TSR · The desk
Science · 4 November 2026
Articles in this category in 4 November 2026.
TSR Desk · science · 4 November 2026, 01:00 UTC
Learning Molecular Chirality via Chiral Determinant KernelsTSR Desk · science · 4 November 2026, 01:00 UTC
RubricWorld: World Model-Guided Rubric Optimization for LLM GradersTSR Desk · science · 4 November 2026, 01:00 UTC
OmniPiano: Diverse Dexterous Piano-Playing Challenges for Standard, Robust, Safe, andTSR Desk · science · 4 November 2026, 01:00 UTC
An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent SystemsTSR Desk · science · 4 November 2026, 01:00 UTC
Beyond Binary Detection: Type-Aware Hallucination Analysis and Hierarchical Detection inTSR Desk · science · 4 November 2026, 01:00 UTC
Beyond Surface Metrics: Multi-Condition Requirements in Enterprise Maintenance and AI CodingTSR Desk · science · 4 November 2026, 01:00 UTC
Local or Escalate? Post-Training Expert Routing for Real-Time Duplex Speech ModelsTSR Desk · science · 4 November 2026, 01:00 UTC
Cross-Prompt Reuse of Entity-Replacement ResponsesTSR Desk · science · 4 November 2026, 01:00 UTC
Reconstruction as Spatial Evaluation: Diagnosing Cross-View Spatial Intelligence in LargeTSR Desk · science · 4 November 2026, 01:00 UTC
AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Question Answering over ScientificTSR Desk · science · 4 November 2026, 01:00 UTC
An auditable agentic pipeline for variant-to-gene prioritisation, validated against orthogonalTSR Desk · science · 4 November 2026, 01:00 UTC
Switchcraft: AI Model Router for Agentic Tool CallingTSR Desk · science · 4 November 2026, 01:00 UTC
Grading the Unannotated: Insights from the WorkRB Skill Extraction Challenge at RecSys-HR 2026TSR Desk · science · 4 November 2026, 01:00 UTC
PentestEval: Benchmarking LLM-based Penetration Testing with Modular and Stage-Level DesignTSR Desk · science · 4 November 2026, 01:00 UTC
Can You Break RLVER? Probing Adversarial Robustness of RL-Trained Empathetic AgentsTSR Desk · science · 4 November 2026, 01:00 UTC
RECEIPT: Measuring and Repairing the Return Assumption of LLM Agents in Web Service Operations