Search: “llm”

arXiv:2610.22314v1 Announce Type: new Abstract: With people increasingly turning to AI chatbots for mental health support, the need to evaluate these tools is becoming more pressing. Recent benchmarks

arXiv:2610.22344v1 Announce Type: new Abstract: Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advan

arXiv:2610.22086v1 Announce Type: cross Abstract: Supervised fine-tuning datasets remain overwhelmingly English-centric and commercially restricted, as their content is frequently generated by proprie

arXiv:2603.26107v1 Announce Type: cross Abstract: People increasingly use multiple Multimodal Large Language Models (MLLMs) concurrently, selecting each based on its perceived strengths. This cross-pl

arXiv:2610.22019v1 Announce Type: cross Abstract: Frontier models, general-purpose and domain-specific alike, now include a midtraining stage between pretraining and post-training, but little has been

arXiv:2610.21220v1 Announce Type: cross Abstract: Recommender systems often need to balance multiple conflicting objectives. Controllable Multi-Objective Recommendation (CMOR) enables dynamic adjustme

arXiv:2610.20763v1 Announce Type: cross Abstract: Full-duplex spoken language models decide at every frame whether to take the floor, defining a conversational personality -- yet each set of weights e

arXiv:2610.21539v1 Announce Type: new Abstract: Diffusion models (DMs) have steadily demonstrated outstanding performance in high-fidelity, controllable generation across diverse scenarios, following

arXiv:2610.22243v1 Announce Type: new Abstract: AI agents take actions through tools. Some actions are sensitive, so guards that supervise them must themselves be evaluated reliably. Yet the data used

arXiv:2610.21440v1 Announce Type: new Abstract: In automatic speech recognition (ASR), transcription errors with similar lexical or semantic discrepancies can have markedly different consequences for

arXiv:2610.21244v1 Announce Type: cross Abstract: Large language models (LLMs) often make discrete decisions, such as flagging phishing or escalating to a human. System-1 models, such as Jev and the O

arXiv:2610.21646v1 Announce Type: new Abstract: With the rise of large language models, agentic systems are becoming increasingly autonomous, as they write code, call tools, revise prompts, and propos

arXiv:2610.21098v1 Announce Type: cross Abstract: The success score of a tool agent reflects both its model and the budgets of the harness that runs it. We present ToolBottleneckBench, a benchmark tha

arXiv:2610.20778v1 Announce Type: cross Abstract: Automating organizational work means answering many small typed questions about one piece of state (does this email need a reply, how urgent is it, wh

arXiv:2610.20003v2 Announce Type: replace Abstract: Human supervisors rely on coding agents' reports to assess progress, verify repairs, and decide when to intervene. But a supervisor cannot investiga

arXiv:2610.20898v1 Announce Type: cross Abstract: Reinforcement learning with self-generated labels, such as majority vote over a model's own samples, often recovers most of the gain of training with

5/5 Across the board, results show the business impact and differentiation of sovereign specialized intelligence, and the opportunity for companies to reach AI independence. Thanks to @nvidia, @Gong_i

arXiv:2603.06135v3 Announce Type: replace-cross Abstract: Distinguishing legitimate critical speech from coordinated conspiracy narratives is a pressing challenge for the integrity of the online infor

arXiv:2503.14555v2 Announce Type: replace-cross Abstract: Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these

arXiv:2610.15371v1 Announce Type: cross Abstract: Gnani-Evon-v3.3-30B-A3B is a long-context hybrid Mamba-Transformer mixture-of-experts model for reasoning, instruction following, and tool use in Engl

arXiv:2610.19999v1 Announce Type: new Abstract: Legal-content reproduction requires matching the source exactly in section hierarchy, verbatim text, citations, and amendment spans; a dropped citation

arXiv:2610.20086v1 Announce Type: new Abstract: Synthetic data is increasingly used in language-model pretraining. Existing knowledge-corpus synthesis pipelines, including WRAP and Nemotron-CC, usuall

arXiv:2610.17410v1 Announce Type: new Abstract: Advances in large-scale machine learning have enabled agentic AI systems: persistent, autonomous computational entities that pursue goals, initiate acti

arXiv:2610.19478v1 Announce Type: new Abstract: Agricultural systems make decisions over heterogeneous entity types, textual judgments, and knowledge-question options. Generating a textual answer adds

arXiv:2610.17110v1 Announce Type: cross Abstract: AI-assisted research leaves instructions, computations, artifact revisions and checks whose relationships matter when another researcher receives the

arXiv:2610.18090v1 Announce Type: new Abstract: Ambiguous or incomplete task specifications complicate both execution and clarification for language-model agents. Yet agents' responses to these inform

arXiv:2610.20419v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) models have become almost a cornerstone of open-domain question answering tasks; in which the quality of answers ge

arXiv:2610.17827v1 Announce Type: new Abstract: Existing approaches to training and evaluating search agents focus heavily on final-answer quality, largely neglecting how generated answers map back to

arXiv:2610.17641v1 Announce Type: new Abstract: Bias scores in language-model evaluations often conflate what a model prefers with whether it answers at all. We identify this confound in extsc{BBQ}, w

arXiv:2610.19754v1 Announce Type: new Abstract: Biomedical multi-hop reasoning over knowledge graphs requires identifying a semantically valid relation sequence that supports the answer. Existing meth

arXiv:2610.17338v1 Announce Type: new Abstract: Language-model agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation

arXiv:2610.15153v1 Announce Type: new Abstract: We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill. The keep-alive duty is i

arXiv:2610.15239v1 Announce Type: new Abstract: Most benchmarks for large language models in medicine are built from licensing examinations and theoretical questions. The few that draw on real clinica

arXiv:2610.17197v1 Announce Type: cross Abstract: In the age of 'Software 3.0', when a complete program can be rewritten in minutes by an agent, the traditional approach of relying on code as the sole

arXiv:2610.14700v1 Announce Type: new Abstract: Most text-to-SQL benchmarks provide the target database. In a large data catalog, however, choosing the sources is part of the problem: an agent must fi

arXiv:2610.14750v1 Announce Type: new Abstract: Credit assignment in modular financial reinforcement learning is difficult to evaluate because an attributed signal may improve a component loss without

arXiv:2609.34404v2 Announce Type: replace-cross Abstract: Leveraging the strong generative capabilities and stable training dynamics of diffusion models, diffusion-based recommender systems (RSs) have

arXiv:2610.15062v1 Announce Type: new Abstract: Supporting edge Artificial Intelligence (AI) inference as a network service is challenging because current mobile systems can transport tensors but do n

arXiv:2610.20051v1 Announce Type: new Abstract: In recent years, with advances in multimodal interaction technologies and the growing demand for intelligent emotional support, Multimodal Emotional Sup

arXiv:2610.14539v1 Announce Type: new Abstract: Real-world business requests often leave key requirements unstated because frontline practitioners struggle to articulate rules they know from experienc

arXiv:2402.03694v3 Announce Type: replace-cross Abstract: Network traffic analysis in cloud and internet service provider (ISP) networks increasingly relies on machine learning (ML) models, as encrypt

arXiv:2610.19287v1 Announce Type: cross Abstract: Compute cost in automated essay scoring (AES) is usually treated as a technical efficiency issue rather than a measurement design concern. Yet deploym

arXiv:2610.20370v1 Announce Type: new Abstract: Hate speech has become increasingly prevalent on social media, raising concerns about its detection, interpretation, and moderation. Persian, a relative

arXiv:2610.19114v1 Announce Type: new Abstract: Activation steering controls large language models at inference time, but its effectiveness depends on the choice of reference data. We introduce genesi

arXiv:2610.16769v1 Announce Type: new Abstract: Geospatial reasoning links VLMs to real-world action and decision making. Reliable reasoning requires accurate spatial information and effective spatial

arXiv:2610.19043v1 Announce Type: cross Abstract: Because its binary optimization landscape contains exponentially many local optima, MAX-CUT is highly sensitive to initialization. We study Particle P