Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents Paper • 2610.18614 • Published 12 days ago • 5
Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents Paper • 2610.18614 • Published 12 days ago • 5
Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents Paper • 2610.18614 • Published 12 days ago • 5
Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction Paper • 2610.10549 • Published about 1 month ago • 8
Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction Paper • 2610.10549 • Published about 1 month ago • 8
Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction Paper • 2610.10549 • Published about 1 month ago • 8
EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation Paper • 2609.24115 • Published Sep 21 • 5
EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation Paper • 2609.24115 • Published Sep 21 • 5
EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation Paper • 2609.24115 • Published Sep 21 • 5
TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs Paper • 2607.22639 • Published Jun 22 • 5
TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs Paper • 2607.22639 • Published Jun 22 • 5
TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs Paper • 2607.22639 • Published Jun 22 • 5
ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs Paper • 2606.12451 • Published Jun 4 • 2
ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs Paper • 2606.12451 • Published Jun 4 • 2
ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs Paper • 2606.12451 • Published Jun 4 • 2
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval Paper • 2605.29271 • Published May 28 • 4
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval Paper • 2605.29271 • Published May 28 • 4
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval Paper • 2605.29271 • Published May 28 • 4
MirrorBench: An Extensible Framework to Evaluate User-Proxy Agents for Human-Likeness Paper • 2601.08118 • Published Jan 13 • 2
MirrorBench: An Extensible Framework to Evaluate User-Proxy Agents for Human-Likeness Paper • 2601.08118 • Published Jan 13 • 2