2 papers
cs.DC2026
Serving a Revisable World: Versioned Execution for Interruptible Agents
Yanxin Zhang, Rahul Sharma, Nitin Vegesna +3
LLM agents revise running tasks when users change instructions, tools fail, or new information changes a plan. Today's servers express a revision as aborting old requests and submi…
cs.AR2026
On the Limits of Machine-Learned Ranking for Modern Microarchitectural Policies
Yanxin Zhang, Shayne Wadle, Yuxuan Xiong +4
Machine-learning predictors estimate processor performance far faster than cycle-level simulation. For design-space exploration, however, the valuable test is not merely reproducin…