Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub — mentioned by knes

Wed, 18 Mar 2026 05:10:00 GMT

Agreed.this paper studied 33k+ agent-authored PRs on GitHub (https://arxiv.org/pdf/2601.15195) #1 rejection reason: missing context. 80% needed human fixes. Agents can write code fine. They just don't know what "done" looks like in your codebase. Count successful merges into repos with real history instead of LOC and the hard part is specification, not execution. Wrote about this topic @ https://www.augmentcode.com/blog/the-end-of-linear-work

Paper and discussion history. A mention is not an endorsement.

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub — HN submission

Thu, 29 Jan 2026 11:09:24 GMT

Where Do AI Coding Agents Fail?

2 points; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub · HackerPapers discussions

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub — mentioned by knes

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub — HN submission