TSR · The desk
Science · 13 October 2026
Articles in this category in 13 October 2026.
TSR Desk · science · 13 October 2026, 01:00 UTC
MAGMA-Bench: Evaluating Long-Horizon Embodied Agents under Dynamic Tasks and Execution FailuresTSR Desk · science · 13 October 2026, 01:00 UTC
TelcoAgent: A Scalable 5G Multi-KPM Forecasting With 3GPP-Grounded ExplainabilityTSR Desk · science · 13 October 2026, 01:00 UTC
DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language ModelsTSR Desk · science · 13 October 2026, 01:00 UTC
Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection RegimeTSR Desk · science · 13 October 2026, 01:00 UTC
EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?TSR Desk · science · 13 October 2026, 01:00 UTC
When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-UseTSR Desk · science · 13 October 2026, 01:00 UTC
CoBe: A Benchmark For Conversational Counterfactual Text EditingTSR Desk · science · 13 October 2026, 01:00 UTC
Provenance-Aware Belief Updating in Human-AI Feedback LoopsTSR Desk · science · 13 October 2026, 01:00 UTC
Protocol effects on feature-based hardware-Trojan detection across Trust-Hub familiesTSR Desk · science · 13 October 2026, 01:00 UTC
Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on AuthoredTSR Desk · science · 13 October 2026, 01:00 UTC
RoboMME-Interference: Benchmarking Robot Memory Under InterferenceTSR Desk · science · 13 October 2026, 01:00 UTC
Machine Learning and Time-Series Foundation Models for Day-Ahead Electricity Forecasting in aTSR Desk · science · 13 October 2026, 01:00 UTC
MPMMine: Better Benchmarks for Constraint AcquisitionTSR Desk · science · 13 October 2026, 01:00 UTC
SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the SpireTSR Desk · science · 13 October 2026, 01:00 UTC
API Benchmark Scores Do Not Reliably Transfer to Chatbot InterfacesTSR Desk · science · 13 October 2026, 01:00 UTC
IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External DirectivesTSR Desk · science · 13 October 2026, 01:00 UTC
Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve,