without-training-or-prebuilt-index-searching-module-call-graph CLM-0273observationsingle paperReviewed by AI
Without training or a prebuilt index, searching a module call graph built on the fly for breadth at file level and then expanding it into a function call graph for depth reached about 43-44% function-level Top-1 localization on SWE-bench Lite and Verified with open 32B and 72B models, beating prior LLM localizers, and the better locations raised an issue-solving pipeline's resolve rate by roughly 3 to 30 points depending on model.
Capability: Finding what matters in a large codebase
Observed on
SWE-bench Lite and Verified, 2025, Qwen2.5-Coder-32B and Qwen2.5-72B; Top-1 file and function accuracy; downstream via Agentless repair and validation..
Sources
- Validated by: Top-1 file and function localization accuracy on SWE-bench Lite and Verified against Agentless, LocAgent-style and other open localizers using the same open models; resolve rate of Agentless with and without its locations; ablations of each phase.. Open models only, which makes the comparison fair but leaves the ceiling unknown; Top-1 is a strict metric and the reported resolve-rate range is wide because it spans models.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- Giving an agent a parsed code graph (files, classes, functions with import, call and inheritance edges) and tools to search and traverse it lets a fine-tuned 32B open model localize issues about as well as proprietary agents at roughly an eighth of the cost, reaching about 93% file-level accuracy, and better localization carried through to about 12 points more resolved issues at Pass@10 when plugged into a fixed repair pipeline.Finding what matters in a large codebase · reviewed by AI
- Constraining a localization agent with a priority queue over candidate code regions scored for relevance, decomposition of each search action, and pruning of context by distance from the issue's anchors reached a 65% function-level match rate on SWE-bench Lite, the best open-source result at the time, and feeding its locations to an open-source repair pipeline raised the resolved rate by about 6 points.Finding what matters in a large codebase · reviewed by AI
- On SWE-bench Lite, asking the model to name suspicious files from the issue plus a repository tree finds the ground-truth file in about 79% of cases and embedding retrieval over the issue text in about 68%, and taking the union of the two raises file-level localization to about 82% because the two methods miss different files; a fixed three-step narrowing (files, then classes and functions, then edit lines) with no agent loop then supported the best open-source resolve rate at the time (32%).Finding what matters in a large codebase · reviewed by AI
- Adding a repository-wide line-level graph of definitions and references, queried for the ego-graph around names the model is looking at, raised SWE-bench resolve rates for all four frameworks it was plugged into (two agentic, two procedural) by an average of about 33% relative, at a modest cost increase that was larger for the agentic ones; the same plug-in also helped on CrossCodeEval.Finding what matters in a large codebase · reviewed by AI
- Issue localization can be done as retrieval-and-rerank with no agent at all: an embedding model and reranker trained on issue-to-patched-function pairs mined from public GitHub (SweLoc) localize functions on SWE-bench Lite and LocBench at least as accurately at Acc@10 as agents built on Claude 3.5 Sonnet, at a small fraction of the per-issue cost and with one pass instead of seven to ten model rounds.Finding what matters in a large codebase · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: Repositories with dynamic dispatch or cross-language calls where a static call graph misses the relevant edges and free search does better.