Pues la respuesta la han encontrado tirando del hilo de un nombre que se menciona en el paper: Aletheia Parece ser la siguiente evolución en la línea de trabajo de agentes matemáticos de Google
AGENTS
-
LLMs as System Components: Beyond Tool Calling
By
–
No, tool calling has been around for many years – LLMs can be part of a *system* that can run experiments. LLMs are definitely useful!
-
Safety concerns with Motbot and Clawdbot AI agents
By
–
I would be careful with it – Motbot / Clawdbot is not very safe to use. I would use it only with a sandboxed agent + that has no access to your credentials and data.
-
Gödel Agent: Self-Referential Framework for Recursive Self-Improvement
By
–
Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement Yin et al.: https://
arxiv.org/abs/2410.04444 #ArtificialIntelligence #DeepLearning #MachineLearning -
ARC-AGI-3 Quickstart: Build AGI Solver Agents Locally
By
–
If you're feeling like inventing AGI today, check out the new ARC-AGI-3 quickstart. You can get started building your own solver agent in minutes, locally, and you can run your experiments at 150,000 APM.
-
Claude Plans First AI-Driven Mars Rover Navigation
By
–
On December 8, the Perseverance rover safely trundled across the surface of Mars.
— Anthropic (@AnthropicAI) 30 janvier 2026
This was the first AI-planned drive on another planet. And it was planned by Claude. pic.twitter.com/kVbdKWibuPOn December 8, the Perseverance rover safely trundled across the surface of Mars. This was the first AI-planned drive on another planet. And it was planned by Claude.
-
Context Management Crucial for Long-Horizon Agent Development
By
–
Context management is just as important as model quality for long-horizon agents. Our co-founder @hwchase17 joined @sequoia to share what we've learned building LangGraph and Deep Agents: – Building agents is different from traditional software because the logic lives in the
-
Agent-1 to Superintelligence: AI 2027 Scenario Implications
By
–
From Agent-1 to Superintelligence: Decoding the AI 2027 Scenario and Its Profound Implications Check out my article: https://
linkedin.com/pulse/from-age
nt-1-superintelligence-decoding-ai-2027-its-giuliano-liguori–vb1vf
… Via @ingliguori #AI2027 #FutureTech -
LangSmith Agent Builder GA and Experiment Comparison Tools
By
–
Check out what we shipped this January We’re starting 2026 with: • LangSmith Agent Builder now GA — describe the agent you want and let it handle planning, tool selection, and using subagents when needed • Side-by-side experiment comparison to see what actually changed
