Knowledge catalogue
arXiv:2607.24555v1 Announce Type: cross Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys
arXiv:2607.22724v1 Announce Type: cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing traject
arXiv:2606.13385v2 Announce Type: replace-cross Abstract: LLM-based web agents are increasingly deployed in real-world settings such as e-commerce, where they interact extensively with untrusted web c
arXiv:2607.21961v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate long-form conversational content such as podcasts from textual sources. While these syste
arXiv:2601.08160v2 Announce Type: replace Abstract: Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. How
arXiv:2603.13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been propo
As an AI community of LLM experts, are we really going to stay silent while US officials make absurd claims to push anti-consumer laws? Not only does the release timeline between Fable and K3 make hig
arXiv:2407.00740v2 Announce Type: replace Abstract: As large language models (LLMs) are widely adopted in real-world applications, it has become critical to ensure LLMs satisfy safety constraints, suc
arXiv:2607.19739v1 Announce Type: cross Abstract: Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive wo
arXiv:2607.19367v1 Announce Type: new Abstract: Calibration is the primary criterion for evaluating LLM confidence, but it is insufficient: it admits trivially incoherent estimators, depends on the ev
arXiv:2607.13594v1 Announce Type: new Abstract: LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a gua
arXiv:2607.13396v1 Announce Type: new Abstract: What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow set-shifting from cognitive psyc
arXiv:2602.11198v2 Announce Type: replace-cross Abstract: Multi-agent frameworks (MAFs) promise to simplify LLM-driven software development, yet no principled metric captures how well AI coding assist
arXiv:2607.13034v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task act
arXiv:2607.12893v1 Announce Type: new Abstract: Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing be
arXiv:2607.12334v1 Announce Type: new Abstract: Retrieval-augmented question answering depends on selecting evidence passages that jointly support answer generation. However, many RAG pipelines rely o
arXiv:2510.00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with external verifiers or reward models that distinguish
arXiv:2607.08690v1 Announce Type: cross Abstract: Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in para
arXiv:2607.08038v1 Announce Type: new Abstract: Diagnostic error is a major threat to patient safety, yet current large language model (LLM) systems often treat diagnosis as a one-shot prediction task
arXiv:2508.11847v4 Announce Type: replace-cross Abstract: We propose a method for evaluating the robustness of widely used LLM ranking systems -- variants of a Bradley--Terry model -- to dropping a wo
Editor’s note: Some of the most interesting questions in AI are being asked by information theoreticians, around how to provide context to an emerging class of AI agents. A few weeks ago, we waded int
arXiv:2607.08057v1 Announce Type: cross Abstract: Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, whic
arXiv:2607.08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context,
arXiv:2606.19042v2 Announce Type: replace-cross Abstract: In vibe coding, an emerging AI-driven paradigm, an LLM generates an entire program from a natural language prompt, but what happens to the var
arXiv:2508.16560v4 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts. A core SAE training
arXiv:2607.04290v1 Announce Type: cross Abstract: Large Language Models (LLMs) are proposed as control interfaces for next-generation networks, but their latency, hallucinations, and lack of control g
arXiv:2607.03228v1 Announce Type: new Abstract: LLM-based agents offer new opportunities for automating business process execution beyond the limits of rule-based systems. However, general-purpose LLM
arXiv:2607.00990v1 Announce Type: cross Abstract: Large language model (LLM)-based software engineering agents are increasingly developed to resolve software issues by generating patches from issue re
arXiv:2607.01223v1 Announce Type: new Abstract: When should an AI system's answer be trusted? Formal proof assistants offer certainty but cannot reach most of the problem distribution; scalar LLM judg
arXiv:2607.01006v1 Announce Type: new Abstract: Large Language Models (LLMs) represent one of the most significant advances in AI and natural language processing in recent years. Still, many pressing
arXiv:2606.31174v1 Announce Type: new Abstract: Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized sub
arXiv:2606.28733v1 Announce Type: new Abstract: LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete user goals. Yet not every goal is
arXiv:2602.11351v2 Announce Type: replace Abstract: Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond
arXiv:2606.13670v2 Announce Type: replace Abstract: Reproducibility in the social and behavioral sciences is typically evaluated by independent researchers who reanalyze the original data to assess wh
arXiv:2604.01193v2 Announce Type: replace Abstract: Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement le
arXiv:2606.27154v1 Announce Type: new Abstract: Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. How
arXiv:2606.25207v1 Announce Type: cross Abstract: Hyperparameter Optimization (HPO) is essential for maximizing machine learning model performance, and its core challenge is sample efficiency: finding
arXiv:2606.25674v1 Announce Type: new Abstract: LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone
arXiv:2606.24667v1 Announce Type: new Abstract: Dense retrieval embedding models are a fundamental component of modern retrieval-based AI systems. Most dense retrievers are trained with contrastive ob
arXiv:2504.17070v3 Announce Type: replace-cross Abstract: Robots need task planning methods to achieve goals that require more than one action. Recently, large pretrained models have demonstrated impr
arXiv:2606.20512v2 Announce Type: replace-cross Abstract: LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test su
arXiv:2606.22402v1 Announce Type: cross Abstract: Large language model (LLM)-based approaches for automated code compliance (ACC) of building regulations are prone to generating incorrect and hallucin
arXiv:2606.11521v1 Announce Type: new Abstract: LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-spec
arXiv:2506.02568v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated substantial efficacy in advancing graph-structured data analysis. Prevailing LLM-based graph methods
arXiv:2501.00745v3 Announce Type: replace-cross Abstract: The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval. However,
arXiv:2601.21218v2 Announce Type: replace Abstract: Large language models (LLMs) are highly capable of answering questions, but they are often unaware of their own knowledge boundary, i.e., knowing wh
arXiv:2606.10457v1 Announce Type: new Abstract: Decision rules that enterprise experts apply tacitly -- in auditing, compliance, and contract review -- can be systematically recovered and improved thr
arXiv:2412.11449v2 Announce Type: replace-cross Abstract: We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representati
arXiv:2606.09118v1 Announce Type: new Abstract: As LLM capabilities advance rapidly, the evaluation methods used to assess them increasingly lag behind. Traditional benchmarks relied on programmatic v
arXiv:2606.07513v1 Announce Type: new Abstract: Humans learn from social life. Simulating this process with LLM-powered agents represents a promising research direction, raising a natural question: wh
arXiv:2603.04982v3 Announce Type: replace-cross Abstract: Can targeted user training unlock the productive potential of generative artificial intelligence in professional settings? We study this quest
arXiv:2509.25397v2 Announce Type: replace-cross Abstract: The proliferation of open large language models (LLMs) is fostering a vibrant ecosystem in artificial intelligence (AI). However, the methods
arXiv:2606.05296v1 Announce Type: cross Abstract: LLM agents operate in two distinct regimes: open-weight agents amenable to reinforcement learning (RL) and black-box agents whose behaviour must be co
arXiv:2606.05901v1 Announce Type: new Abstract: Large language models (LLMs) have fundamentally transformed the landscape of Natural Language Processing. Despite these advances, LLMs and LLM-based sys
arXiv:2606.04599v1 Announce Type: new Abstract: Large language model (LLM) agents have shown promise in automating complex data-analysis workflows, but their reliable deployment remains challenging in
arXiv:2606.04421v1 Announce Type: new Abstract: Many current agentic systems and LLM pipelines correct mistakes by optimizing outcome reward. This addresses only the what of failure: when an outcome d
arXiv:2606.02982v1 Announce Type: cross Abstract: The rapid growth of large language model (LLM) inference services has increased the demand for efficient multi-tenant GPU scheduling. While modern inf
arXiv:2606.03467v1 Announce Type: new Abstract: LLM-based multi-agent systems exhibit remarkable collaborative capabilities in complex multi-step tasks. However, these systems are highly sensitive to
arXiv:2509.09685v5 Announce Type: replace-cross Abstract: We present TalkPlayData 2, a synthetic dataset for multimodal conversational music recommendation generated by an agentic data pipeline. In th
arXiv:2606.03305v1 Announce Type: new Abstract: Benchmark contamination, where evaluation examples appear in a model's training data, threatens the validity of LLM assessment. Statistical tools for de