TELBench
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Announce Type: new Abstract: Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable. We study span-level error localization for deep-research agents.
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
arXiv:2606.02060v2 Announce Type: replace Abstract: Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable. We study span-level error localization for deep-research agents.