3 papers
cs.AI2026
Safe Harness Self-Evolution: A Theoretical Analysis of Feasibility and Limits
Qianshu Cai, Yonggang Zhang, Jun Nie +6
Harness self-evolution is the process by which an agent modifies its prompts, tools, code, or orchestration in response to task feedback while keeping the underlying language model…
hep-th2026
Carrollian holography with agentic AI: Real mass is imaginary
Reiko Liu, Wen-Jie Ma, Hu Zheng +1
We introduce LACIA, a verification-driven agentic AI workflow for theoretical physics, and apply it with independent human checks to construct Carrollian conformal bases. We develo…
cs.AI2026
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
Qianshu Cai, Yonggang Zhang, Xianzhang Jia +5
Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a…