This article is the clearest Chinese piece I've seen recently on Agent memory. Disclosure: That EverOS mentioned in the article is made by us @EverMind
. Adding three points: 1. That 93.05% LoCoMo accuracy isn't some paper hype number—it's from a script you can run straight from
LLMS
-
Technical insights on AI agent memory and LoCoMo accuracy
By
–
-
Leveraging Multi-Agent Architectures and AI Models for Business Growth
By
–
🚨 Agent Swarms Help Create Billion Dollar Companies
— Abacus.AI (@abacusai) 13 mai 2026
Use SOTA AI models including
– Opus 4.7 and Sonnet 4.6
– GPT 5.5
– Nano Banan Pro
– SeeDance 20
to create multi-agent architectures with swarms of agents
Thousands of people are using these multi-agent systems to run… pic.twitter.com/HvMmDnAS14Agent Swarms Help Create Billion Dollar Companies Use SOTA AI models including – Opus 4.7 and Sonnet 4.6
– GPT 5.5
– Nano Banan Pro – SeeDance 20 to create multi-agent architectures with swarms of agents Thousands of people are using these multi-agent systems to run -
Research on Sparser, Faster, and Lighter Transformer Language Models
By
–
Sparser, Faster, Lighter Transformer Language Models
-
AI Autonomy Levels: Presets, Refined Inputs, and Evaluated Outputs
By
–
increasing levels of autonomy: /skill: preset prompts /plan: human-refined inputs /goal: AI-evaluated outputs
-
ELF: Embedded Language Flows — arXiv paper
By
–
ELF: Embedded Language Flows Hu et al.: https://
arxiv.org/abs/2605.10938 #ArtificialIntelligence #AIAgents -
Embedded Language Flows: New AI Agent Research
By
–
ELF: Embedded Language Flows Hu et al.: https://
arxiv.org/abs/2605.10938 #ArtificialIntelligence #AIAgents -
Anthropic Launches Claude-for-Legal, an AI Lawyer Tool
By
–
Anthropic acaba de lanzar el abogado más barato del mundo
— Nico (@nicos_ai) 12 mai 2026
Se llama claude-for-legal.
Y esto es lo que es capaz de hacer:
• Leer y revisar contratos
• Redactar respuestas legales
• Construir tablas de reclamaciones para juicios
• Vigilar fechas de vencimiento y renovaciones… https://t.co/4YJnce23tA pic.twitter.com/uoyrRALTwUAnthropic has just launched the world's cheapest lawyer It's called claude-for-legal. And here's what it's capable of doing:
• Reading and reviewing contracts
• Drafting legal responses
• Building claims tables for trials
• Monitoring due dates and renewals
• Connecting -
Workshop on Reliable Financial Agents at AICouncilConf
By
–
We're live from @AICouncilConf A huge thank you to everyone who joined Charles Dickens’ workshop this morning: Towards Reliable Financial Agents: How a 4B Model Outsmarted a 235B Giant. You can find our team in the exhibitor hall throughout the rest of the conference.
-
OpenAI confirms Study Mode still accessible via slash commands
By
–
OpenAI contacted me to say “Study Mode is still live and accessible via /study and /learn shortcuts” so that’s good, although the official study mode page doesn’t mention that. (I don’t think slash commands are a natural thing for the vast majority of people).
-
OpenAI confirms Study Mode accessible via /study and /learn shortcuts
By
–
Was told by OpenAI that “Study Mode is still live and accessible via /study and /learn shortcuts” (I don’t think this is generally known, or documented)