Collective Intelligence with Foundation Models
arXiv:2607.07729v1 Announce Type: cross Abstract: As foundation models grow in scale and diversity, coordinating multiple models into cooperative reasoning systems offers a path toward safer, more…
Read the full articleYou might also wanna read
Survey of Self-Evolving AI Agents: Bridging Foundation Models and Lifelong Adaptability
Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, m
arxiv.org·11mo ago
How AI is reshaping collective intelligence and why we need to design systems that preserve shared problem-solving
Jacob Taylor and Scott Page explore how AI is changing the physics of collective intelligence, and the challenge now is to design systems th
brookings.edu·16d ago
Skill-MAS: A Meta-Skill Approach to Improving Multi-Agent Systems Without Retraining
Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. Ho
arxiv.org·19d agoSkill-MAS: A Meta-Skill Approach to Improving Multi-Agent Systems Without Retraining
Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. Ho
arxiv.org·19d ago
The Evolution of AI: From Static Benchmarks to Inference-Time Search for Autonomous Agents
Benchmarking at inference time as a way to achieve your agent's goals
adlrocha.substack.com·6mo ago
HASTE: A Hierarchical Multi-Agent System for Transfer-Efficient ML Engineering Across Competitions
ML engineering agents waste compute rediscovering known techniques because every competition is a cold start. We present HASTE, a hierarchic
arxiv.org·4d ago
SkillsBench: A Benchmark for Evaluating AI Agent Skills Across Diverse Tasks
Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no
arxiv.org·4mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.