adding-repository-wide-line-level-graph-definitions-references-queried-ego-graph-around CLM-0261observationsingle paperReviewed 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.
Capability: Finding what matters in a large codebase
Observed on
SWE-bench Lite with GPT-4o and similar, 2024; frameworks Agentless, RAG, SWE-agent and AutoCodeRover; ego-graph depth k=1 or 2..
Sources
- Validated by: Resolve rate and cost on SWE-bench Lite for each of four frameworks with and without the plug-in; ablation over ego-graph depth; secondary test on CrossCodeEval code completion.. Gains are consistent across four frameworks, which is the strength of the paper, but end-to-end resolve rate is the only metric, so the improvement is attributed to navigation by argument rather than by a localization measurement.
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
- For a domain-specific language essentially absent from pretraining corpora (FORM symbolic algebra), QLoRA fine-tuning an 8B model on a few thousand examples validated by executing them through the language's own interpreter beats frontier open-weight models of up to 756B parameters given syntax documentation in context, on execution rate and strict output match for the larger benchmarks, while general reasoning scores drop under 3 points.Generating and editing working code · reviewed by AI
- 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 repository-level issue-fixing tasks (SWE-bench Lite/Verified/Pro), spending effort upstream — expanding the issue text into a structured requirement spec from retrieved repo context, then testing and refining that spec via generated code and tests — raises resolve rate over agents that consume the raw issue description, and raises the share of patches that even apply cleanly by a larger margin than it raises correctness.Generating and editing working code · reviewed by AI
- On 2,154 expert-curated multiple-choice questions across eight architectural categories, 11 current models all score above 90% zero-shot (best about 94%), with quality-attribute and pattern questions near ceiling, but accuracy varies by category and drops for smaller models on the harder tiers (to about 85-87%), so declarative architectural knowledge is largely present while the benchmark cannot show whether it is applied in design.Making design decisions that hold up as a system grows · 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: Frameworks or languages where the graph adds cost without raising resolve rate, or a comparison showing a language-server or plain symbol search gives the same gain.