paper-with-me

Papers

FastCode: Fast and Cost-Efficient Code Understanding and Reasoning

2026-03-01 · Zhonghang Li, Zongwei Li, Yuxuan Chen, Han Shi, Jiawei Li, Jierun Chen, Haoli Bai, Chao Huang arxiv

Repository-scale code reasoning is a cornerstone of modern AI-assisted software engineering, enabling Large Language Models (LLMs) to handle complex workflows from program comprehension to complex debugging. However, balancing accuracy with context cost remains a significant bottleneck, as existing agentic approaches often waste computational resources through inefficient, iterative full-text exploration. To address this, we introduce FastCode, a framework that decouples repository exploration from content consumption. FastCode utilizes a structural scouting mechanism to navigate a lightweight semantic-structural map of the codebase, allowing the system to trace dependencies and pinpoint relevant targets without the overhead of full-text ingestion. By leveraging structure-aware navigation tools regulated by a cost-aware policy, the framework constructs high-value contexts in a single, optimized step. Extensive evaluations on the SWE-QA, LongCodeQA, LOC-BENCH, and GitTaskBench benchmarks demonstrate that FastCode consistently outperforms state-of-the-art baselines in reasoning accuracy while significantly reducing token consumption, validating the efficiency of scouting-first strategies for large-scale code reasoning. Source code is available at https://github.com/HKUDS/FastCode.

📄 PDF Abstract BibTeX arXiv:2603.01012

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Long Movie Clip Classification with State-Space Video Models

2022-04-04 · Md Mohaiminul Islam, Gedas Bertasius

Most modern video recognition models are designed to operate on short video clips (e.g., 5-10s in length). Thus, it is challenging to apply such models to long movie understanding tasks, which typically require sophistic…

ClassificationDecoderGPUVideo Classification+2

Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models

2025-06-11 · Zongjie Li, Shuai Wang

This position paper proposes a fundamental shift in designing code generation models: treating reasoning depth as a controllable resource. Rather than being an incidental byproduct of prompting, we argue that the trade-o…

BenchmarkingCode Generation

Distilled Dual-Encoder Model for Vision-Language Understanding

2021-12-16 · Zekun Wang, Wenhui Wang, Haichao Zhu, Ming Liu 외

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster i…

Image to textmodelQuestion AnsweringVisual Entailment+3

Fast Thinking for Large Language Models

2025-09-28 · Haoyu Zheng, Zhuonan Wang, Yuqian Yuan, Tianwei Lin 외 arxiv

Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tuning or reinforcement learning. While Chain…

Reinforcement Learning

Semantic Intelligence: Integrating GPT-4 with A Planning in Low-Cost Robotics

2025-05-03 · Jesse Barkley, Abraham George, Amir Barati Farimani

Classical robot navigation often relies on hardcoded state machines and purely geometric path planners, limiting a robot's ability to interpret high-level semantic instructions. In this paper, we first assess GPT-4's abi…

Large Language ModelRobot Navigation