Loading the edition…
· Past edition · 11 stories
Retrospective edition reconstructed from later captures. Paper versions may include later updates; coverage labels describe the evidence used.
Research & academia
Multi-harness reinforcement learning brings modest gains, but the choice of execution harness is associated with larger solve-rate differences.
Why it matters: When evaluating coding-agent training, separate gains under training harnesses from robustness across interfaces: in this study, harness choice mattered more than either the estimated RL gains or the normalization rule.
Research & academia
Open each story in the reader. Summaries are shown when available; some sources provide an abstract only. With an account you can keep your own notes.
A diffusion-augmented approach aims to accelerate autoregressive generation.
Why it matters: Faster decoding needs a sound comparison against the same underlying output distribution.
Research & academia
A code-editing study measures changes beyond the requested repair.
Why it matters: Correctness and preservation of unrelated code are separate properties of an edit.