Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM ReasoningResearchSep 29, 2026
How Much Imprecision is Enough Imprecision in my Classifier? A Practical Elicitation ProcedureResearchSep 29, 2026
The Selection Rule Decides the Winner: A Pre-Registered Audit of Open-Set Graph Anomaly DetectionResearchSep 29, 2026
When Valid Tool Calls Change Meaning: Formation-Consistent Dispatch for LLM AgentsResearchSep 29, 2026
Beneath the Tokens: A Performance Engineering Study of Multi-Token Prediction in GPU-Accelerated LLM InferenceResearchSep 29, 2026
TNF based Spectral Embedding for Effective Application of Supervised Machine Learning Techniques in Automobile Insurance Fraud DetectionResearchSep 29, 2026
JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World EnvironmentsResearchSep 29, 2026