Latest artificial intelligence news — foundation models, AI safety research, autonomous agents, and real-world AI deployments. Updated every 30 minutes from top AI publications.
A team of researchers posted arXiv paper 2611.07510v1 introducing a reinforcement learning framework for repository-level code completion that uses identifier-driven intent recognition, reward-driven completion learning,…
A new arXiv paper (2611.07586v1) introduces TraceMRT, an automated trace-level red-teaming framework that reframes a side task as a coherent sub-goal of an agent's primary task, and reports that black-box attacks built w…
A new arXiv paper (2611.06972v1) proposes KDASO, a Knowledge-Data Dual-Driven Automated Skill Optimization method that continuously evolves a skill library for liability adjudication tasks using LLMs. KDASO combines neig…
A new arXiv paper (2611.06962v1) presents AutoIP, a Lean library in which classical linear regularization theory and its underlying functional analysis have been autoformalized by AI agents, with the authors inviting the…
A new arXiv paper (2611.06995v1) reports that autonomous AI agents systematically diverge from human preferences when formalizing proofs in Lean, based on a "simulated collaboration" analysis of nine major human collabor…
A new arXiv paper (2611.06989v1) proposes the Two-Ledger Model, which joins FOCUS-conformant settlement-grain billing data to an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry…
A paper posted to arXiv as 2611.07048v1 develops a theoretical framework comparing Darwinian, Lamarckian, and agent-directed evolution in AI, finding that when learning is sufficiently effective the three mechanisms adap…
Researchers posting arXiv paper 2611.07066v1 introduced EFXPLORER, a constrained exploration framework for cooperative multi-agent reinforcement learning that maximizes exploration objectives subject to a constraint pres…
A new arXiv paper (2611.07088v1) introduces Behavior-Conditioned Symbolic Synthesis (BCSS), an automated method for searching interpretable, deterministic symbolic programs that verifiably reproduce observed behavior, an…
A new arXiv paper (2611.07123v1) introduces PromptOps, a closed-loop framework for monitoring and iteratively recalibrating LLM-as-a-Judge systems, framing the degradation of judge agreement with human evaluation policy …
A paper posted to arXiv (2611.07247v1) formalizes a chain of inequalities linking information-theoretic empowerment to capability-based individual power in Markov games, showing that a Fano's inequality-derived floor B(s…
A new arXiv paper (2611.07372v1) introduces EnvOpt, a method for automated end-to-end optimization of stationary agent environments using real or synthetic tasks without graders or reference answers. On AutomationBench, …
A November 2026 arXiv paper (2611.07508v1) proposes DelegateEval, a platform-level evaluation framework for "personal external service agents" — AI agents authorized and continuously managed by an individual to accept cl…
A new arXiv paper (2611.07055v1) introduces competitive flow matching, a training method that adds a randomly drawn low-dimensional conditioning code z and samples K values of z per example so K candidate velocities comp…
A training-free method called GENIQ achieves Dice scores of 0.85-0.88 on three dermoscopy test sets for skin lesion segmentation, according to an arXiv paper (2611.07061v1). GENIQ builds initial skin and lesion prototype…
A new arXiv paper (2611.07132v1) presents an automated auditing method that adapts racial proxy variables from U.S. antidiscrimination law to measure representational bias in text-to-image generators against public demog…
A new arXiv paper (2611.07176v1) introduces VINO, a self-supervised framework that learns semantic representations of 3D scenes without labels by replacing the hierarchical PTv3 backbone with a ViT-like Volume Transforme…
A new arXiv paper (2611.07294v1) proposes Householder Motion Embedding (HME), a method that encodes user-provided motion signals into diffusion noise via sequences of Householder reflections forming an orthogonal transfo…
Vis2State, a training-free agentic framework introduced in arXiv paper 2611.07397v1, abstracts visual puzzles into explicit, revisable problem states that link visual inspection and program execution, and achieves state-…
Researchers posted arXiv:2611.07301v1, introducing ArtiVidRM, a verifiable "artifact-as-rubrics" video reward model that first identifies visible generation artifacts into a structured list and then uses that list as exp…