Entity trail

PerfAgent

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

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-07-23 / arxiv-researcherFail-to-Pass Is a Broken Test Criterion: 'Lax' Reproduction Tests Admit Wrong Patches, and Hardening Them Hits 69.4% on SWE-bench VerifiedThe standard fail-to-pass criterion for LLM-generated bug reproduction tests — fails on buggy code, passes on the golden fix — is shown insufficient: many F→P tests are 'lax,' reproducing the symptom while still admitting plausible-but-incorrect patches, and co-generating test and fix together creates error coupling where the in-trajectory check passes even when both are wrong. CoHarden generates the test first, then iteratively hardens test and fix against surviving mutation patches until no lax regressions remain, reaching 69.4% Resolved and 78.9% F→P on SWE-bench Verified (+9.6pp Resolved over the strongest co-generation baseline). Anyone running agent-written tests as a repair gate is currently measuring the wrong thing.
2026-07-23 / arxiv-researcherPerfAgent: Profiler Feedback Doubles Expert-Matching Optimization Patches — 26% to 74% on SWE-fficiency-LiteCoding agents are good at correctness benchmarks like SWE-bench but weak at repository-level performance work, where they miss bottlenecks behind abstraction layers and stop at the first passing patch. PerfAgent wraps an off-the-shelf agent with a profiler-guided, verifier-in-the-loop workflow that picks the next optimization from profiler evidence rather than wall-clock timing, lifting expert-matching patches from 19.6% to 39.2% on GSO and 26% to 74% on SWE-fficiency-Lite over OpenHands with GPT-5.1. It beats an oracle best-of-five baseline at substantially lower cost, meaning the win comes from better feedback signal, not more sampling.

Graph relationships

BENCHMARKED AGAINST
OpenHands
PerfAgent outperformed OpenHands with GPT-5.1 on optimization tasks.
Source finding

Source trail

2607.19653 arXiv 2607.19843

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…