TSR · The desk
Science · 27 October 2026
Articles in this category in 27 October 2026.
TSR Desk · science · 27 October 2026, 01:00 UTC
The Helpful Agent Problem: When Emergent Cooperation Among LLM Agents Bypasses IntendedTSR Desk · science · 27 October 2026, 01:00 UTC
ACVA-Bench: Beyond Prompt Following in Abstract Concept Visualization Ability for Text-to-ImageTSR Desk · science · 27 October 2026, 01:00 UTC
RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning AlgorithmsTSR Desk · science · 27 October 2026, 01:00 UTC
OpenHome: From Perception to Insight in Smart-Home Camera VideosTSR Desk · science · 27 October 2026, 01:00 UTC
When Agents Fail: Model or Harness--Who's to Blame?TSR Desk · science · 27 October 2026, 01:00 UTC
Continuous Audio Thinking for Large Audio Language ModelsTSR Desk · science · 27 October 2026, 01:00 UTC
ALLMTS: Automated LLM-based Medical Triage SystemTSR Desk · science · 27 October 2026, 01:00 UTC
Where Cross-Question Structure in LLM Errors Comes From: Shared Seeds, Shared Prompts, andTSR Desk · science · 27 October 2026, 01:00 UTC
AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic MisalignmentTSR Desk · science · 27 October 2026, 01:00 UTC
Collaborative In-Context Learning for Indoor Radio Map EstimationTSR Desk · science · 27 October 2026, 01:00 UTC
Noise-Robust Financial Numerical Entity Attribute TaggingTSR Desk · science · 27 October 2026, 01:00 UTC
4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented AgentsTSR Desk · science · 27 October 2026, 01:00 UTC
Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-BasedTSR Desk · science · 27 October 2026, 01:00 UTC
TENET: Time-point Encoding Network for Multivariate Time Series Anomaly DetectionTSR Desk · science · 27 October 2026, 01:00 UTC
IGG: A Benchmark for Interactive GUI Grounding under Visibility ConstraintsTSR Desk · science · 27 October 2026, 01:00 UTC
MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery inTSR Desk · science · 27 October 2026, 01:00 UTC
AutoMIL: Automated Multiple Instance Learning for Whole-Slide Image Classification