Yong Wang

Real-world professional tasks demand agents that learn from exploration and feedback, a capability unlocked by a novel engine that reconstructs environments to force agents through the full problem-solving lifecycle.

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

Self-summarization in LLMs can enhance reasoning coherence and reduce context exhaustion, leading to a 4% performance boost with shorter rollouts.

Focused quantum states exhibit over 70% greater resilience against coherent attacks compared to traditional fidelity measures, challenging existing assumptions about quantum robustness.

Fine-grained decision-making in agentic RL can boost performance by nearly 4 points, challenging the reliance on coarse heuristics.

Bootstrapping LLM agents to co-evolve as both agent and environment can lead to significant performance gains, with an average improvement of over 4% on complex tasks.

Forget about re-balancing losses – gradient geometry is the key to unlearning in LLMs without sacrificing retention.

LLM agents can now learn from *everyone's* experience, not just their own, leading to system-wide improvements without requiring additional user effort.