Lune

ICLR2026Top-tier venue

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

Advait Gupta, Rishie Raj, Dang Nguyen, Tianyi Zhou

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 stateof-the-art baseline in terms of success rate. Our code and data can be accessed here.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Adding Conditional Control to Text-to-Image Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Adding Conditional Control to Text-to-Image Diffusion Models cites Learning Transferable Visual Models From Natural Language Supervision
  • Adding Conditional Control to Text-to-Image Diffusion Models cites Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Learning Transferable Visual Models From Natural Language Supervision
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on20

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  3. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  4. Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
  5. Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations

Related papers

  1. Visual Programming: Compositional visual reasoning without trainingTanmay Gupta, Aniruddha KembhaviCVPR 2023
  2. ToolChain*: Efficient Action Space Navigation in Large Language Models with A* SearchYuchen Zhuang, Xiang Chen, Tong Yu, Saayan Mitra et al.ICLR 2024 · 119 citations
  3. Retro-R1: LLM-based Agentic RetrosynthesisWei Liu, Jiangtao Feng, Hongli Yu, Yuxuan Song et al.NeurIPS 2025 · 8 citations
  4. MAXS: Meta-Adaptive Exploration with LLM AgentsJian Zhang, Zhiyuan Wang, Zhangqi Wang, Yu He et al.ACL Findings 2026
  5. ATLAS: Agent Tuning via Learning Critical StepsZhixun Chen, Ming Li, Yuxuan Huang, Yali Du et al.ACL Findings 2025 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines