparing with recent image editing approaches, we demonstrate FaSTA* is significantly more computationally efficient while remaining competitive with the state-of-the-art baseline in terms of success rate.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 14607