Learning Adaptive Parallel Execution for Efficient Code Localization
Code localization constitutes a key bottleneck in automated software development pipelines. While concurrent tool execution can enhance discovery speed, current agents demonstrate a 34.9% redundant invocation rate, which negates parallelism benefits. We propose FuseSearch, reformulating parallel code localization as a joint quality-efficiency optimization} task. Through defining tool efficiency -- the ratio of unique information gain to invocation count -- we utilize a two-phase SFT and RL training approach for learning adaptive parallel strategies. Different from fixed-breadth approaches, FuseSearch dynamically modulates search breadth according to task context, evolving from exploration phases to refinement stages. Evaluated on SWE-bench Verified, FuseSearch-4B achieves SOTA-level performance (84.7% file-level and 56.4% function-level F1 scores) with 93.6% speedup, utilizing 67.7% fewer turns and 68.9% fewer tokens. Results indicate that efficiency-aware training naturally improves quality through eliminating noisy redundant signals, enabling high-performance cost-effective localization agents.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
AHASD: Asynchronous Heterogeneous Architecture for LLM Adaptive Drafting Speculative Decoding on Mobile Devices
Speculative decoding enhances the inference efficiency of large language models (LLMs) by generating drafts using a small draft language model (DLM) and verifying them in batches with a large target language model (TLM).…
Cerberus: Efficient Inference with Adaptive Parallel Decoding and Sequential Knowledge Enhancement
Large language models (LLMs) often face a bottleneck in inference speed due to their reliance on auto-regressive decoding. Recently, parallel decoding has shown significant promise in enhancing inference efficiency. Howe…
DenoiseFlow: Uncertainty-Aware Denoising for Reliable LLM Agentic Workflows
Autonomous agents are increasingly entrusted with complex, long-horizon tasks, ranging from mathematical reasoning to software generation. While agentic workflows facilitate these tasks by decomposing them into multi-ste…
Mathematical ReasoningCode GenerationMedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution
Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medical reasoning tasks. However, their sequential autoregressive decoding forces inherently parallel clinical reaso…
Learning Latency-Aware Orchestration for Parallel Multi-Agent Systems
Multi-agent systems (MAS) enable complex reasoning by coordinating multiple agents, but often incur high inference latency due to multi-step execution and repeated model invocations, severely limiting their scalability a…