2 papers
cs.AI2026
Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories
Liang Zhu, Minyang Hu, Bo Yang +6
Computation cost is a critical challenge for LLM agent systems, as their long-horizon trajectories continuously accumulate computational overhead. While existing studies focus on i…
cs.AI2026
Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification
Haoyang Liu, Jie Wang, Boxuan Niu +8
Building mathematical optimization models is critical in operations research (OR), while it requires substantial human expertise. Recent advancements have utilized large language m…