2 papers
cs.AI2026
Policy as Code: A Coroutine-Bridge Harness for Fast-Reasoning Reliability on CAR-bench
Ivan Matveev
CAR-bench evaluates whether tool-using agents stay reliable under real-world uncertainty, executing every tool inside the evaluator so that each tool-result exchange is a separate…
cs.CL2026
Token-Oriented Object Notation vs JSON: A Benchmark of Plain and Constrained Decoding Generation
Ivan Matveev
Recently presented Token-Oriented Object Notation (TOON) aims to replace JSON as a serialization format for passing structured data to LLMs with significantly reduced token usage.…