Agent Plasticity: capability is not the same as learning efficiency
anirudhg9119 · x · 2026-10-09
Core claim post: across Chess, Go, and Hex, one model reaches the highest fitted performance while another is the most efficient learner. Agent Plasticity is defined as held-out performance gain per unit of learning cost, measured up to saturation—capability ≠ learning efficiency. Full details in the thread's main arXiv entry.
More from Research
- RWTH Aachen's ARROW unifies 3D reconstruction and point tracking from any RGB inputs, sets new SOTA — kwangmoo_yi · 2026-10-09
- HAIPS 2026 workshop lands at COLM tomorrow with top AI privacy researchers — tianshi_li · 2026-10-09
- Tighter Bayes error bounds via generalized Bhattacharyya and Chernoff means — FrnkNlsn · 2026-10-09
- PAMI: part-anchored motion lifts contact recall 14.5% in text-to-HOI generation — _akhaliq · 2026-10-09
- Study finds LLM novelty judges are unstable: scores swing wildly with evaluation design choices — _akhaliq · 2026-10-09
- Google's AMIE lands in The Lancet: 90% match with doctors' final diagnoses in real clinics — sundarpichai · 2026-10-09