Xinyu Ye

🔥New paper: Omni-SimpleMem 🧠Multimodal lifelong memory for AI agents — text, image, audio & video. 📈Results: 🏆LoCoMo F1: +57% over Mem0 / Claude-Mem 🏆Mem-Gallery F1: +165% over Mem0 / Claude-Mem ⚡ 3.5x faster retrieval 🔬 How it was built: AutoResearchClaw's Human-in-the-Loop Co-Pilot mode: 🧑‍🔬 Humans set the research direction 🤖 AI agents ran ~50 experiments autonomously 🐛 Found bugs worth +175% F1 🏗️ Redesigned architecture ✍️ Optimized prompts humans missed 📄Paper: arxiv.org/abs/2604.01007 💻Code: github.com/aiming-lab/Sim… Led by @JiaqiLiu835914, and nice work w/ @YanqingLiu83931, @StephenQS0710, @lillianwei423, @richardxp888, @HaoqinT, @ZhengBerkeley, @cihangxie, @dingmyu

🚀 Introducing AutoHarness (「Aha」) — automated harness engineering for AI agents. In LLM training, the aha moment is when a model learns to reason. For agents, it's when a better harness makes the same model shine. Agent = Model + Harness. The model reasons. The harness does everything else: 🧠 Context management 🛡️ Tool governance 💰 Cost control 👁️ Observability 💾 Session persistence These are the patterns that separate a toy from a system. AutoHarness automates this entire layer. 🔧 What's inside: - 6-step tool pipeline: parse → classify → permit → execute → sanitize → audit - 3 modes (Core / Standard / Enhanced) — from lightweight to full-featured - Smart context management with token budgeting and multi-layer compression - Full observability: per-call cost tracking, JSONL audit trail, trace diagnostics - Multi-agent profiles with role-based permissions - Any LLM provider Every agent deserves its aha moment. Led by @JiaqiLiu835914, and Kudos to the team @XinyeYee, @richardxp888, @lillianwei423, @HaoqinT @Xinyu2ML, @yuyinzhou_cs, @ZhengBerkeley, @dingmyu, @cihangxie, etc.