Tag
This article summarizes an empirical study on harness design for coding agents, showing that context management prevents overflow failures, rule-based elision before LLM summarization is cost-effective, and planning's role varies with model strength.
This paper explores using large language models and AI agents for autonomous chip design, modeling it as an AI-organization and discussing action spaces for black-box optimization in chip design scenarios.
This paper presents LingBot-VLA 2.0, which enhances VLA foundation models for robotics by improving generalization across tasks and embodiments, expanding action space to whole-body degrees of freedom, and incorporating predictive dynamics modeling for better temporal reasoning.
This paper identifies a threshold in decision capacity that determines whether self-play reinforcement learning agents collapse under asymmetric rule perturbations, showing that eliminating all positive-reach contingent decisions leads to rapid convergence to a deterministic exploitation attractor.