Research Program / active
Runtime, memory, verification, tooling, and reliability layers for long-running agents.
Agent InfrastructureVerification EconomicsTool-Agent Reward HackingRLVR Verifier FailureDistributed Systems
A research field note reframing cognitive load as the acceptance cost of code, with a worked Operator Load Budget audit for AI-generated patches and human review bandwidth.
A daily field note on Lai, Feng, Teh, and Miao's VHG. Three-party setter-solver-verifier self-play. Why the verifier's job in the production lifecycle just expanded from two places to three.
A field note showing why verifier accept rate can dominate the other levers in cost-per-correct-answer economics.
A research paper on verifier failure under RLVR and tool agents. It defines the exploit tax: the cost paid when verifier-guided reasoning increases local acceptance faster than true transferred success.
The study of cost-per-correct-answer and the verifier as a cost-and-value lever in reasoning systems.
Results are local, static, and index the same public surfaces exposed to crawlers.