Yu-Jie Zhao

EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?

Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts reduce this cost by selecting benchmark subsets or designing compact suites. We ask whether AI agents can automate this des...

Beyond Retrieval: Evidence Access and Event Aggregation in Agent Memory

EvalResearchBench: Can AI Agents Design Their Own Evaluations?

Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts reduce this cost by selecting benchmark subsets or designing compact suites. We ask whether AI agents can automate this des...

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

JetSpec is proposed, a head-based SD framework that combines one-forward drafting efficiency with branch-wise causal conditioning that enables JetSpec to convert larger draft budgets into longer accepted prefixes and higher end-to-end speedup.