ResearcharXiv APIResearchDirect Pass@k Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time ReasoningRead the sourceLoading
News · Research
Research
Stories whose headline matches this topic. The lead is the newest one. A story dated today is marked as the top story of the day.
Live
Latest story
ResearcharXiv APIResearchDirect Pass@k Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time ReasoningRead the source
ResearcharXiv APIResearchCost-Aware Abstention for LLM-Based IT Ticket ClassificationRead the sourceResearcharXiv APIResearchLow-Bit N-Gram Embeddings for Language ModelsRead the sourceResearcharXiv APIResearchCan an Agent Debug a Web Corpus? Agentic Auditing of Slovak FineWeb2Read the sourceResearcharXiv APIResearchBilingual Language Models Capture Cross-Linguistic Influence in Second-Language ReadingRead the sourceResearcharXiv APIResearchHow Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast LesionsRead the sourceResearcharXiv APIResearchWould an LLM Match into a Residency? Uncertainty, Reasoning and Image Use of Open Language Models on the Spanish MIR ExaminationRead the sourceResearcharXiv APIResearchDiffusion Language Models for Perplexity-Aware Black-Box AttacksRead the sourceResearcharXiv APIResearchLongZero: Enhancing Long-Context Reasoning in LLMs from Zero DataRead the sourceResearcharXiv APIResearchThink Harder Where It Matters: Item-Level Adaptive Recursion for Sequential RecommendationRead the sourceResearcharXiv APIResearchEnvironment Duels: A Microcosm of LLM Co-EvolutionRead the sourceResearcharXiv APIResearchQuant-Arena: Benchmarking LLM Agents for Quantitative Trading ResearchRead the source