AI Paper Atlas

Research map / Large language models / Agents, code and math

MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair

Ali Reza Ibrahimzada, Brandon Paulsen, Reyhaneh Jabbarvand, Joey Dodds, Daniel Kroening

ICML 2026 · Large language models › Agents, code and math · approach: Execution-based code verification · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add semantic analyzer and test generator agents on top of a standalone coding agent (ablation)MatchFixAgent · 1091 non-dispute translation pairsvalidation accuracy: accuracy drops by 42.3% without themImproved
add the six semantic analyses to test generator and verdict agents (ablation)MatchFixAgent · 1091 non-dispute translation pairsvalidation accuracy: 60.31% -> 100%Improved
add semantic analyses to reduce agent cost (ablation)MatchFixAgent · 1091 non-dispute translation pairsturns, tokens, time: turns 66.3K -> 63.7K; input tokens 136K -> 128K; duration 61.28h -> 56.71hImproved
standalone agent versus multi-agent on disputed cases where MatchFixAgent is correct (ablation)standalone Claude Code agent · 145 manually resolved disputesaccuracy: 47.7% vs 56.1% on prior-tool-correct casesImproved
use MatchFixAgent repair instead of reprompting-based repairtranslation repair · 265 buggy translationsrepaired (%): 18.5% -> 50.6%Improved
add generated tests from MatchFixAgentproject code coverage · subject projectscoverage (%): 89.6% -> 98.1%Improved
swap Claude 3.7 Sonnet and Claude Code for o4-mini and Codex (ablation)MatchFixAgent · 96 sampled instancesagreement with existing validation: 73% agreementNo clear effect
short-circuit control flow analyzer at CFG similarity threshold 0.7MatchFixAgent control flow analyzer · all experimentsLLM invocations skipped: approximately 25% of LLM invocations skippedImproved
short-circuit data flow analyzer at similarity threshold 0.7MatchFixAgent data flow analyzer · all experimentsLLM invocations skipped: approximately 35% of LLM invocations skippedImproved
use PL-agnostic Tree-Sitter design instead of per-pair toolingMatchFixAgent · development costlines of code: 1650 vs 10859 / 19052 / 3843Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy