Home Knowledge Base Perturbation Recovery Rate

Perturbation Recovery Rate

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

arXiv:2606.05806v1 Announce Type: new Abstract: Existing benchmarks evaluate Tool-Integrated Reasoning (TIR) in LLMs on idealized ''happy paths'', largely overlooking real-world tool failures. We introduce ToolMaze, a benchmark for dynamic path discovery and error recovery in TIR agents. To separate systematic replanning from blind trial-and-error, ToolMaze adopts a two-dimensional design: DAG-based topological complexity and a $2 \times 2$ taxonomy of tool perturbations (explicit/implicit,...

arXiv CS 5d ago

Closed-Form Pose Estimation of Endoluminal Medical Devices via Gradiometer-Based Electromagnetic Localization System

arXiv:2606.01946v1 Announce Type: new Abstract: Embedded magnetic tracking holds highly attractive prospects for remote navigation of endoluminal medical devices. However, existing six-degree-of-freedom pose recovery approaches often require pre-calibrated workspace field maps or iterative nonlinear optimization. This letter presents a Gradiometer-Based Electromagnetic Localization System (GELS), a closed-form tracking framework that uses a compact magnetometer array as an embedded...

arXiv CS 8d ago

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Announce Type: new Abstract: Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization capabilities remain fundamentally limited. They3 lack the robustness required to handle perturbations, frequently failing when con-4 fronted with lighting changes, altered camera viewpoints, or small initial-state5 variations. We propose PROBEACT, a training-free runtime intervention...

arXiv CS 1d ago