AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchWhen Stable and Preferred Semantics Agree: A Path-Based Approach
arXiv:2610.30176v1 Announce Type: new Abstract: We investigate structural conditions under which preferred and stable semantics agree in abstract argumentation frameworks. Our approach is based on suitably chosen sets of…
- arXiv cs.AIagentsFeedback That Backfires in Games: Do LLM Players Repeat the Move They Just Watched Fail?
arXiv:2610.30205v1 Announce Type: new Abstract: When an LLM agent's move fails, the harness writes the move and the failure message into the transcript and asks again. In tool calling, this record makes small models more…
- arXiv cs.AIresearchBreaking the high-degree barrier in Lehmer's problem with a human-AI discovery loop
arXiv:2610.30277v1 Announce Type: new Abstract: While artificial intelligence has made rapid progress in mathematical reasoning, many open problems depend on structure that is revealed only through large-scale computatio…
- arXiv cs.AIresearchRoute-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs
arXiv:2610.30351v1 Announce Type: new Abstract: Large language models often apply complex reasoning indiscriminately, leading to overthinking on simple tasks and underthinking on harder ones. We present Route-and-Generat…
- arXiv cs.AIresearchSoft Ontology Priors over Latent Concept Posteriors for Weakly Supervised Neuro-Symbolic Learning
arXiv:2610.30391v1 Announce Type: new Abstract: Neuro-symbolic (NeSy) predictors that supervise only the task label suffer from reasoning shortcuts: distinct concept mappings achieve the same maximum likelihood, leaving…
- arXiv cs.AIagentsRoleFlow: Self-Evolving Multi-Role Agentic Collaboration via Structural Adaptation
arXiv:2610.30429v1 Announce Type: new Abstract: Large language model (LLM) based multi-agent systems often rely on predefined collaboration structures, limiting their adaptability to evolving task requirements. Although…
- arXiv cs.AIagentsSecure Agentic AI and Multimodal Intelligence in 6G Communication Systems
arXiv:2610.30436v1 Announce Type: new Abstract: Sixth-generation (6G) communication systems are expected to support immersive, intent-driven, and latency-critical services through tight integration of multimodal intellig…
- arXiv cs.AIagentsSpecMAGIC: Specification-Guided Multi-Task Generalization in Multi-Agent Reinforcement Learning
arXiv:2610.30443v1 Announce Type: new Abstract: Multi-task generalization is an important yet underexplored problem in multi-agent reinforcement learning (MARL). Many real-world applications require multi-agent systems t…
- arXiv cs.AIagentsA Three-Pillar Governance Framework for Safe and Trustworthy AI Agents
arXiv:2610.30445v1 Announce Type: new Abstract: AI agents capable of autonomous decision-making introduce significant challenges related to safety, alignment, accountability, and human oversight. Existing Human-in-the-Lo…
- arXiv cs.AIresearchSame Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning
arXiv:2610.30450v1 Announce Type: new Abstract: Reasoning LLMs often continue reasoning after reaching a correct answer, wasting computation and sometimes replacing it with an incorrect one. Deciding when to stop is a me…
- arXiv cs.AIagentsWhy Bother Me Again? Benchmarking Personal Agent Memory for Interaction Preferences
arXiv:2610.30485v1 Announce Type: new Abstract: Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable a…
- arXiv cs.AIagentsFrom Single-Actor Environments to Multi-Actor Event Worlds: Can LLMs Be Event World Models?
arXiv:2610.30488v1 Announce Type: new Abstract: World models help agents assess the consequences of their actions before acting. Many real systems, however, involve multiple actors who make their own decisions, can evolv…
- arXiv cs.AIagentsWhat the Trace Shows and What the Label Says: Auditing Behavioral Detectors in Agent Evaluation
arXiv:2610.30491v1 Announce Type: new Abstract: LLM agents are often evaluated by reducing execution traces to labels such as final-answer correctness, tool verification, and fault propagation. These labels are measureme…
- arXiv cs.AIagentsFrom Prose to Properties: Testing Research Claims with ARATest for Agent-Native Science
arXiv:2610.30495v1 Announce Type: new Abstract: AI agents now run experiments and report findings, so research produces claims faster than researchers can check them. Each empirical claim implies a property that must hol…
- arXiv cs.AIresearchCan LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3
arXiv:2610.30499v1 Announce Type: new Abstract: A generally intelligent system acquires new skills efficiently without requiring humans to redesign its software scaffold for every new task. Yet language models rarely act…
- arXiv cs.AIagentsPLE: Physical-Engineering's Last Exam
arXiv:2610.30537v1 Announce Type: new Abstract: Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no exi…
- arXiv cs.AIagentsGoverned Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core
arXiv:2610.30557v1 Announce Type: new Abstract: LLM agents that act on live Web data must combine heterogeneous evidence, remember what they have done and improve from outcomes without weakening their own safeguards. We…
- arXiv cs.AIagentsDiagnosing Personalization Failures in Mobile GUI Agents
arXiv:2610.30573v1 Announce Type: new Abstract: Unlike conventional GUI agents, personalized GUI agents require user preferences to guide sequential execution over changing GUI states. This raises two challenges: determi…
- arXiv cs.AIresearchModel Organisms of Collusion: Corrective Transfer in Untrusted Monitors
arXiv:2610.30582v2 Announce Type: replace Abstract: AI control protocols aim to get useful work from models that may be misaligned by monitoring their behaviour. One approach uses a second copy of the same model as the m…
- arXiv cs.AIagentsBetter Reasoning, Not Just Bigger Models: A Structure-Grounded Framework for Efficient and Reliable Inference
arXiv:2610.30611v1 Announce Type: new Abstract: Scaling large language models has substantially improved linguistic fluency, yet reliable autonomous agents require more than fluent generation. In multi-turn inference, cu…
- arXiv cs.AIresearchLarge language models show systematic failures in incorporating evolving medical knowledge
arXiv:2610.30631v1 Announce Type: new Abstract: Medical knowledge evolves as clinical guidelines revise recommendations, yet whether large language models (LLMs) faithfully incorporate such changes remains unclear. We in…
- arXiv cs.AIresearchSpeculative Acceptance Does Not Decay with Position: A Full-Length Diagnostic on Long Chain-of-Thought with Independent Drafts
arXiv:2610.30644v1 Announce Type: new Abstract: The claim that speculative-decoding acceptance rate decays as a chain-of-thought grows longer has become a de facto industry narrative, motivating draft-model co-design and…
- arXiv cs.AIagentsAnticipating Social Consequences with Distributional World Models
arXiv:2610.30657v1 Announce Type: new Abstract: Social world models predict how interactions develop after an action, helping agents negotiate, cooperate and mediate. In these situations, one action can lead to several p…
- arXiv cs.AIagentsA Topology-Guided GeoAI Agentic Framework for Urban Flood Screening
arXiv:2610.30660v1 Announce Type: new Abstract: Open-world geographic artificial intelligence (GeoAI) agents can transform public geospatial data into accessible decision support for real-world challenges, but must balan…
- arXiv cs.AIresearchGroup Relative Policy Optimisation Improves Multilingual Speech Recognition in Low-Resource Languages
arXiv:2610.30663v1 Announce Type: new Abstract: Autoregressive encoder-decoder speech recognition models trained with teacher forcing can suffer from exposure bias, limiting their ability to recover from their own predic…
- arXiv cs.AIresearchScaling Laws for Safety Probes
arXiv:2610.30678v2 Announce Type: replace Abstract: Safety probes trained on a model's activations are a standard tool for monitoring language models in real time. Each time a new model is released or a new harm area nee…
- arXiv cs.AIresearchDisentangling Robustness and Sycophancy in Multilingual LLMs
arXiv:2610.30696v1 Announce Type: new Abstract: When a multilingual LLM agrees with a user's false premise, is it being sycophantic, or does it simply not know better in that language? Current research does not distingui…
- arXiv cs.AIagentsGovernance-State Corruption in Long-Term Memory for LLM Agents: A Cross-Model Stress Test
arXiv:2610.30698v1 Announce Type: new Abstract: An LLM agent can retrieve a memory correctly yet use it incorrectly after its validity state changes. We study governance-state corruption: faults that alter which retained…
- arXiv cs.AIresearchFaithful Latent Harm Monitors Work No Better Than the Models Own Behaviour at a Matched False Alarm Rate
arXiv:2610.30727v1 Announce Type: new Abstract: Large language models have been reported to encode the harmfulness of a request separately from their decision to refuse it, and latent safety monitors such as Latent Guard…
- arXiv cs.AIagentsAgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes
arXiv:2610.30738v1 Announce Type: new Abstract: When tool-use agents write files, execute code, or send data, their final responses do not explain the resulting security events, and heterogeneous runtimes expose the rele…
- arXiv cs.AIresearchHow Firm Are AI Models' Ethical Boundaries? A Pay-Stub Editing Test of 15 Models
arXiv:2610.30751v2 Announce Type: replace Abstract: Can a small change in wording move an AI model from refusing a sensitive request to acting on it? We test 15 models on the same request to increase the income shown on…
- arXiv cs.AIagentsIs Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
arXiv:2610.30755v1 Announce Type: new Abstract: LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or othe…
- arXiv cs.AIresearchCan Loan Processors and Underwriters Spot AI-Edited Statements? An Empirical Study
arXiv:2610.30758v2 Announce Type: replace Abstract: AI-assisted editing can produce loan documents that preserve familiar issuer layouts while changing the applicant's identity. We investigated whether experienced underw…
- arXiv cs.AIagentsAgentDP: Towards Automated Model Deployment for Heterogeneous Embedded AI Applications
arXiv:2610.30760v1 Announce Type: new Abstract: This paper presents AgentDP, which aims to deploy pre-trained AI models on heterogeneous embedded devices by fully automating model optimization and adaptation (O&A) with L…
- arXiv cs.AIresearchScaling Laws for Generative Reward Models
arXiv:2610.30765v1 Announce Type: new Abstract: We study generative reward models (GenRMs) as online preference providers for policy optimization in creative writing. Across Qwen3 reward-model sizes from 0.6B to 14B, Thi…
- arXiv cs.AIagentsLLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades
arXiv:2610.30769v1 Announce Type: new Abstract: Large language models (LLMs) increasingly operate in multi-agent systems where they collaborate by responding to others' choices, creating endogenous feedback loops with vu…
- arXiv cs.AIresearchProQuant: Preserving Expert Quality over Quantity in Ultra-Low-Bit Quantization of Mixture-of-Experts Models
arXiv:2610.30779v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) large language models reduce computation through sparse activation but still incur substantial storage costs. Mixed-precision post-training quantiz…
- arXiv cs.AIagentsAn Introduction to World Models for Generalist Agents
arXiv:2610.30789v1 Announce Type: new Abstract: World models have recently emerged as a promising direction toward developing generalist agents capable of understanding, predicting, and interacting with diverse environme…
- arXiv cs.AIagentsAgentic Knowledge-Model Co-Evolution via Consistency Regularization
arXiv:2610.30790v1 Announce Type: new Abstract: LLM agents can evolve by learning from accumulated experience. Existing approaches extract reusable external knowledge, such as skills and memories, from experience to guid…
- arXiv cs.AIresearchWhat Lies Beyond Perception: A Partition Theory of the Limits of AI Evaluation and Oversight
arXiv:2610.30803v1 Announce Type: new Abstract: Replacing the judge can move a benchmark score, and models can be trained to hide capabilities. Both put the evaluator in question: what can it certify? We develop a partit…
- arXiv cs.AIresearchTESSA: A Governance-Oriented Custom GPT for SME Guidance under the EU AI Act: Design, Implementation, and Evaluation
arXiv:2610.30822v1 Announce Type: new Abstract: The increasing adoption of generative AI presents new opportunities while raising AI governance and regulatory challenges, particularly for small and medium-sized enterpris…
- arXiv cs.AIresearchSemi-Linear Gaussian Bayesian Networks: Enhancing Flexibility in Node Dependencies via penalized B-Splines
arXiv:2610.30838v1 Announce Type: new Abstract: Bayesian networks for continuous variables often rely on restrictive assumptions: linear Gaussian models lack flexibility to capture nonlinear dependencies, while non-param…
- arXiv cs.AIagentsADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization
arXiv:2610.30851v1 Announce Type: new Abstract: Scientific discovery often requires identifying a small number of high-performing designs in vast, constrained search spaces. This is difficult when evaluations are costly,…
- arXiv cs.AIresearchParameter Learning in Active Inference via Variational Message Passing
arXiv:2610.30899v1 Announce Type: new Abstract: Active inference casts perception, learning and planning as variational inference, where the Expected Free Energy (EFE) defines the planning objective. Recent work showed t…
- arXiv cs.AIresearchBeyond Phenotypic Similarity: Relation Refinement and Selective Population Graph Learning for Multimodal Brain Disorder Diagnosis
arXiv:2610.30902v1 Announce Type: new Abstract: Population graph learning supports brain disorder diagnosis by sharing information across subjects. Its effectiveness, however, depends on whether the relationships guiding…
- arXiv cs.AIresearchTwinStore: A Synthetic Consumer Platform Using Vision--Language Models
arXiv:2610.30909v1 Announce Type: new Abstract: We present TwinStore, a source-available synthetic consumer platform for physical retail built on vision--language models. TwinStore turns a store into a digital twin---fro…
- arXiv cs.AIagentsHarnessing Language Models as Optimization Modeling Agents
arXiv:2610.30917v1 Announce Type: new Abstract: Large language models (LLMs) can translate natural-language optimization problems into solver programs, but reliably producing correct formulations and implementations rema…
- arXiv cs.AIresearchDConstrain: Compiling Context-Parameterized Transitions for Diffusion Language Model Constrained Decoding
arXiv:2610.30920v1 Announce Type: new Abstract: Diffusion language models (DLMs) decode multiple tokens in parallel, so individually valid tokens can be incompatible together under a schema. Exact joint inference over a…
- arXiv cs.AIresearchThe Geometry of Meaning in Neural Manifolds
arXiv:2610.30938v1 Announce Type: new Abstract: Just as different languages express the same concept through different words, neural networks express similar functions through incompatible coordinate systems. Different a…
- arXiv cs.AIresearchMeasuring the Reasoning-Action Coupling in Driving Vision-Language-Action Models through Counterfactuals
arXiv:2610.30953v1 Announce Type: new Abstract: Driving vision-language-action (VLA) models bring an appealing form of explainability to a safety-critical domain, since a system that can state the reasons for its maneuve…