SlopCodeBench: Benchmarking How Coding Agents Degrade over Long-Horizon Tasks #1 Post by FiberBundle » Fri, Mar 27, 2026, 10:44 PM UTC SlopCodeBench: Benchmarking How Coding Agents Degrade over Long-Horizon Tasksarxiv.org
Re: SlopCodeBench: Benchmarking How Coding Agents Degrade over Long-Horizon Tasks #2 Post by cestivan » Fri, Mar 27, 2026, 11:17 PM UTC [dead]