Agent-CoEvo: Code and Tests Should Evolve Together — Multi-Agent Framework Outperforms on SWE-bench

Available in: 中文
2026-04-07T23:56:51.530Z·1 min read
A new multi-agent framework called Agent-CoEvo demonstrates that software repair should not optimize code under fixed tests, but instead coevolve both code and tests simultaneously — achieving stat...

A new multi-agent framework called Agent-CoEvo demonstrates that software repair should not optimize code under fixed tests, but instead coevolve both code and tests simultaneously — achieving state-of-the-art results on SWE-bench Lite and SWT-bench Lite.

The Problem With Current AI Code Repair

Most LLM-based repair systems use a linear pipeline:

Bug Report → Generate Fix → Run Tests → Pass/Fail

Tests are treated as immutable correctness oracles. But real software engineers don't work this way — they often discover that tests themselves contain bugs, missing assumptions, or misinterpreted failure conditions.

The Insight

"Repository-level issue resolution is fundamentally not optimization under fixed tests, but search over evolving behavioral constraints."

When fixing code, the behavioral constraints (tests) should evolve alongside the fix.

Agent-CoEvo Framework

A coevolutionary multi-agent system where:

Results

BenchmarkMetricAgent-CoEvo
SWE-bench LiteRepair successSOTA
SWT-bench LiteRepair successSOTA
Test qualityReproductionImproved

Why This Matters

↗ Original source · 2026-04-07T00:00:00.000Z
← Previous: AI Agents Under EU Law: First Systematic Regulatory Mapping Reveals Critical Compliance Gaps for Autonomous SystemsNext: Quantum-Inspired Ising Machine Solves Problems 4x Larger Than Simulated Annealing — FPGA Implementation 6x Faster →
Comments0