Knowledge catalogue
arXiv:2606.23403v2 Announce Type: replace Abstract: As agentic LLM systems move from prototypes to deployment, evaluating them has become more important and more difficult. Evaluation goals are often
arXiv:2609.32717v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) alignment is intended to ensure that models remain helpful and safe, but its stability under input distributional s
arXiv:2610.20155v1 Announce Type: cross Abstract: Banks rely on extensive internal policy frameworks to ensure that corporate lending decisions comply with regulatory requirements and internal risk st
arXiv:2610.19331v1 Announce Type: new Abstract: This paper presents LLM-jp-4, a family of Japanese sovereign large language models (LLMs) developed with an emphasis on transparency, reproducibility, a
arXiv:2308.12241v2 Announce Type: replace-cross Abstract: Recently, the fast development of Large Language Models (LLMs) such as ChatGPT has significantly advanced NLP tasks by enhancing the capabilit
arXiv:2610.19238v1 Announce Type: new Abstract: When writing code, the same computation can be expressed in different programming languages and through different implementation strategies. We show tha
arXiv:2604.00477v2 Announce Type: replace Abstract: LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their assessmen
arXiv:2610.16790v1 Announce Type: cross Abstract: Language model APIs can expose token-specific biases while withholding logits and token probabilities. Existing bias-based extraction recovers relativ
arXiv:2610.20256v1 Announce Type: new Abstract: Long-horizon agents must coordinate reasoning, tool use, and environment feedback over extended interactions. Learning from sparse outcome rewards requi
arXiv:2610.14146v1 Announce Type: new Abstract: Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its fin
arXiv:2607.08964v3 Announce Type: replace Abstract: AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple
arXiv:2610.19257v1 Announce Type: new Abstract: Memory for long-horizon video generation must satisfy two competing requirements: it must remain bounded so generation can continue indefinitely, while
arXiv:2512.22814v2 Announce Type: replace Abstract: Accurate long-range weather forecasting remains a major challenge for AI models, both because errors accumulate over autoregressive rollouts and bec
arXiv:2610.20384v1 Announce Type: new Abstract: Agents for mixed-degradation image restoration typically learn what a tool does to an image only after running it: failed calls waste computation and ha
arXiv:2608.28281v2 Announce Type: replace Abstract: Loop Engineering is emerging as a practice for organizing development work around coding agents. Instead of writing each prompt by hand, practitione
arXiv:2603.19714v2 Announce Type: replace Abstract: Looped language models (LoopLMs) perform iterative latent computation to refine internal representations, offering an alternative to explicit chain-
arXiv:2610.14071v1 Announce Type: cross Abstract: As LLM agents are increasingly deployed in high-stakes enterprise settings, understanding how they handle sensitive information in agentic dialogue ha
arXiv:2610.19042v1 Announce Type: new Abstract: Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we
arXiv:2610.18522v1 Announce Type: new Abstract: Reusable skills let LLM agents load task-specific instructions on demand, but they make execution depend on implicit routing over skill metadata. We tes
arXiv:2610.20479v1 Announce Type: new Abstract: Bias audits of multilingual language models usually compare a model's average stereotype score in English with its average in another language and read
arXiv:2610.18877v1 Announce Type: cross Abstract: Time-series language models typically align numerical signals with language using labels, captions, or question-answer pairs. Although such supervisio
arXiv:2610.15908v1 Announce Type: new Abstract: Phase-annotated conversational data is essential for studying the progression of online grooming of minors and for developing early warning tools. Howev
arXiv:2610.14777v1 Announce Type: new Abstract: LLM-powered data analytics aims to translate natural language instructions into executable analytical programs over underlying data. However, existing a
arXiv:2610.19138v1 Announce Type: cross Abstract: How well can a language model turn a large, incomplete and partly contradictory body of documents into a plan when no single correct answer exists? We
arXiv:2610.16975v1 Announce Type: new Abstract: Drug discovery remains a resource-intensive and time-consuming process, involving billions of dollars and a decade of development to advance a drug to m
arXiv:2610.20238v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) excel on graph-structured data but suffer catastrophic forgetting when classes arrive sequentially. In class-incremental gr
arXiv:2610.19623v1 Announce Type: new Abstract: Single-image 3D reconstruction has advanced rapidly, yet standalone garments remain challenging due to thin-shell geometry, open boundaries, and layered
arXiv:2610.16552v1 Announce Type: new Abstract: An ordered visual code lets a short prefix stand in for an image, and the training loss decides what that prefix contains. Under pixel reconstruction th
arXiv:2610.19735v1 Announce Type: new Abstract: Scenario-based validation is essential for automated road vehicles but cannot cover the full variability of openworld traffic. We present MakSafe, a for
arXiv:2610.20570v1 Announce Type: new Abstract: Brazilian Portuguese remains underserved by open-source language models, and the few that are safety-aligned rarely document what did not work or valida
arXiv:2610.17544v1 Announce Type: cross Abstract: Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted mem
arXiv:2610.19827v1 Announce Type: cross Abstract: LLMs absorb vast knowledge from training data, yet their inherently probabilistic nature offers no guarantee that this knowledge will surface in their
arXiv:2610.19647v1 Announce Type: new Abstract: Accurately delineating Arctic coastal polynyas from sea ice concentration data remains challenging because of complex coastal geometry and spatially het
arXiv:2603.00720v2 Announce Type: replace Abstract: Fine-tuning Multimodal Large Language Models (MLLMs) with parameter-efficient methods like Low-Rank Adaptation (LoRA) is crucial for task adaptation
arXiv:2610.17613v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems (MAS) can solve complex problems beyond the reach of a single agent by decomposing tasks and coordi
arXiv:2601.22050v2 Announce Type: replace Abstract: In recent years, multilingual Large Language Models (LLMs) have become an inseparable part of daily life, making it crucial for them to master the r
arXiv:2603.18965v2 Announce Type: replace Abstract: Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by pro
arXiv:2610.19679v1 Announce Type: cross Abstract: Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in completing complex tasks through multi-step reasoning and tool in
arXiv:2610.14956v1 Announce Type: new Abstract: The Model Context Protocol provides a shared interaction substrate for the agentic web, allowing heterogeneous services to expose capabilities through a
arXiv:2610.19659v1 Announce Type: new Abstract: People delegate multi-step work to LLM agents and read only the reply that the agent hands back. Current evaluation scores task completion and the faith
arXiv:2509.09658v3 Announce Type: replace Abstract: Hallucinations in multimodal large language models (MLLMs), where a model generates content inconsistent with the input image, pose significant risk
arXiv:2610.14389v1 Announce Type: new Abstract: Benchmark scores tell us what an LLM can do, but not how much energy is required to deliver that capability. We directly measure this trade-off for 86 o
arXiv:2601.02978v3 Announce Type: replace-cross Abstract: Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models
arXiv:2610.15714v1 Announce Type: new Abstract: Healthcare agents must transform longitudinal clinical evidence into reliable actions through heterogeneous tools and stateful workflows, conditions und
arXiv:2610.19928v1 Announce Type: new Abstract: Reasoning over infinitely long documents is becoming a reality with recurrent memory agents. However, increasing context length exacerbates the trade-of
arXiv:2610.15463v1 Announce Type: new Abstract: With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly con
arXiv:2610.19267v1 Announce Type: cross Abstract: Online memes are often carriers of unsafe content such as disinformation and propaganda. Their rapid evolution in response to news events and strong d
arXiv:2610.17763v1 Announce Type: new Abstract: Long-term memory supports agents across sessions. Repeated retrieval and write-back can let one historical claim occupy multiple retrieval positions and
arXiv:2610.16298v1 Announce Type: new Abstract: Training neural networks in reduced precision can yield significant efficiency gains, yet all existing methods that scale to standard computer vision be
arXiv:2610.19844v1 Announce Type: new Abstract: Memory-efficient subspace optimization has emerged as a practical approach to reducing the memory cost of LLM training while preserving optimization per
arXiv:2610.14727v1 Announce Type: new Abstract: Autoregressive world models have emerged as a powerful paradigm for sample efficient decision making, yet their open loop rollouts often exhibit increas
arXiv:2610.19681v1 Announce Type: new Abstract: Accurate 3D reconstruction in real-world environments remains a significant challenge due to the coexistence of reflective and non-reflective surfaces,
arXiv:2610.19262v1 Announce Type: new Abstract: Robots following persistent language instructions must decide which cached room judgments remain valid as their environment changes. We present MIND (Ma
arXiv:2607.28103v2 Announce Type: replace Abstract: Memory-augmented LLM-based agents are vulnerable to memory injection attacks: Agents may retrieve poisoned memory from attackers, which diverts thei
arXiv:2610.20007v1 Announce Type: cross Abstract: We study the minimax estimation of the pseudo-spectral gap gamma_{ps} of a Markov chain from the observation of a single trajectory. Extending earlier
arXiv:2610.19457v1 Announce Type: new Abstract: Expected-reward maximization in reinforcement learning concentrates probability mass on a few outcomes, even in tasks that require many distinct, high-q
arXiv:2610.12568v2 Announce Type: replace Abstract: Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajecto
arXiv:2606.16710v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) are credited with solving complex problems, yet their agents routinely act on context that may be false. Prior work
arXiv:2610.18141v1 Announce Type: new Abstract: Omnimodal large language models (OLLMs) are susceptible to cross-modal hallucinations under audio-visual interference. We find that, for a substantial f
arXiv:2610.19728v1 Announce Type: cross Abstract: Video large language models (Video LLMs) often generate responses unsupported by the input video. Contrastive decoding (CD) can mitigate these halluci