TSR · The desk
Science · 9 October 2026
Articles in this category in 9 October 2026.
TSR Desk · science · 9 October 2026, 01:00 UTC
RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving RewardTSR Desk · science · 9 October 2026, 01:00 UTC
Do Language Models Need Music Supervision? Verifiable Rewards for Multi-Constraint SymbolicTSR Desk · science · 9 October 2026, 01:00 UTC
RamanBench: A Large-Scale Benchmark for Machine Learning on Raman SpectroscopyTSR Desk · science · 9 October 2026, 01:00 UTC
Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny TransformersTSR Desk · science · 9 October 2026, 01:00 UTC
MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User IntentTSR Desk · science · 9 October 2026, 01:00 UTC
From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QATSR Desk · science · 9 October 2026, 01:00 UTC
ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and EvaluationTSR Desk · science · 9 October 2026, 01:00 UTC
Chronocooked: A Benchmark for Interval Timing in Reinforcement Learning AgentsTSR Desk · science · 9 October 2026, 01:00 UTC
Adversarial Images Hijack Web Agents from Visual Grounding to Browser ExecutionTSR Desk · science · 9 October 2026, 01:00 UTC
Geological text descriptions in ill-posed inverse problems: insights from learnedTSR Desk · science · 9 October 2026, 01:00 UTC
CredLeakBench: Evaluating Credential Leakage and Recovery in LLM AgentsTSR Desk · science · 9 October 2026, 01:00 UTC
Which Buildings Are Artificial Intelligence-Ready? A Measurement-Based Assessment Framework forTSR Desk · science · 9 October 2026, 01:00 UTC
Trajectory Abstraction for the Science of Language Agent BehaviorTSR Desk · science · 9 October 2026, 01:00 UTC
Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology ReportingTSR Desk · science · 9 October 2026, 01:00 UTC
Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus DatasetTSR Desk · science · 9 October 2026, 01:00 UTC
Reinforcement Learning for Code Optimization