Showing 2026Show all
3 papers · 1 filter
cs.AI2026
AgentPProf: Semantic Profiler for Long Horizon AI Agents
Yusheng Zheng, Chaokun Chang, Yu Mao +7
AI agents increasingly orchestrate long-running activities with users, tools, and system resources for days and weeks. To improve agent quality, safety, and cost efficiency, develo…
cs.PL2026
When Can Agents Safely Checkpoint, Fork, Restore, and Merge? Exact Checking for Execution Edits
Yusheng Zheng, Xiaoyu Song, Yanpeng Hu +3
Agent runtimes can Checkpoint an execution, Fork it, Restore a checkpoint, or Merge branches without restarting a task. We call these operations execution edits, with Checkpoint re…
cs.CL2026
Implicit Reasoning Steering via Concept Chaining
Xiao Ye, Sanika Chavan, Yuxi Huang +4
Large language models often appear to reason reliably, yet on many questions repeated sampling yields both correct and incorrect answers, revealing an underlying fragility in how f…