Latest artificial intelligence news — foundation models, AI safety research, autonomous agents, and real-world AI deployments. Updated every 30 minutes from top AI publications.
Researchers introduced ReCAST (Reward Credit ASsignment across Timesteps), a method for per-reward, timestep-dependent credit assignment in diffusion reward fine-tuning, detailed in arXiv paper 2609.13425v1. ReCAST uses …
A new analysis method called Elo-per-token measures how large language model agents allocate test-time compute as they revise solutions, use tools, explore alternatives, and decide when to stop, addressing the difficulty…
Researchers released CVSS-X, a synthetic speech-to-speech translation corpus that translates English into 28 target languages across 12 language families, comprising roughly 240,000 parallel speech pairs per language and…
Researchers proposed LabAgent, a reproduce-and-discovery harness that uses AI agents to preserve and extend a laboratory's research methods, according to an arXiv paper (2609.13437v1). LabAgent ranked first over commerci…
A new arXiv paper introduces Continual Search, an iterative framework for automated root-cause attribution (RCA) in long-horizon AI agent failures, reporting that it improves GPT-5.5's F1 score by more than 40%, from 0.3…
A multi-agent supply chain analytics system described in arXiv paper 2609.13561v1 achieved 90% accuracy while cutting input token usage roughly fourfold compared with a single-agent baseline, according to the paper's aut…
Researchers introduced Asclepius, an adaptive agent scaffolding with a self-evolving harness, externalized clinical skills library, and three isolated subagents, which improved critical-action correctness by 22% (p = 0.0…
The FedV-KGQA poster paper reports that federated fusion across vertically partitioned knowledge graphs recovers most of the accuracy of a centralized system, while a single silo recovers little. The work, presented as a…
Researchers proposed GeoSkill, an experience-driven hierarchical skill learning framework for geospatial agents, detailed in arXiv paper 2609.13667v1. GeoSkill combines a Hierarchical Skill Bank, split into a Planning Sk…
Researchers introduced MACE, a Multi-Agent Candidate Event acquisition method that uses evidence-specialized LLM agents to refine event structure before linking, according to a new arXiv paper (arXiv:2609.13670v1). MACE …
A new arXiv survey (2609.13731v1) synthesizes 206 foundational studies and regulatory standards into a systems-security reference framework for trustworthy agentic AI, formalizing the general agent architecture as a stat…
Researchers introduced Abstract-LoRA, a single-image style transfer method that trains lightweight LoRA adapters on specific U-Net blocks in diffusion models, according to an arXiv paper (arXiv:2609.13239v1). Building on…
ArtSociety, a multi-agent framework that coordinates heterogeneous multimodal experts with two training-free controllers, achieved an Overall Score of 0.8870 on the official AffectiveArt Multidimensional Art Emotion Unde…
A new arXiv paper (2609.13251v1) proposes a subject clarity outpainting framework that combines vision-language model (VLM)-guided semantic conditioning with multiscale wavelet supervision to preserve subject detail when…
A structured temporal video reasoning pipeline combining a discrete EventGraph, a continuous EventField, and a human-readable EventGlyph view achieved 0.98 overall accuracy on a calibrated EPIC-KITCHENS subset of 10 vide…
A new arXiv paper (2609.13262v1) proposes a holistic framework for 3D Gaussian Splatting scene extrapolation and interpolation that replaces the error-prone generate-reconstruct-shift cycle with an independent camera vie…
A multi-agent framework integrating planning, tool calling, observation, and verification lets zero-shot LLM agents match reinforcement learning agents on long-horizon agricultural management tasks under the same weather…
A new web-agent architecture called OdoBot completes web-application tasks using 44% and 80% fewer tokens than the state-of-the-art agents Agent-E and WebVoyager, respectively, according to an arXiv paper (arXiv:2609.134…
A new arXiv paper (2609.13552v1) proposes the AI Trust and Assurance Layer (ATAL), a model-agnostic decision assurance architecture that evaluates whether AI-generated flight-planning outputs are reliable enough for oper…
A carbon-aware routing framework that distributes function-calling queries across a three-tier edge-cloud architecture reduces operational carbon emissions by 4x on average while matching cloud-level accuracy, according …