Agent Plasticity: top-performing agents aren't the most efficient learners
RulinShao · x · 2026-10-09
Harman Singh et al. study how well agents learn from experience: they amortize experience into reusable artifacts and introduce "Agent Plasticity" to measure how efficiently agents improve on held-out environments. Key finding: the top performer is not necessarily the most efficient learner — static capability and experiential learning are distinct axes.
More from coding & agent
- LlamaIndex explains why Markdown is its default parsing output (HTML for merged headers) — llama_index · 2026-10-09
- 3 engineers, $1M and 1.5T tokens: Compound V2 rebuilds Office suite for AI agents — peterjliu · 2026-10-09
- While waiting for his AI coding limit to reset, a dev went back to hand-writing Go — haydendevs · 2026-10-09
- Orchestrator rebuilds its agent terminal: 13ms typing lag, 5x faster output — julianweisser · 2026-10-09
- Dev releases free 'AI Software Factory' ebook on agentic SDLC — Pavan_Belagatti · 2026-10-09
- Infisical Launches Agent Vault to Give AI Coding Agents API Access Without Real Credentials — ycombinator · 2026-10-09