Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents Paper • 2610.20344 • Published 13 days ago • 63
DecepEval: A Benchmark for Evaluating Deception in LLM Agents Paper • 2610.07967 • Published 21 days ago • 61
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers? Paper • 2610.07557 • Published 21 days ago • 75
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 28 days ago • 157
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 29 days ago • 220
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published Sep 8 • 474