#theory
- Agentic Transformers Provably Learn Depth-First Search via Reinforcement Learning Carnegie Mellon University / Ohio State University research
- The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary research
- Self-Evolving Agent Harness: Scaffold Self-Improvement with Frozen Model Weights research
- Agentic Transformers Provably Learn to Search via Reinforcement Learning research