Large Language Models

AI joins the 8-hour work day as GLM ships 5.1 open source LLM, beating Opus 4.6 and GPT-5.4 on SWE-Bench Pro

Claude Suffered a 'Major Outage.' Anthropic Says It's Fixed.

Anthropic later said it had "applied a fix" and service should be returning to normal.

How I use Claude for strategy, Gemini for research and ChatGPT for 'the grind'

[2603.04743] DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval

Abstract page for arXiv paper 2603.04743: DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval

[2603.04759] Stacked from One: Multi-Scale Self-Injection for Context Window Extension

Abstract page for arXiv paper 2603.04759: Stacked from One: Multi-Scale Self-Injection for Context Window Extension

[2603.04727] Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild

Abstract page for arXiv paper 2603.04727: Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in t...

[2603.04707] Detection of Illicit Content on Online Marketplaces using Large Language Models

Abstract page for arXiv paper 2603.04707: Detection of Illicit Content on Online Marketplaces using Large Language Models

[2603.04698] Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement

Abstract page for arXiv paper 2603.04698: Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement

[2603.04678] Optimizing Language Models for Crosslingual Knowledge Consistency

Abstract page for arXiv paper 2603.04678: Optimizing Language Models for Crosslingual Knowledge Consistency

[2603.04676] Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks

Abstract page for arXiv paper 2603.04676: Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks

[2603.04663] Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency Hallucination Detector

Abstract page for arXiv paper 2603.04663: Neuro-Symbolic Financial Reasoning via Deterministic Fact Ledgers and Adversarial Low-Latency H...

[2603.04597] Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

Abstract page for arXiv paper 2603.04597: Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

[2603.04474] From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Abstract page for arXiv paper 2603.04474: From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

[2603.04464] Understanding the Dynamics of Demonstration Conflict in In-Context Learning

Abstract page for arXiv paper 2603.04464: Understanding the Dynamics of Demonstration Conflict in In-Context Learning

[2603.04459] Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks

Abstract page for arXiv paper 2603.04459: Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks

[2603.04460] VSPrefill: Vertical-Slash Sparse Attention with Lightweight Indexing for Long-Context Prefilling

Abstract page for arXiv paper 2603.04460: VSPrefill: Vertical-Slash Sparse Attention with Lightweight Indexing for Long-Context Prefilling

[2603.04455] Large Language Models as Bidding Agents in Repeated HetNet Auction

Abstract page for arXiv paper 2603.04455: Large Language Models as Bidding Agents in Repeated HetNet Auction

[2603.04454] Query Disambiguation via Answer-Free Context: Doubling Performance on Humanity's Last Exam

Abstract page for arXiv paper 2603.04454: Query Disambiguation via Answer-Free Context: Doubling Performance on Humanity's Last Exam

[2603.04453] Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models

Abstract page for arXiv paper 2603.04453: Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models

[2603.04452] A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Science

Abstract page for arXiv paper 2603.04452: A unified foundational framework for knowledge injection and evaluation of Large Language Model...

[2603.04444] vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models

Abstract page for arXiv paper 2603.04444: vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models

[2603.04436] ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation

Abstract page for arXiv paper 2603.04436: ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation

[2603.04443] AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systems

Abstract page for arXiv paper 2603.04443: AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systems