TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents Paper • 2605.16909 • Published May 16 • 10
DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation Paper • 2604.14683 • Published Apr 16 • 36
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 330
AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents Paper • 2601.06818 • Published Jan 11 • 1
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security Paper • 2601.18491 • Published Jan 26 • 126
Controlled Self-Evolution for Algorithmic Code Optimization Paper • 2601.07348 • Published Jan 12 • 115
