Search: “llm”

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:2511.11182v2 Announce Type: replace Abstract: Hallucination continues to pose a major obstacle in the reasoning capabilities of large language models (LLMs). Although the Multi-Agent Debate (MAD

arXiv:2610.14443v1 Announce Type: cross Abstract: Model cards, system cards, and safety reports increasingly document LLM safety behaviors, yet safety evaluations typically start from predefined bench

arXiv:2601.07239v2 Announce Type: replace Abstract: Deterministic inference is a comforting ideal in classical software: the same program on the same input should always produce the same output. As la

arXiv:2610.16661v1 Announce Type: new Abstract: An LLM agent using tools can fail silently. It stops before the task is done, raises no error, and answers fluently. Two kinds of monitor address this,

arXiv:2610.13105v1 Announce Type: new Abstract: Failure attribution for LLM agents aims to identify decisive steps responsible for task failure, which is critical for debugging and improving agentic s

arXiv:2610.12667v1 Announce Type: new Abstract: Large language model (LLM) evaluations on clean benchmarks overstate model robustness: real inputs arrive perturbed, and these meaning-preserving varian

arXiv:2610.13416v1 Announce Type: new Abstract: Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effec

arXiv:2610.10199v1 Announce Type: new Abstract: Emerging legislation requires large language models (LLMs) to be audited for compliance with regulatory standards, particularly fairness. Such black-box

arXiv:2610.07311v1 Announce Type: new Abstract: Agentic memory allows LLM agents to reuse past experience, yet retrieved memories can also distort inference even when they are benign, correctly stored

arXiv:2610.05303v1 Announce Type: new Abstract: A large language model (LLM) agent solves long-horizon tasks through many reasoning-action turns, with one verification signal at termination. Deployed

arXiv:2610.02351v1 Announce Type: new Abstract: ReAct-based agents typically rely on a single LLM policy to propose actions, interact with the environment, and decide when a task is complete. This cou

arXiv:2610.03480v1 Announce Type: new Abstract: Post-training a large language model (LLM) often requires exploring trade-offs between multiple rewards, but retraining for each trade-off is expensive.

arXiv:2610.03432v1 Announce Type: cross Abstract: Online data selection has demonstrated substantial efficiency gains for LLM pretraining by training on the most valuable candidates within each batch.

arXiv:2610.03356v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly deployed in high-stakes settings such as industrial maintenance and equipment fault troubleshooting,

arXiv:2610.00979v1 Announce Type: new Abstract: Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing

arXiv:2610.00704v1 Announce Type: new Abstract: Natural-language skills are textual procedural memories through which large language model (LLM) agents retain reusable task knowledge without updating

arXiv:2609.38954v1 Announce Type: cross Abstract: Large language model (LLM) agents could help security operations centers (SOCs) investigate advanced persistent threats (APTs) by turning weak leads i

arXiv:2609.38291v1 Announce Type: cross Abstract: Large language model (LLM) agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtime

arXiv:2609.39727v1 Announce Type: new Abstract: Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet

arXiv:2609.39549v1 Announce Type: cross Abstract: As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant secur

arXiv:2609.36116v1 Announce Type: new Abstract: We study how to build more capable general-purpose agents by extending large language models (LLMs) with native typed decision-making. We introduce Dyad

arXiv:2508.14925v2 Announce Type: replace-cross Abstract: By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a c

arXiv:2609.31140v1 Announce Type: new Abstract: Most Vision-Language Models (VLMs) are built by extending pretrained Large Language Models (LLMs) with visual modules and multimodal alignment. However,

arXiv:2609.30784v1 Announce Type: cross Abstract: This paper proposes an architecture for equipping large language models (LLMs) with audio-understanding capabilities without fine-tuning their weights

arXiv:2609.27355v1 Announce Type: cross Abstract: Unlearning ensures LLM compliance by removing the influence of private or copyrighted training data. However, since LLM models typically undergo post-

arXiv:2609.21676v1 Announce Type: cross Abstract: We present the Spoken Wikipedia Presentation Corpus, an extension of the Spoken Wikipedia Corpora featuring LLM-generated slide decks for multimodal A

arXiv:2609.19947v1 Announce Type: new Abstract: LLM-based AI agents process user requests through iterative reasoning and tool execution, often involving the invocation of remote LLM APIs with local t

arXiv:2609.18417v1 Announce Type: new Abstract: Multi-turn agent trajectories often contain redundant rounds (failed tool calls, parallel sub-queries, verification-only steps) that inflate both traini

arXiv:2609.17863v1 Announce Type: new Abstract: LLM inference optimizations report speedups on different models, GPUs, prompts, and quality metrics, making them hard to compare or combine. We build a

arXiv:2609.18282v1 Announce Type: new Abstract: Large language models are increasingly used to generate and evaluate online content, yet it remains unclear whether the qualities they associate with hi

arXiv:2609.17306v1 Announce Type: cross Abstract: Multi-agent Systems (MAS) combine multiple model outputs to solve complex reasoning tasks. However, despite rapid growth of available open-source mode

arXiv:2609.16627v1 Announce Type: new Abstract: Quantifying organizational environmental action from publicly available web content remains a challenging environmental data science problem because rel

arXiv:2609.17331v1 Announce Type: new Abstract: Large language model (LLM) agents exhibit strong language-generation and problem-solving capabilities, yet suffer from three structural limitations: per

arXiv:2609.15559v1 Announce Type: cross Abstract: Grammatical error correction (GEC) evaluation has traditionally relied on reference or edit overlap, which can penalize valid rewrites that differ fro

arXiv:2609.13692v1 Announce Type: cross Abstract: LLM serving reuses KV cache by exact prefix match, so when a prompt is assembled from a set of reusable pieces -- retrieved passages, tool definitions

arXiv:2609.11709v1 Announce Type: new Abstract: When multiple LLM agents yield conflicting answers, the decision-making process dictates whether agent diversity improves performance or merely compound

arXiv:2609.11314v1 Announce Type: new Abstract: Traffic flow prediction is a core supporting technology for intelligent transportation systems. It uses historical data to infer future traffic dynamics

arXiv:2609.09458v1 Announce Type: new Abstract: As LLM agents move from answering questions to carrying out procedures, failures can be unwarranted rather than visibly wrong: the final response looks

arXiv:2601.12723v3 Announce Type: replace-cross Abstract: Optimization benchmarks play a fundamental role in assessing algorithm performance; however, existing artificial benchmarks often fail to capt

arXiv:2609.08832v1 Announce Type: new Abstract: Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a discrepancy that has been observed but remains larg

arXiv:2609.04445v1 Announce Type: cross Abstract: A conformal certificate can be valid when an LLM answers alone and invalid when the same LLM sees peers that unanimously assert a wrong answer. The qu

arXiv:2609.03148v1 Announce Type: new Abstract: Most prior works focused on conflicts between an LLM's internal parametric knowledge and externally provided context. In contrast, we investigate how LL

arXiv:2609.02940v1 Announce Type: cross Abstract: Recent automatic speech recognition (ASR) systems increasingly integrate large language models (LLMs) to leverage their semantic knowledge, either ext

arXiv:2609.04047v1 Announce Type: cross Abstract: Background: Researchers increasingly use repeated identical prompts to audit stochastic variation in large language model (LLM) brand recommendations,

arXiv:2609.01836v1 Announce Type: cross Abstract: Long-running LLM agents rely on persistent memory to carry state across interactions, including permissions, restrictions, and revocations. When memor