A 27B agent just beat Claude Opus 4.8 and GPT-5.5 on held-out research replication. Replica turns paper replication into a scalable RL task …

A 27B agent just beat Claude Opus 4.8 and GPT-5.5 on held-out research replication. Replica turns paper replication into a scalable RL task space. Replicating a paper forces the same hypothesis-driven exploration as open research, and it surfaces details the original authors left underspecified. The reward signal comes from an auto-generated rubric judge that runs low-noise and agrees with human assessment of replication quality. Faraday, the resulting 27B agent, calls coding agents as tools. Rollout analysis shows it takes a more scientifically principled approach rather than gaming the rubric. The authors argue this points toward long-horizon scientific capability trained into weights, without requiring complex harnesses. Paper: https://arxiv.org/abs/2608.13331 Track more trending AI papers in our academy: https://academy.dair.ai/

Claude Opus 4.7 just implemented an AlphaZero-style self-play pipeline from scratch. It did this on consumer hardware in three hours, then b…
NEW paper from Microsoft Every agent benchmark has the same hidden problem: how do you know the agent actually succeeded? Microsoft research…
NEW paper worth reading. GPT-5.4 nano plus a critic-comparator orchestration loop hits 76.4% on SWE-bench Verified, matching standalone Gemi…
// The confidence cliff in self-improving autoresearch // Autoresearch loops are still quite brittle. Here is a nice paper offering some ins…

Source: DAIR.AI (X) | 2026-08-14

Related