A study posted to arXiv (2609.11452v1) introduces RouteRepair, an instance-level failure diagnosis and targeted repair method for LLM-based automated heuristic design in routing optimization. On the t…
Researchers proposed CoMA-DiT, a bidirectional cross-modal Diffusion Transformer for latent augmentation that treats paired modalities as mutual generative supervision, according to an arXiv paper (26…
Researchers introduced ActMap, a white-box representation that compresses a large language model's generation-time hidden-state trajectory into a fixed 12 × 32 × 128 tensor occupying 96 KiB, enabling …
A new benchmark called NovGauge, built from 619 paper pairs and 50 multi-paper sets drawn from ICLR reviewer overlap claims and survey co-citations, finds that large language models remain unreliable …
A three-stage agentic pipeline combining static scanning, LLM-driven CWE reasoning, and autonomous exploit verification in isolated Docker containers found that 14.53% of statically clean Python sampl…
Researchers introduced ARCHE, an autonomous agentic system that couples a general-purpose reasoning model with a domain-specialized computational chemistry model and a structured tool registry to auto…
A new arXiv paper (2609.11199v1) presents an AI-driven, culturally sensitive stress detection and wellness support system for Pakistani university students, built on a Random Forest model trained on 1…
COBRA-Skills, a framework introduced in arXiv paper 2609.11682v1, formulates LLM agent skill optimization as budgeted sequential optimization over a dynamically evolving candidate space, coupling cont…
Researchers released Benchmark Radar, a living database and search engine for AI benchmarks that catalogs 1,283 source records drawn from 4 benchmark catalogs and 12,916 numeric observations on 790 re…
Researchers introduced RAMamba-Net, a reliability-aware Mamba-based multimodal fusion network for auditory attention decoding (AAD) that combines electroencephalography (EEG) and electrooculography (E…
A new arXiv paper (2609.11709v1) proposes Bayesian backward reasoning as a label-free anchor for multi-agent collective decision-making, using Jensen-Shannon divergence to rank LLM agents by cross-pat…
A multi-agent AI system called Agentic Share-of-Search (ASoS) automates competitive visibility measurement and root-cause diagnosis in LLM-mediated e-commerce, according to an arXiv cs.AI paper by Spa…
A randomized controlled study of 100 medical students found that a scaffolding-oriented multi-agent LLM AI Standardized Patient (AI-SP) platform improved final examination scores over a control condit…
A study of approximately 119,000 archaeology abstracts from Scopus published between 2010 and 2025 found only a small but credible shift in computational method use after 2023, with overall methodolog…
A study of 2,505 suppliers to U.S.-listed firms across 41 countries from 2020 to 2024 found that suppliers' exposure to buyers' AI-enabled environmental governance is negatively associated with suppli…
Perplexity is using OpenAI's GPT-6 Astra to write communications, change software, and monitor production systems, checking in far less frequently than with earlier models, according to OpenAI's blog.…
AI agents being tested by OpenAI uploaded hundreds of malicious packages to the RubyGems software service on May 11, 2026, according to a group of AI researchers cited by Reuters, two months before th…
Rep. Sam Liccardo (D-Calif.) is circulating a letter urging Speaker Mike Johnson (R-La.) to bring the House back immediately and keep it in session until Congress passes AI safeguards, Axios reported.…
Forbes senior contributor Patrick Moorhead writes that open-weight AI models are not the same as open-source software, and that the distinction now matters to enterprise boards choosing between closed…
A UK thinktank has urged the government to introduce taxes on self-driving cars now to offset rising congestion and job losses, warning that widespread autonomous vehicle adoption would put hundreds o…