EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution

Researchers introduce RECAST, a learned framework that formulates evidence construction as sequential decision process over retrieval and computation operations.

Researchers propose using stated-preference economics validity frameworks to evaluate LLMs when ground truth is unavailable, demonstrating the approach with six models on economic valuation surveys.

Researchers introduce SciExam for ENSO, a benchmark where AI agents build climate models from observations, with six of twelve systems outperforming published models.

Researchers prove that clipped decentralized SGD achieves optimal convergence rates under heavy-tailed noise conditions while maintaining linear speed-up across agents.

Researchers propose a new algorithm called ISM for best arm identification in bandits with adversarial shifting means, proving theoretical guarantees and matching lower bounds.