We mostly solved multi-node coordination decades ago in distributed computing. Turns out LLM teams face some of the same coordination problems today. Here is a really good read for anyone designing multi-agent systems. It applies distributed systems theory to LLM teams and finds the same O(n²) communication bottlenecks, straggler delays, and consistency conflicts showing up directly. Decentralized teams wasted more rounds communicating without making progress, but they also recovered faster when individual agents stalled. How does this relate to distributed systems? The work attempts to evaluate LLM teams as distributed systems. It lays out a principled framework instead of trial and error for deciding when teams help, how many agents to use, and what coordination structure fits the task. Designing LLM teams without distributed systems principles is like building a cluster without understanding consensus protocols. Paper: https://t.co/klHzUFJL1R

LookaheadKV Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation paper: https://t.co/j8lLnqUARR https://t.co/URKtNQkFKx

LMEB Long-horizon Memory Embedding Benchmark paper: https://t.co/fT3sEwCRgd https://t.co/lCyEY9tadB

Multimodal OCR Parse Anything from Documents On document parsing benchmarks, it ranks second only to Gemini 3 Pro on our OCR Arena Elo leaderboard, surpasses existing open-source document parsing systems, and sets a new state of the art of 83.9 on olmOCR Bench. On structured graphics parsing, dots.mocr achieves higher reconstruction quality than Gemini 3 Pro across image-to-SVG benchmarks, demonstrating strong performance on charts, UI layouts, scientific figures, and chemical diagrams paper: https://t.co/d3MkBHMuWc

@ChristosTzamos Wait this is so awesome!! Both 1) the C compiler to LLM weights and 2) the logarithmic complexity hard-max attention and its potential generalizations. Inspiring!

IBM released NLE: Non-autoregressive LLM-based ASR by Transcript Editing A non-autoregressive approach that formulates speech recognition as conditional transcript editing, achieving 27x speedup over autoregressive baselines with 5.67% WER. https://t.co/LtjPtUxf5a

XSkill: Continual learning from experience and skills A dual-stream framework enabling multimodal agents to accumulate and reuse knowledge without parameter updates. Grounded in visual context, it distills structured workflows and tactical insights to improve reasoning and tool use.

(1/2) Glad to announce our OpenMAIC! 🎉 Open-sourcing MAIC (Multi-Agent Interactive Classroom) from Tsinghua University — LLM-driven multi-agent classroom for scalable & adaptive online education. 🏗️ Core Architecture: ✅ MAIC-Craft: Read (multimodal extraction) → Plan (course components + agent generation) ✅ Adaptive Engine: Cognitive student modeling + Token-level personalization (RAG + Bloom's/ZPD/UDL) ✅ Multi-Agent Classroom: 1 Student + N Agents (Teacher, Assistant, 4 Peer Archetypes) ✅ Manager Agent: Class state receptor for turn-taking orchestration 🔗 Give it a try 👉🏻 GitHub: https://t.co/yicGCKsF1E #AI #EdTech #MultiAgent #LLM #Research #OpenSource #Tsinghua

Foundation models are losing in healthcare. Vertical models are winning. Here's why: GPT-4 can pass the USMLE. It can't write a discharge summary that Epic EHR accepts. That gap is worth billions.

In Oct. 2025, I created https://t.co/aiZgosvMTR, a browser agent extension for Chrome. Here it is beating the crap out of OpenAI Atlas by cheating. It is now OSS. Go forth, and fork/remix/make it your own. https://t.co/7YNmK3GfDZ https://t.co/Lo2vybzQPo

In Oct. 2025, I created https://t.co/aiZgosvMTR, a browser agent extension for Chrome. Here it is beating the crap out of OpenAI Atlas by cheating. It is now OSS. Go forth, and fork/remix/make it your own. https://t.co/7YNmK3GfDZ https://t.co/Lo2vybzQPo

The Top AI Papers of the Week (March 9 - March 15) - KARL - OpenDev - SkillNet - Memex(RL) - AutoHarness - FlashAttention-4 - The Spike, the Sparse, and the Sink Read on for more:

Finally finished vibe coding my personal health app built with Claude. Here's what it does: - Connects to the Oura API to sync sleep, recovery, steps, and exercise data - Tracks my monthly bloodwork via Rythm Health CSV uploads - Uses Playwright to scrape Chronometer daily nutrition and water intake - Uses Gemini to OCR Ladder workout screenshots and track my lifts - Full dashboard with weight trends, calorie balance charts, macro tracking, and a tabbed daily log It's completely interactive and honestly, pretty fucking cool. Blood markers even have visualizations based on what's in range and out of range.

Finally finished vibe coding my personal health app built with Claude. Here's what it does: - Connects to the Oura API to sync sleep, recovery, steps, and exercise data - Tracks my monthly bloodwork via Rythm Health CSV uploads - Uses Playwright to scrape Chronometer daily nutrition and water intake - Uses Gemini to OCR Ladder workout screenshots and track my lifts - Full dashboard with weight trends, calorie balance charts, macro tracking, and a tabbed daily log It's completely interactive and honestly, pretty fucking cool. Blood markers even have visualizations based on what's in range and out of range.

@DnuLkjkjh I'll try to update it with the major ones. E.g., Gemma 4 next week (likely), and DeepSeek V4 any day now 😃