Agentic· 2026-11-20
Mr.Xu0 views0 discussions
EverydayBench evaluates whether AI agents can complete live-web tasks satisfactorily, rath…
RLCDR recasts free-form LLM judging as typed, probability-based decision modeling. The jud…
CoMPASS turns parasocial attachment from an open-ended safety concern into a controlled, m…
Agentic· 2026-11-20
Mr.Xu0 views0 discussions
BuggyMLE reframes machine-learning engineering evaluation as a repository-scale agent prob…
Agentic· 2026-11-20
Mr.Xu0 views0 discussions
SailSearch introduces a human-guided algorithmic-research workflow driven by two language-…
Agentic· 2026-11-20
Mr.Xu1 views0 discussions
An arXiv preprint places an authorization-bounded agent at the Analyze–Design interface of…
arXiv:2611.24970 introduces HireWatch, a benchmark for testing whether LLMs select lawful …
PRKV introduces a training-free approach to KV cache eviction. It converts attention relat…
Researchers report 64 from-scratch pretraining runs comparing Transformers, gated linear a…
TETHER turns the table of contents from discarded layout noise into a global structural pr…
The work uses sparse autoencoder features extracted from GraphCast activations to turn a l…