Tian-Yu Shi

See Better, Foresee Better, Act Wiser: Physically Grounded Proactive Modeling and Decision Making

Zero2Repo: Can Coding Agents Build Repositories from Scratch?

Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limited to a single language and depend on manually curated tasks. We introduce Zero2Repo, a benchmark in which an agent receives a product requirements document, an interface...

TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing

TwinRouterBench is introduced, a step-level routing benchmark with two tracks that supports fast offline iteration followed by end-to-end validation under live agent execution, and success is measured by official task resolution and realized API spend.

See Better, Foresee Better, Act Wiser: Physically Grounded Proactive Modeling and Decision Making

This work studies retail service from sparse third-person video: before an explicit customer request, an agent must use limited human-object interaction evidence to intervene or remain silent, and introduces the Proactive Intent World Model, which advances static intent recognition toward intent world modeling by organ...

CARE: Context-Aware Ranking Evolution with Executable Scoring Programs for Budgeted Reaction Optimization

CARE is introduced, a reference-conditioned controller that separates program synthesis from experiment selection and attains the lowest normalized regret, the highest normalized best-so-far AUC, and the highest Top-1% Success@15 among the evaluated methods.

MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale

Results indicate that verifier-backed multi-cycle adaptation can increase small-model capability, rather than only routing around a fixed student.