TSR · The desk
Science · 28 October 2026
Articles in this category in 28 October 2026.
TSR Desk · science · 28 October 2026, 01:00 UTC
ImageRSI: Verification-Driven Recursive Self-Improvement for Agentic Image GenerationTSR Desk · science · 28 October 2026, 01:00 UTC
RxnExBench: Benchmarking Vision-Language Models for Structured Chemical Reaction ExtractionTSR Desk · science · 28 October 2026, 01:00 UTC
EvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful EvolverTSR Desk · science · 28 October 2026, 01:00 UTC
MedAction: Towards Active Multi-turn Clinical Diagnostic LLMsTSR Desk · science · 28 October 2026, 01:00 UTC
Validating the Comparison, Not Just the Scorer: Why Overall Accuracy Can Mislead in InteractiveTSR Desk · science · 28 October 2026, 01:00 UTC
StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual ReasoningTSR Desk · science · 28 October 2026, 01:00 UTC
From Visual Affinity to Learning Credit in Multimodal Reinforcement LearningTSR Desk · science · 28 October 2026, 01:00 UTC
EASformer: Environment-Action-State Alignment for Industrial Generative RankingTSR Desk · science · 28 October 2026, 01:00 UTC
AgentPerturb: Evaluating LLM Agent Robustness under Controlled Interaction PerturbationsTSR Desk · science · 28 October 2026, 01:00 UTC
What the Query Remembers: Query Abstraction Governs Lexical and Dense Retrieval of ClassicalTSR Desk · science · 28 October 2026, 01:00 UTC
MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP AgentsTSR Desk · science · 28 October 2026, 01:00 UTC
Beyond Gain: Measuring Skill Internalization for Agent Skill RetirementTSR Desk · science · 28 October 2026, 01:00 UTC
SP-Guide: Enhancing Aerial Vision-Language Navigation with Spatial PriorsTSR Desk · science · 28 October 2026, 01:00 UTC
Astro2Method: Benchmarking LLMs on Machine Learning Method Selection in AstronomyTSR Desk · science · 28 October 2026, 01:00 UTC
Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion SimulationsTSR Desk · science · 28 October 2026, 01:00 UTC
Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting