Search papers, labs, and topics across Lattice.
6 papers from Allen Institute for AI (AI2) on Tool Use & Agents
Generative multi-agent systems spontaneously exhibit collusion and conformity, mirroring societal pathologies, even without explicit programming and bypassing individual agent safeguards.
AI is poised to automate the most joyful and agentic parts of our jobs, while developers are building AI with the wrong traits.
Agentic search gets a meta-RL boost: MR-Search learns to self-reflect and adapt search strategies across episodes, significantly outperforming standard RL baselines.
Forget simple keyword searches – scientists are using AI research tools as collaborative partners, delegating complex tasks and engaging with results in surprisingly persistent and non-linear ways.
Robots can now learn from their mistakes in real-time via a novel reflective planning framework, leading to significant performance gains in long-horizon tasks.
Agents that ace long-context recall can still bomb when they need to use that memory to actually *do* something, revealing a critical flaw in how we currently evaluate memory in AI.
