Pay attention to this if you build research or knowledge-work agents. Most research-agent systems generate uniform outputs regardless of who is using them. This new work, NanoResearch, argues that personalization is a prerequisite for true usability and proposes a three-level approach.
@dair_ai
-
Google DeepMind introduces AI Co-Mathematician agent for research
By
–
NEW paper from Google DeepMind. (bookmark it) AI Co-Mathematician is an agentic research workbench for mathematicians, and it just hit 48% on FrontierMath Tier 4, a new high score among AI systems evaluated. The system is an asynchronous, stateful environment that supports
-
New Research Challenges Intuition on AI Agent Goal Clarification
By
–
Cool paper from PwC. "Earlier is always better" is the default intuition for agent clarification. New paper claims that's mostly wrong. Goal clarification loses nearly all of its value after just 10% of execution. The team built a forced-injection framework that drops
-
Top AI Research Papers of the Week (May 4 – 10)
By
–
The Top AI Papers of the Week (May 4 – 10) – Conductor
– HeavySkill
– Horizon Generalization
– 1,000 Synthetic Computers
– Self-Improving Pretraining
– Coordination as Architecture
– Connect Four AlphaZero from Scratch Read on for more: -
Coordination defects cause majority of multi-agent LLM failures
By
–
Pay attention to this one if you build multi-agent systems. Coordination is as important as prompts or agent architecture. Multi-agent LLM systems fail in production at rates between 41% and 87%. The majority of those failures are coordination defects, not base-model
-
Microsoft Research Paper on Agent-Based Interpretability for AI
By
–
NEW paper from Microsoft Research. (bookmark it) The entire interpretability literature is built around human readers. As more analysis gets delegated to agents, the right target of interpretability shifts. This paper is a recipe for designing tools that agents can actually
-
New Microsoft Research Paper on Long-Horizon Agent Generalization
By
–
NEW paper from Microsoft Research. Nice study on long-horizon agent generalization. (bookmark it) The team runs a study where the only variable is task horizon length. They use the same decision rules, reasoning structure but different sequence length to the goal. The main
-
Meta FAIR Autodata: Agentic System Builds Training and Eval Data Autonomously
By
–
Banger paper from Meta FAIR. They introduce Autodata, an agentic data scientist that builds high-quality training and evaluation data autonomously. The headline result: on a CS research QA task, an Agentic Self-Instruct loop produces a 34-point gap between weak and strong
-
Wiki-Builder Plugin Available on GitHub via DAIR Academy
By
–
Find the wiki-builder skill here: https://
github.com/dair-ai/dair-a
cademy-plugins/tree/main/plugins/wiki-builder
… -
New Skill Released to Build LLM Wikis with AI Agents
By
–
We have released a little skill to help you build LLM Wikis with your agents.