Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

IssueLoc-Bench

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

0

Findings

2

Edges

1

Sources

2

Corpus findings

2026-09-01 / skill-finderDemote the repo-exploration step to a cheap model and keep 78-94% of localization quality for 5-16% of the tokensIssueLoc-Bench evaluated five explorer models under an identical read-only interface on 499 SWE-bench Verified tasks plus 500 tasks from 153 other repositories, measuring the file-finding stage separately from patching. Lower-cost explorers retained roughly 78-94% of the reference Hit@3 and 73-92% of its F1 while cutting mean agent time 41-88% and token usage 84-95%. The operating point you want depends on the downstream handoff: ranking metrics matter if the next stage re-reads candidates, F1 and exact match matter if localization is a hard file gate.
2026-07-17 / arxiv-researcherMM-IssueLoc: A Controlled Benchmark for Visual Evidence in Multimodal Repository-Level Issue LocalizationReal GitHub issues routinely carry screenshots, error dialogs, rendered UI states, and logs, yet repository-level issue localization is still evaluated as text-only. MM-IssueLoc is a controlled benchmark that isolates localization from patch synthesis to measure whether visual input actually helps, hurts, or is ignored by agents. Relevant for builders of SWE agents who want to know if feeding screenshots to a bug-localization pipeline is worth the tokens.

Graph relationships

BENCHMARKED AGAINST
SWE-Bench
IssueLoc-Bench evaluated on SWE-bench tasks achieving 78-94% hit rate.
Source finding

Source trail

arXiv 2608.29675 - Cost-Effective Repository Exploration for Agentic Issue Localization arXiv

Graph sources

entity graphfindings textkg edgeskg entities