Knowledge catalogue
arXiv:2609.17474v1 Announce Type: cross Abstract: Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can a
arXiv:2609.16161v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown impressive capabilities across a range of natural language processing tasks, and LLM inference has emerged as a
arXiv:2607.09493v2 Announce Type: replace Abstract: Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the
arXiv:2609.16532v1 Announce Type: new Abstract: Continued pretraining (CPT) with data augmentation such as paraphrasing can store inside a large language model (LLM) the knowledge of a small source co
arXiv:2609.14839v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into automated code optimization introduces a critical reliability risk we term the Efficiency Halluci
arXiv:2609.14767v1 Announce Type: cross Abstract: Hierarchical orchestration, in which a Manager agent reviews worker output and can send it back for revision, is the default coordination pattern in p
arXiv:2609.14237v1 Announce Type: cross Abstract: LLM serving systems increasingly disaggregate inference into finer-grained stages, with recent approaches separating attention from FFN or MoE executi
arXiv:2609.14780v1 Announce Type: cross Abstract: Multi-tenant tools commonly accept a tenant identifier and validate it against the caller's entitlement. For a large language model (LLM) agent, that
arXiv:2609.13422v1 Announce Type: new Abstract: LLM judges are increasingly used to evaluate and improve AI-generated outputs, yet their reliability for complex professional work remains unclear. We s
arXiv:2604.05793v2 Announce Type: replace-cross Abstract: In LLM agent pipelines, prompt privacy risk propagates beyond a single model call: raw user content enters retrieval queries, memory writes, t
arXiv:2609.12923v1 Announce Type: cross Abstract: A single SM utilization percentage can make an LLM inference workload look compute-saturated while hiding how much useful work is being done. The prob
arXiv:2609.10964v1 Announce Type: new Abstract: Agentic LLM workflows consist of sequences of model turns interleaved with tool interactions, so their end-to-end completion time depends not only on in
arXiv:2609.11109v1 Announce Type: cross Abstract: The utility of AI in multi-coder qualitative coding has been widely discussed, yet little empirical evidence exists to delineate the contexts in which
arXiv:2606.19468v2 Announce Type: replace Abstract: The narrative composition of web-scale LLM pretraining corpora remains largely unexplored, even though narrative is a fundamental mode of human comm
arXiv:2609.10896v1 Announce Type: new Abstract: Speech-based automatic detection of Alzheimer's disease (AD) provides a non-invasive and scalable approach to early cognitive screening. AD affects both
arXiv:2609.10135v1 Announce Type: cross Abstract: To address insufficient contextualization, weak generalization, and poor scenario adaptation in tourism meteorological services, we propose SmartWeath
arXiv:2609.06783v1 Announce Type: cross Abstract: LLM agents operate in workflows where unsafe actions can have real consequences. Existing safety evaluations often reduce behavior to a single score,
arXiv:2609.05976v1 Announce Type: cross Abstract: Large Language Model (LLM) unlearning aims to suppress target knowledge while preserving general capabilities. In multilingual settings, unlearning mu
arXiv:2609.07379v1 Announce Type: cross Abstract: Large language models (LLMs) have recently shown promise for historical entity linking, but preference optimization for this task is often formulated
arXiv:2609.05824v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external skills, but routing user requests over large skill registries is difficult because many
arXiv:2609.06853v1 Announce Type: cross Abstract: Shared key--value (KV) cache reuse improves large language model (LLM) serving, but it can also create a timing side channel that reveals whether a pr
arXiv:2609.06674v1 Announce Type: cross Abstract: We present a new attack that reconstructs the text generated by locally hosted LLMs by observing CPU cache activity during detokenization. Unlike prio
arXiv:2609.09883v1 Announce Type: new Abstract: Depth pruning reduces large language model (LLM) inference cost by removing complete Transformer blocks. Activation-based methods collect hidden states
arXiv:2609.05901v1 Announce Type: cross Abstract: Autonomous LLM agents can turn untrusted content into effectful actions such as payments and permission changes. If the same process interprets this c
arXiv:2609.09835v1 Announce Type: new Abstract: Personalized language models aim to adapt responses to individual users, whose preferences are often latent and revealed gradually through interaction.
arXiv:2609.05774v1 Announce Type: new Abstract: Recent multi-agent LLM systems increasingly rely on graph-structured communication to coordinate specialized agents. We revisit multi-agent orchestratio
arXiv:2609.08772v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being investigated for physiological time-series prediction, yet their effectiveness may depend not only o
arXiv:2609.08288v1 Announce Type: new Abstract: Travel survey data are essential for transportation planning and travel behavior analysis, yet collecting large-scale representative samples is costly a
arXiv:2601.17036v2 Announce Type: replace-cross Abstract: ArXiv recently prohibited the upload of unpublished review papers to its servers in the Computer Science domain, citing a high prevalence of L
arXiv:2602.00276v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities on math and coding, but frequently fail on symbolic classical planning
arXiv:2609.09090v1 Announce Type: cross Abstract: Large language models (LLMs) may abandon correct positions when users push back, exhibiting a failure mode known as sycophancy. Existing evaluations t
arXiv:2503.08051v2 Announce Type: replace Abstract: In the era of generative AI, recommender systems are moving from precise prediction to trustworthy generation. Large language models (LLMs) support
arXiv:2609.08558v1 Announce Type: new Abstract: Personalized memory helps LLM agents deliver stable, tailored assistance by storing and reusing user-specific data across interactions. In multi-user sc
arXiv:2609.07290v1 Announce Type: cross Abstract: The rapid digital transformation of manufacturing, often referred to as Industry 4.0, relies on seamless interoperability between physical and softwar
arXiv:2603.18074v2 Announce Type: replace Abstract: Technical-service LLM agents are entering production workflows, where value depends on whether engineers adopt generated replies. Service tickets hi
arXiv:2609.06972v1 Announce Type: cross Abstract: LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection
arXiv:2603.00039v2 Announce Type: replace Abstract: LLM-as-a-judge ensembles are the standard paradigm for scalable evaluation, but their aggregation mechanisms suffer from a fundamental flaw: they im
arXiv:2606.19376v2 Announce Type: replace Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expe
arXiv:2609.04667v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly proposed for enterprise workflows, yet existing evaluations rarely test whether business-decision con
arXiv:2609.05093v1 Announce Type: new Abstract: We present Discovery Loop, a lightweight system that uses a large language model (LLM) to iteratively evolve optimization algorithms. Starting from a si
arXiv:2609.05117v1 Announce Type: cross Abstract: Current LLM safety benchmarks largely rely on binary metrics, overlooking how models respond to harmful prompts with varying threat implicitness. We i
arXiv:2609.03151v1 Announce Type: cross Abstract: Long-context reasoning for large language models (LLMs) is becoming increasingly important, but training over long sequences remains challenging due t
arXiv:2609.03340v1 Announce Type: new Abstract: Distributed LLM-agent teams can read the latest shared facts and still act on an obsolete plan. A planner may derive an action from requirement r_3, ano
arXiv:2609.03350v1 Announce Type: cross Abstract: Pretraining data for Armenian, a morphologically rich and low-resource language, is scarce, and no open Armenian LLM has been released with the data a
arXiv:2609.02931v1 Announce Type: cross Abstract: Scripted and rule-based non-player characters (NPCs) in combat video games often exhibit predictable behaviors that experienced players can exploit, w
arXiv:2609.03160v1 Announce Type: new Abstract: Nastase et al. (2026) argue that large language models (LLMs) may illuminate language processing because both rely on distributed, context-sensitive rep
arXiv:2609.02967v1 Announce Type: cross Abstract: Topology-guided safeguards for LLM-based multi-agent systems (MAS) train a GNN over the inter-agent communication graph to localize risky agents and i
Brilliant paper on long-horizon agents. They cut 78.9% of an agent's LLM calls while raising its success rate. Here is how: It turns out that ReAct issues one primitive action per model round. That al
arXiv:2609.02379v1 Announce Type: cross Abstract: While existing work on LLM authorship attribution (AA) has made progress, available benchmarks remain limited, often focusing on English, controlled s
arXiv:2609.00052v1 Announce Type: cross Abstract: Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to
arXiv:2609.00267v1 Announce Type: cross Abstract: Autonomous LLM agents increasingly act on a user's behalf: they hold credentials, call tools and services, and spawn sub-agents that act further on th
arXiv:2609.00227v1 Announce Type: cross Abstract: LLM agents increasingly diagnose incidents and propose remediations. In a GitOps workflow, applying a fix means editing a version-controlled config fi
arXiv:2609.01572v1 Announce Type: new Abstract: Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer models without decommissioning their predecessors expan
arXiv:2609.00237v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems tackle complex reasoning by orchestrating how multiple agents are configured and how they collabora
arXiv:2609.00549v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly rely on external skills, yet standard evaluations obscure whether retrieving these skills actually helps.
arXiv:2609.00595v1 Announce Type: cross Abstract: Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating f
arXiv:2609.00728v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown remarkable promise in translating and reformulating complex mathematical optimization problems across modeling l
arXiv:2609.00519v1 Announce Type: cross Abstract: Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control perfo
arXiv:2608.28646v1 Announce Type: new Abstract: Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic KYC-style constraints on risk, fees, and dive
arXiv:2608.28986v1 Announce Type: new Abstract: LLMs often struggle with modern Korean poetry, producing outputs that resemble 'line-broken prose.' We address two coupled tasks: detecting whether a Ko