process · priority-scheduled-search-distance-aware-context-pruning TEC-0057 · proposed

Priority-scheduled search with distance-aware context prunin

Keep a scored queue of code entities to inspect, let the model decompose each search into smaller lookups it scores for relevance, and drop context whose graph distance from already-relevant anchors is large, so the agent spends its budget

Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.

Keep a scored queue of code entities to inspect, let the model decompose each search into smaller lookups it scores for relevance, and drop context whose graph distance from already-relevant anchors is large, so the agent spends its budget Filed by the drafting stage from OrcaLoca: An LLM Agent Framework for Software Issue Localization (2502.00350) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Function, file and class match rates on SWE-bench Lite against prior open-source localizers, with ablations removing scheduling, decomposition and pruning; downstream resolved-rate change when its output replaces the baseline's localization.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Finding what matters in a large codebase

Does it work?

nothing measured0 supporting · 0 contesting sources

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.

No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.

Code

No repository linked yet. Contribute one.

Sources

Either way, bring evidence: a link, or what you saw.

Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.