Year: 2026
Type: conference-paper
Abstract: Code localization is a primary bottleneck in automated software development.While parallel tool execution can accelerate discovery, existing agents suffer from a 34.9% redundant tool invocation rate, negating the benefits of parallelism.We introduce FuseSearch, which reframes parallel code localization as a quality-efficiency co-optimization problem.By defining tool efficiency-the ratio of novel information gain to total invocations-we employ a two-stage SFT and RL pipeline to train models in adaptive parallel strategies.Unlike fixed-breadth methods, FuseSearch dynamically adjusts search breadth based on task context, transitioning from exploration to refinement.On SWE-bench Verified, FuseSearch-4B matches SOTA performance (84.7% filelevel and 56.4% function-level F 1 scores) while being 93.6% faster, using 67.7% fewer turns and 68.9% fewer tokens.Our findings demonstrate that efficiency-aware training inherently boosts quality by eliminating noisy, redundant signals, enabling high-performance, low-cost localization agents.Code: https://github. com/sxthunder/FuseSearch.
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166812415