• Computer Science > Artificial Intelligence [Submitted on 25 Feb 2026] Title:ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices View
• Computer Science > Computers and Society [Submitted on 9 Feb 2026] Title:CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation View PDF HTML (experimental)Ab
• Computer Science > Artificial Intelligence [Submitted on 24 Feb 2026] Title:CausalReasoningBenchmark: A Real-World Benchmark for Disentangled Evaluation of Causal Identification
• Computer Science > Artificial Intelligence [Submitted on 24 Feb 2026] Title:PreScience: A Benchmark for Forecasting Scientific Contributions View PDFAbstract:Can AI systems train
• ABD benchmark tests default‑exception abduction in finite first‑order logical worlds. • Models generate sparse exception formulas to restore satisfiability under abnormality pred
• AgentOptics framework uses agentic AI for autonomous optical system control via MCP. • Interprets natural language tasks, executes protocol-compliant actions across heterogeneous
• Asymptotic Semantic Collapse: dominant context absorbs individual semantics in multi‑agent language systems. • Dominant Anchor Node with infinite inertia drives asymptotic alignm
• INDUCTION benchmark tests finite-structure concept synthesis in first‑order logic across small relational worlds. • Models output a single logical formula that uniformly explains
• INSURE‑Dial is the first public benchmark for compliance‑aware voice agents in insurance calls. • Corpus contains 50 real AI‑initiated calls and 1,000 synthetic calls, averaging
• LLMs increasingly synthesize research into structured reports, but logical reliability remains unassessed. • ReportLogic benchmark quantifies report‑level logical quality for dee
• AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Unde
• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages View PDF HTML (experi
• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation View PDF HTML (experimental)Abs
• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:How Uncertain Is the Grade? • A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment Vi
• Computer Science > Artificial Intelligence [Submitted on 17 Feb 2026] Title:How Uncertain Is the Grade? • A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment Vi
• University of Missouri researchers have released the world’s largest collection of protein models with quality assessment-a groundbreaking new resource that could accelerate drug
• TongGeometry, an AI system, autonomously generates olympiad-level geometry problems for high-level competition. • It also solves these problems, matching human expert accuracy an
• Analysts say Metaplanet’s bitcoin-linked income business is becoming critical to funding expansion while avoiding forced BTC sales.
• Computer Science > Artificial Intelligence [Submitted on 5 Feb 2026] Title:TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series
• TemporalBench offers a multi-domain benchmark for temporal reasoning in LLM agents. • Four-tier taxonomy tests historical structure, context-free, contextual, and event-condition
• Benchmark’s Mark Palmer cut his COIN price target to $267 from $421, citing worsening crypto market conditions, while reiterating a buy rating.
• Arabic LLMs often evaluated only on Modern Standard Arabic, neglecting dialects. • Dialects like Emirati carry unique vocabulary, syntax, and cultural context. • Existing benchma
• AssetOpsBench introduces a multi-agent benchmark for industrial asset lifecycle management. • Covers 2.3M sensor telemetry points and 4.2K work orders. • Evaluates agents across
• When we began studying jailbreak evaluations, we found a fascinating paper claiming that you could jailbreak frontier LLMs simply by translating forbidden prompts into obscure la
• Researchers tested jailbreak via Scots Gaelic translation, initially replicating 43% success claim. • GPT-4 responded with bomb instructions in Gaelic, but full output differed f
• Humans can sift through thousands of images, spotting subtle patterns-a skill AI still struggles to match. • Traditional VQA systems answer questions about single images, missing