5/6 With structured execution, execution is controlled and stays on track. You can scale only individual steps that will benefit from it, instead of doing it for the entire agentic trajectory.
AGENTS
-
ReAct Agents and High-Variance Execution in Long-Horizon Tasks
By
–
4/6 ReAct-style agents encode the entire plan in text, and only get evaluated at the very end. In long-horizon tasks, that turns execution into a high-variance gamble.
-
Maestro: Optimizing Compute Through Agentic Framework Structure
By
–
2/6 SWE-bench is not the story. Maestro is not a dedicated SWE agent, it’s an agentic framework that optimizes based on structure and learned priors. ex: knowing that 4 runs of GPT-5 mini are cheaper and better than one GPT-5 run, leads to better use of the same compute –
-
Orchestrated Test-Time Compute Scaling for Long-Horizon Agentic Tasks
By
–
1/6 Long-horizon agentic tasks are breaking our mental models. More tokens, bigger models, and best-of-N only go so far. Orchestrated approach to test-time-compute scaling is what long-horizon tasks need. Here’s what we learned using SWE-bench as a test case. Read the blog for
-
Lakebase: Managed Postgres for Data Apps and Agents
By
–
Get to know Lakebase, a fully managed Postgres for data apps and agents. Take the product tour to see how Lakebase delivers a transactional database integrated into the Lakehouse and a fully managed, serverless Postgres experience: https://
databricks.com/resources/demo
s/tours/appdev/databricks-lakebase?itm_data=demo_center?utm_source=twitter&utm_medium=organic-social
… -
AI Agents Infrastructure: Technical Reality and Privacy Security Risks
By
–
NEW w/#UdbhavTiwari Mapping the technical reality & privacy/security perils of pushing AI agents into our infra We offer palliatives, but the core issues are paradigmatic: 'agency' relies on pervasive data access + ability to act w/o explicit consent.
-
Generative AI Tech Stack: Six Layers Powering Autonomous Agents
By
–
The Generative AI ecosystem is evolving into a full tech stack — powering autonomous AI agents.
From infrastructure and LLMs to RAG pipelines, agent behaviors and orchestration layers, this framework shows the 6 layers driving next-gen AI systems. Credit: @goyalshalini #AI -
Female Optimus Release Date Announcement Expected
By
–
@grok When is the female Optimus scheduled to be released?
-
ChatLLM: Intelligent Model Routing for Seamless Workflows
By
–
We built ChatLLM by Abacus AI so you don’t have to think about models.
— Abacus.AI (@abacusai) 7 janvier 2026
You just type what you want to do.
It routes to the model that fits – reasoning, speed, creativity, longer workflows.
Keeps your flow going.
What would you use this for? pic.twitter.com/WjkBe7LBUtWe built ChatLLM by Abacus AI so you don’t have to think about models. You just type what you want to do.
It routes to the model that fits – reasoning, speed, creativity, longer workflows. Keeps your flow going. What would you use this for? -
Evaluating RL Performance: Challenges in Benchmarking Improvements
By
–
Thanks — I always half expect someone to pop up say “we just cloned this other repo and ran it for a 50% performance improvement”. With RL it is very hard to know what “good performance” is.