REVIEW 10 cited by
LocAgent: Graph-Guided LLM Agents for Code Localization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Code localization--identifying precisely where in a codebase changes need to be made--is a fundamental yet challenging task in software maintenance. Existing approaches struggle to efficiently navigate complex codebases when identifying relevant code sections. The challenge lies in bridging natural language problem descriptions with the appropriate code elements, often requiring reasoning across hierarchical structures and multiple dependencies. We introduce LocAgent, a framework that addresses code localization through graph-based representation. By parsing codebases into directed heterogeneous graphs, LocAgent creates a lightweight representation that captures code structures (files, classes, functions) and their dependencies (imports, invocations, inheritance), enabling LLM agents to effectively search and locate relevant entities through powerful multi-hop reasoning. Experimental results on real-world benchmarks demonstrate that our approach significantly enhances accuracy in code localization. Notably, our method with the fine-tuned Qwen-2.5-Coder-Instruct-32B model achieves comparable results to SOTA proprietary models at greatly reduced cost (approximately 86% reduction), reaching up to 92.7% accuracy on file-level localization while improving downstream GitHub issue resolution success rates by 12% for multiple attempts (Pass@10). Our code is available at https://github.com/gersteinlab/LocAgent.
Forward citations
Cited by 10 Pith papers
-
LLM Agents Can See Code Repositories
Visual graphs of repository structure added to text inputs for multimodal LLM agents reduce token consumption by up to 26% while maintaining or improving issue-resolution accuracy.
-
Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects
Injecting a few vectors near the embedding-space centroid can make them appear in top-k results for up to 94.4% of queries via centrality-driven hubness.
-
Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First
A 7B searcher's sandbox-verified handoff lets a cheap coding model match a frontier model's solve rate on SWE-bench Pro at roughly one fifth the cost, while the router that picks the fixer contributes nothing on this ...
-
Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents
A 427-sample workflow-grounded benchmark finds complementary strengths across lexical, structural, and embedding retrieval for coding-agent context acquisition, with large residual miss rates and a selective-abstentio...
-
What Context Does a Coding Agent Actually Need to Act?
At oracle localization on SWE-bench Verified, the edited source itself carries the act signal; structured surrounding context resolves no more issues than dropping it, and compressed context matches whole files at one...
-
SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
A competitive multi-agent debate over graph-derived fault propagation chains lifts automated issue resolution on SWE-bench Verified to 41.4% pass@1.
-
Gotta catch 'em all! Towards File Localisation from Issues at Large
Across seven projects and all issue types, BM25 beats TF-IDF, LSI, and the bug-specific rVSM, which performs worst.
-
Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation
An empirical study of 1,023 CoT-code pairs shows that 76.4% of LLM-generated CoTs are low quality and that CoT correctness does not guarantee code correctness.
-
Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults
On a new 250-bug Linux kernel benchmark, state-of-the-art LLM agents localize at most 41.6 percent of buggy files at rank 1; the proposed LinuxFL+ framework improves this to 52.4 percent.
-
LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
A survey that classifies LLM-based agent reasoning frameworks into single-agent, tool-based, and multi-agent types and reviews their use across scientific, medical, software, and social domains.
Discussion (0). Continue with ORCID to comment.