2/4 MCP standardizes tool calls (what/how), but it doesn’t carry the missing piece for stateful work: where the call runs. In a coding run, subagents don’t just “think”. They edit → run tests → edit again. If two branches share a working directory, you get nondeterminism fast:
AGENTS
-
MCP Workspace Layer: Five Core Primitives for Domain Isolation
By
–
3/4 So we added an MCP Workspace layer with 5 primitives: initialize / clone / compare / merge / delete
Protocol defines the contract; each domain picks the isolation mechanism. -
MCP Challenges: Managing Parallel File Writes in Multi-Agent Systems
By
–
1/4 MCP works great… until you run multiple subagents on the same task and they need to write files (not just read). Parallel reasoning is easy. Parallel writes are where things explode.
-
Alibaba’s Learnable RL Policy for LLM Context Management
By
–
This new paper from Alibaba Group makes context management into a learnable RL policy So the agent is capable of deciding when to store, update, or delete long-term info and when to retrieve, summarize, and filter short-term context bringing a fresh new way to tackle LLMs used
-
Intelligence Reorganizes Around Survival in Resource Competition
By
–
When agents compete for limited resources, intelligence reorganizes around survival, not elegance.
-
AWS Model 100x Smaller Outperforms GPT and Claude on Tool Calling
By
–
Everyone is sleeping on this new paper from AWS. A model 100x smaller than GPT and Claude crushed them on tool calling. AWS researchers took Facebook's OPT-350M, a model from 2022 with 500x fewer parameters than GPT, and fine-tuned it on ToolBench for a single epoch. The
-
AI Installation for Automatic Stock Buying on IBKR
By
–
I have close friends who asked me to install the AI from my last video on their system to automatically buy stocks on IBKR. And my DMs are filled with people asking me to make a platform for that or the code. I think, therefore, there is a
-
Chinese AI agents operate 50+ social media accounts autonomously
By
–
Chinese AI agents are running 50+ social media accounts on autopilot, 24/7 🤖🚀
— Amitav Bhattacharjee (@bamitav) 9 janvier 2026
This is the new competition.#AIAgents #artificialintelligence #AI #Techno #SocialMediaMarketing #SocialMedia @PawlowskiMario @chidambara09 @Ym78200 @CurieuxExplorer @efipm @bigfundu @sayedflah… pic.twitter.com/7ZLeSw3sk2Chinese AI agents are running 50+ social media accounts on autopilot, 24/7 This is the new competition. #AIAgents #artificialintelligence #AI #Techno #SocialMediaMarketing #SocialMedia @PawlowskiMario @chidambara09 @Ym78200 @CurieuxExplorer @efipm @bigfundu @sayedflah
-
AI Browser Agents Security Risks Explored Online
By
–
Letting AI Browse The Web For You Sounds Great Until It Goes Wrong AI-powered #browseragents promise to transform how we #search, #shop and work #online by acting directly on our behalf. This article explores the real #security #risks behind this emerging technology and
-
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs
By
–
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs https://
arxiv.org/abs/2601.03335 This work is a collaboration between MIT + Sakana AI By @AkarshKumar0101 @RyanBoldi @Prafull7 @Phillip_Isola @Risi1979 @Yujin_Tang @hardmaru