3 papers
cs.AI2026
ContextWeave: A Real-World Workflow Benchmark
Bo Wang, Yuqian Yao, Enxi Wang +25
Memory is essential as language agents move from isolated tasks to long-horizon, stateful workflows, yet existing evaluations often reduce it to retrieval or question answering. We…
cs.CL2026
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
Jiahang Lin, Shichun Liu, Chengjun Pan +8
Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because…
cs.CL2026
SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning
Renxi Wang, Honglin Mu, Liqun Ma +5
Long-context understanding has emerged as a critical capability for large language models (LLMs). However, evaluating this ability remains challenging. We present SCALAR, a benchma…