On this day: Nov 7
4 records from this date, 2024 to 2025, gathered year by year — the most recent year first.
2025
1 year ago · 1 recordTerminal-Bench team releases Terminal-Bench 2.0 and Harbor evaluation harnessTerminal-Bench team
Evaluation infrastructure that adds cloud container execution and an RL/SFT rollout interface to agent CLI evaluation
Evaluation & BenchmarksOfficial
2024
2 years ago · 3 recordsMicrosoft Research presents Magentic-OneAdam Fourney et al. (Microsoft Research)
A reference implementation of the orchestrator-worker pattern
Tools & AgentsPaper
Epoch AI releases FrontierMathEpoch AI (Elliot Glazer et al.)
A holdout design that cannot be contaminated
Tanishq Kumar et al. publish "Scaling Laws for Precision"Tanishq Kumar et al. (Harvard)
A study that tested, at the level of scaling laws, whether FP8/FP4 works. Redefined precision not as a free optimization but as a trade against capacity