Fix SWE-Milestone paper listing (was incorrectly titled EvoClaw) - #58
Merged
Merged
Conversation
arXiv 2603.13428 is SWE-Milestone, not EvoClaw. Replace the 404 FSoft-AI4Code/EvoClaw code link with the official benchmark repo published in the paper. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Correct the arXiv 2603.13428 listing. The live paper title is SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution, not EvoClaw. The previous GitHub URL
FSoft-AI4Code/EvoClawis a confirmed 404; this PR replaces it with the official benchmark repo published in the paper HTML.Papers live in README (not
data/projects.json). Only these two rows changed.Before
[EvoClaw: Evaluating AI Agents on Continuous Software Evolution](https://arxiv.org/abs/2603.13428) (arXiv'26) - Benchmark revealing performance drops from >80% to at most 38% in continuous evolution settings.[EvoClaw](https://github.com/FSoft-AI4Code/EvoClaw) (arXiv'26) - Evaluating agents on continuous software evolution.After
[SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution](https://arxiv.org/abs/2603.13428) (ICML'26) - Benchmark revealing performance drops from >80% on isolated tasks to 38.03% in continuous evolution settings.[SWE-Milestone](https://github.com/DeepCommit-ai/SWE-Milestone) (ICML'26) - Evaluating agents on continuous software evolution.Evidence (checked live, not inferred)
ICML 2026. Abstract: scores drop from>80%on isolated tasks to38.03%in continuous settings. No EvoClaw name and no code URL on the abs page.github.com/DeepCommit-ai/SWE-Milestone, pipelinegithub.com/DeepCommit-ai/DeepCommit.gh api repos/FSoft-AI4Code/EvoClaw→ HTTP 404.gh api repos/DeepCommit-ai/SWE-Milestone→ public MIT repo, description[ICML 2026] Evaluating AI Agents on Continuous Software Evolution, homepagehttps://swe-milestone.com.EvoClaw-Bench/EvoClaw301-redirects to that same repo (rename), and was not substituted as the listed URL.slhleosun/EvoClaw,clawinfra/evoclaw, etc.) were not used.Checklist
data/projects.jsonwith correct schema — N/A: paper/benchmark rows are hand-maintained in READMEnode scripts/generate-readme.jswas run and README.md is up to date (idempotent; AUTOGEN sections unchanged)node scripts/validate.jspasses (Validated 119 projects across 10 categories/Validation passed.)git diff --checkis cleannode scripts/check-links.jsnot applicable (script only checksdata/projects.json, which this PR does not change)Category
🤖 Generated with Claude Code