Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
Paper • 2610.20344 • Published • 63
Krish
krishkgto
AI & ML interests
inference optimization, diffusion models, bioinformatics, federated learning, reinforcement learning
Recent Activity
upvoted a paper 10 days ago
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents updated a model 15 days ago
krishkgto/dino-demo published a model 15 days ago
krishkgto/dino-demoOrganizations
None yet
upvoted a paper 10 days ago
updated a
model 15 days ago
published a
model 15 days ago
updated a
model 15 days ago
published a
model 15 days ago
upvoted 3
papers 15 days ago
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Paper • 2610.07967 • Published • 61
MaLiang-Harness: A Programmable Path to Image and Video Generation
Paper • 2609.34309 • Published • 220
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
Paper • 2609.38169 • Published • 156