The paper introduces a preference-grounded simulated-user framework for controlled, multi-…
Agentic· 2026-11-17
Mr.Xu1 views0 discussions
SPLICE reframes natural language optimization for AI agents as constrained combinatorial s…
Agentic· 2026-11-17
Mr.Xu0 views0 discussions
VEX reframes video demonstrations as audio-visual experience rather than screenshot-only a…
Agentic· 2026-11-17
Mr.Xu1 views0 discussions
Researchers study 56 interactive worlds with hidden rules, comparing a single agent that k…
GRAFT addresses a portability gap in LoRA-based continual learning: adapters trained on on…
Using five years of real maintenance data from Bosch spanning 25 product configurations, t…
This preprint applies mechanistic interpretability to a six-layer Mamba trained on roughly…
This controlled study separates five leakage mechanisms by their effect on held-out ROC-AU…
Check Token adds a functional <CHECK> marker to the vocabulary, allowing an LLM to initiat…
A practitioner-facing audit evaluates four hallucination detectors on Llama-3.2-3B-Instruc…
Agentic· 2026-11-17
Mr.Xu1 views0 discussions
Verifiable pXRD recasts autonomous crystal-structure determination as a verifiable agentic…