Yuyang Hu

Coding agents routinely fail to build agents that truly meet user requirements, with the gap between demonstration and delivery being the norm.

Omni-modal foundation models achieve self-improvement via RL compute scaled to 1M context, leveraging asynchronous training and agentic grading for enhanced intelligence.

Atria Dawn Preview is introduced, a foundation agentic language model designed for scientific research and engineering workflows, with the goal of expanding the frontier of agent productivity in the real world.

Distilling operational knowledge from GitHub repositories boosts AI research agents' performance by over 134% on key benchmarks.

AREX achieves superior performance in deep research tasks by recursively refining answers through a novel self-improvement mechanism that outpaces traditional search methods.

Explicit evidence graphs in VeriGraph enable LLMs to achieve 87.61% claim grounding, transforming how we verify AI-generated conclusions.

Arbor's innovative approach to autonomous research enables a cumulative learning process that outperforms existing models by over 2.5 times in real-world tasks.

LLM agents are shockingly vulnerable to multi-stage "trojan" attacks that inject malicious instructions into their workspace, achieving near-perfect success rates where standard prompt injection defenses fail.

Scaling out peer agents with a shared reasoning hub, AgentFugue, unlocks a new dimension of capability gains in long-horizon tasks, proving that collective reasoning is more than just parallel compute.

LLMs can now recall relevant information from long interaction histories without retraining, thanks to a state-adaptive memory framework that uses lightweight cues to reconstruct distant information on demand.

A small, outcome-driven proxy model can outperform complex indexing methods for LLM memory retrieval, offering a more efficient and scalable solution for long-term tasks.