2026-09-10 · 1 source · ran in №10

OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows

Sources

arXiv cs.AI OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows 2026-09-10

Topics

Related coverage

Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite 2026-09-14

How Ora benchmarks every major AI agent on Vercel 2026-08-22

Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation 2026-09-23

Claude Cowork and chat are now one Claude 2026-09-16

On the Navier–Stokes Millennium Prize Problem 2026-09-08

GPT‑6 Astra 2026-09-04