TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discovery

2026-08-23

AI Summary

针对多目标材料发现中局部优化难的问题，提出TRACE框架，通过记录和评估每次编辑的效果来指导后续搜索，提高发现效率。

Abstract

Multi-objective materials discovery with LLM agents is often limited not only by how many candidates can be proposed, but by how effectively each costly property evaluation informs the next search step. Existing agents mainly store evaluated candidates and their scores, so they know which materials succeeded but not which executable edits caused useful property changes. This makes local refinement difficult when objectives compete and an edit that improves one property may damage another. We propose TRACE, a transition-aware residual control framework that treats evaluated edits as the basic unit of feedback. TRACE records each local refinement as a parent-edit-child transition with observed property deltas, aggregates transition evidence to estimate reusable edit effects, and ranks future edits by their predicted ability to reduce the current candidate's remaining constraint violations while avoiding damage to already satisfied objectives. In a controlled same-backbone comparison, TRACE improves over LLEMA, the state-of-the-art LLM-agent baseline, raising macro-average hit rate from 18.13\% to 25.96\%.

Problem

• Multi-objective materials discovery
• LLM agents
• property evaluation
• local refinement
• transition-aware

Innovation

• Transition-Aware
• Residual Control
• Local Refinement
• Property Evaluation
• Multi-Objective Materials Discovery