Article · Original
The article text is unavailable in this language; an existing version is shown.
– https://t.co/quiAZ2O9Ac
Title: "AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems"
Researchers introduce AgentBug-Smith to turn agent bug reports into runnable testsMachine translation
Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.
AgentBug-Smith turns real GitHub bug reports into runnable tests, forming a growing benchmark of 200 bugs. The source says the best of three coding agents fixed just 9% of those bugs. A short guide drawn from past fixes raised one agent’s correct fixes from 1 to 6 on 79 unseen bugs.
Self-improving AI agents will need to fix their own code.
And this paper from top US+China labs, shows coding agents miss most such bugs but improve with lessons from past fixes.
that real bugs in agent harnesses, can be automatically turned into a growing set of runnable tests.
An agent's own code is everything around the model: tool calls, memory, and prompts. Its bugs depend on live model calls, which makes them hard to recreate and test.
So the researchers built AgentBug-Smith, which turns real GitHub bug reports into runnable tests. The result is a 200-bug benchmark that keeps growing.
The best of 3 coding agents fixed just 9% of those bugs, versus about 40% reported on regular software bugs. A short guide of lessons from past fixes lifted an agent from 1 to 6 correct fixes on 79 unseen bugs.
Before trusting a coding agent with your agent's code, try it on bugs you've already fixed.
View replied-to post on X