Tag
Meta paper evaluates frontier agents on how well they learn from experience across chess, Go, Hex and NetHack with frozen weights, defining plasticity as held-out gain per dollar. Claude Fable 5 showed the largest absolute gains while GPT-5.6 Sol was far more cost-efficient, showing the best performer isn't the most efficient learner.
Learn2Play Bench is a benchmark of novel, counterintuitive text-based games designed to evaluate how well LLM agents learn from interaction experience rather than relying on pretrained knowledge, revealing findings on experience retention, a human-agent performance gap, and the importance of agent harness design.
An API for AI that learns and adapts from experiences, enabling LLMs to form and revise preferences over time, with early access offered for design partners.
JERP introduces a method for LLM agents to jointly learn interpretable natural-language rules and update policy parameters from the same interaction trajectories, improving performance on AlfWorld and WebShop while maintaining inspectability.
This paper proposes the EDV framework, which uses multiple heterogeneous agents in execute-distill-verify stages to build reliable experiences for LLM agents, preventing self-confirmatory errors and improving performance on long-horizon benchmarks.
ExpGraph is a model-agnostic framework that enables LLM agents to reuse past experiences via a self-evolving graph of skills and failures, improving task performance by 12–21% without retraining the executor.