Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

SHERLOC: Structured Diagnostic Localization for Code Repair Agents

Hovhannes Tamoyan, Sean Narenthiran, Erik Arakelyan, Mira Mezini, Boris Ginsburg · Jun 23, 2026 · Citations: 0

Automatic Metrics Coding Medicine Multi Agent Tool Use
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Moderate trust

Use this for comparison and orientation, not as your only source.

Best use

Background context only

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Moderate

Derived from extracted protocol signals and abstract evidence.

Abstract

LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated localization frameworks have emerged, yet are still evaluated as file retrieval rather than actionable diagnosis, producing locations without the diagnostic context a repair agent needs. We introduce SHERLOC (Structured Hypothesis-driven Exploration and Reasoning for Localization), a training-free framework pairing a reasoning LLM with compact repository tools and self-recovery, without fine-tuning or multi-agent orchestration. SHERLOC reaches state-of-the-art localization across model scales: 84.33% accuracy@1 on SWE-Bench Lite and 81.27% recall@1 on SWE-Bench Verified; at ~30B parameters, it matches or outperforms other agentic methods. Injecting our locations and diagnostic findings into repair agents yields, on average, +5.95 pp resolve rate on SWE-Bench Verified while cutting localization and total tokens by 36.7% and 23.1%.

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Usefulness score

25/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

Usefulness for eval research

Adjacent candidate

Extraction confidence 55%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing."

Quality Controls

missing

Not reported

No explicit QC controls found.

"LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing."

Benchmarks / Datasets

strong

SWE Bench, SWE Bench Lite, SWE Bench Verified

Useful for quick benchmark comparison.

"SHERLOC reaches state-of-the-art localization across model scales: 84.33% accuracy@1 on SWE-Bench Lite and 81.27% recall@1 on SWE-Bench Verified; at ~30B parameters, it matches or outperforms other agentic methods."

Reported Metrics

strong

Accuracy, Recall, Recall@1

Useful for evaluation criteria comparison.

"SHERLOC reaches state-of-the-art localization across model scales: 84.33% accuracy@1 on SWE-Bench Lite and 81.27% recall@1 on SWE-Bench Verified; at ~30B parameters, it matches or outperforms other agentic methods."

Human Feedback Details

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Not reported
  • Expertise required: Medicine, Coding

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: Tool Use, Multi Agent
  • Quality controls: Not reported
  • Evidence quality: Moderate
  • Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

SWE-benchSWE-bench LiteSWE-bench Verified

Reported Metrics

accuracyrecallrecall@1

Research Brief

Metadata summary

LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing.
  • Dedicated localization frameworks have emerged, yet are still evaluated as file retrieval rather than actionable diagnosis, producing locations without the diagnostic context a repair agent needs.
  • We introduce SHERLOC (Structured Hypothesis-driven Exploration and Reasoning for Localization), a training-free framework pairing a reasoning LLM with compact repository tools and self-recovery, without fine-tuning or multi-agent orchestration.

Researcher Actions

  • Compare this paper against others mentioning SWE-bench.
  • Validate inferred eval signals (Automatic metrics, Tool-use evaluation) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

SWE-bench Accuracy

Research Summary

Contribution Summary

  • We introduce SHERLOC (Structured Hypothesis-driven Exploration and Reasoning for Localization), a training-free framework pairing a reasoning LLM with compact repository tools and self-recovery, without fine-tuning or multi-agent…
  • SHERLOC reaches state-of-the-art localization across model scales: 84.33% accuracy@1 on SWE-Bench Lite and 81.27% recall@1 on SWE-Bench Verified; at ~30B parameters, it matches or outperforms other agentic methods.
  • Injecting our locations and diagnostic findings into repair agents yields, on average, +5.95 pp resolve rate on SWE-Bench Verified while cutting localization and total tokens by 36.7% and 23.1%.

Why It Matters For Eval

  • We introduce SHERLOC (Structured Hypothesis-driven Exploration and Reasoning for Localization), a training-free framework pairing a reasoning LLM with compact repository tools and self-recovery, without fine-tuning or multi-agent…
  • SHERLOC reaches state-of-the-art localization across model scales: 84.33% accuracy@1 on SWE-Bench Lite and 81.27% recall@1 on SWE-Bench Verified; at ~30B parameters, it matches or outperforms other agentic methods.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: SWE-bench, SWE-bench Lite, SWE-bench Verified

  • Pass: Metric reporting is present

    Detected: accuracy, recall, recall@1

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.