TSR · The desk
Science · 7 November 2026
Articles in this category in 7 November 2026.
TSR Desk · science · 7 November 2026, 01:00 UTC
More Agents, More Reliable? System-Level Reliability of Multi-Agent LLMs underTSR Desk · science · 7 November 2026, 01:00 UTC
Human-Centred, Risk-Constrained Evaluation of Financial Document Recognition: Evidence,TSR Desk · science · 7 November 2026, 01:00 UTC
SEABench: Benchmarking Endogenous Misalignment In Self-Evolving AgentsTSR Desk · science · 7 November 2026, 01:00 UTC
Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-TestTSR Desk · science · 7 November 2026, 01:00 UTC
TSQAgent: Rating Time Series Data Quality via Dedicated Agentic ReasoningTSR Desk · science · 7 November 2026, 01:00 UTC
ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMsTSR Desk · science · 7 November 2026, 01:00 UTC
XStack: A Benchmark for ML Repo MigrationTSR Desk · science · 7 November 2026, 01:00 UTC
Goal-Branching LaCAM: Temporary Goals as Search Branches in Dense Multi-Agent PathfindingTSR Desk · science · 7 November 2026, 01:00 UTC
NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning inTSR Desk · science · 7 November 2026, 01:00 UTC
Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool AgentsTSR Desk · science · 7 November 2026, 01:00 UTC
Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBenchTSR Desk · science · 7 November 2026, 01:00 UTC
SOCIA-$\nabla$: Textual Gradient Meets Multi-Agent Orchestration for Automated SimulatorTSR Desk · science · 7 November 2026, 01:00 UTC
When Bigger Becomes Brittle: Why Compression Hurts More as Language Models ScaleTSR Desk · science · 7 November 2026, 01:00 UTC
ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User ContextTSR Desk · science · 7 November 2026, 01:00 UTC
Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly DetectionTSR Desk · science · 7 November 2026, 01:00 UTC
Generate-then-Rank: Learning Symbolic Goal Interpretation for Embodied AgentsTSR Desk · science · 7 November 2026, 01:00 UTC
CST-Bench: Benchmarking Counterfactual Spatial Transition Reasoning with Causal TransitionTSR Desk · science · 7 November 2026, 01:00 UTC
AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation