news

Jul 28, 2026 Released CodeNib, a multi-view data system for serving repository context to coding agents — paper, code, codenib.ai.
Jun 15, 2026 Started as a research intern at NVIDIA, working on LLM agents for hardware design and verification.
Mar 13, 2026 SWE-Milestone is out — a benchmark for continuous software evolution where frontier agents fall from >80% on isolated tasks to 38%. To appear at ICML 2026.
Mar 9, 2026 Our position paper on multi-agent memory as a computer architecture problem is on arXiv, and was featured on ACM SIGARCH.
Feb 26, 2026 AMA-Bench measures long-horizon memory for agentic applications, beyond the usual dialogue setting — paper, site.