Top 10 Eval Papers of 2026: verifiers, agent-as-a-judge, and audit of self-improvement
omarsar0 · x · 2026-11-16
AI researcher omar sar published his pick of the top 10 eval papers of 2026, arguing that while new models and agents claim higher benchmark scores every week, eval quality itself is often overlooked. The list spans durability, quality, robustness and efficiency, plus emerging topics like verifiers, agent-as-a-judge, LLM-as-a-judge, and auditing self-improvement.
More from Research
- WebArena-Pro launches: 300-task multimodal web-agent benchmark across 20 apps — xhluca · 2026-11-16
- U-M's CrowdBark crowdsources dog videos to study canine communication with AI — radamihalcea · 2026-11-16
- Koshien robot team shares control stack: nonlinear-opt trajectories hit ±1.2cm average error — 4310sy · 2026-11-16
- A diffusion model trained on CIFAR-10 re-images black hole M87* — and the ring persists — bravo_abad · 2026-11-16
- SPU benchmark tests whether AI can predict real wet-lab outcomes in 116 tasks — liangchen5518 · 2026-11-16
- Self-improving agent papers this week: agents learn the benchmark, not the task — TheTuringPost · 2026-11-16