Search: “llm”

arXiv:2605.15572v1 Announce Type: new Abstract: The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characte

arXiv:2605.15436v1 Announce Type: new Abstract: This paper presents a comprehensive analysis of neural activation patterns across six distinct large language model (LLM) architectures, examining their

arXiv:2605.15215v1 Announce Type: new Abstract: Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are t

arXiv:2605.15581v1 Announce Type: new Abstract: LLM-based root cause analysis (RCA) agents have recently emerged as a promising paradigm for incident diagnosis in microservice AIOps. However, their re

arXiv:2605.13850v1 Announce Type: new Abstract: Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus o

arXiv:2605.14271v1 Announce Type: new Abstract: LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. Howev

arXiv:2605.14362v1 Announce Type: cross Abstract: Context window efficiency is a practical constraint in large language model (LLM)-based developer tools. Paulsen [12] shows that all tested models deg

arXiv:2605.14465v1 Announce Type: new Abstract: Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constra

arXiv:2605.13848v1 Announce Type: new Abstract: Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routi

arXiv:2605.15102v1 Announce Type: cross Abstract: Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consiste

arXiv:2605.15184v1 Announce Type: new Abstract: Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools,

arXiv:2605.15156v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Ma

arXiv:2605.14978v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by having a lightweight draft model propose speculative windows of candidate tokens for parallel verifica

arXiv:2605.15155v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coars

arXiv:2605.14866v1 Announce Type: cross Abstract: As modern microservice systems grow increasingly complex due to dynamic interactions and evolving runtime environments, they experience failures with

arXiv:2605.12520v1 Announce Type: cross Abstract: Taxonomy induction is crucial for organizing concepts into explicit and interpretable semantic hierarchies. While existing methods have achieved promi

arXiv:2605.13295v1 Announce Type: cross Abstract: LLM-based multi-agent systems have demonstrated strong performance across complex real-world tasks, such as software engineering, predictive modeling,

arXiv:2605.12718v1 Announce Type: new Abstract: Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structu

arXiv:2509.18993v3 Announce Type: replace Abstract: Low-rank architectures have become increasingly important for efficient large language model (LLM) pre-training, providing substantial reductions in

arXiv:2605.13740v1 Announce Type: new Abstract: Whether navigating a building, operating a robot, or playing a game, an agent that acts effectively in an environment must first learn an internal model

arXiv:2605.13037v1 Announce Type: new Abstract: Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rat

arXiv:2605.12838v1 Announce Type: new Abstract: Tracking an interpretable emotional arc of a conversation via the sentiment of individual utterances processed as a whole is central to both understandi

arXiv:2605.12991v1 Announce Type: cross Abstract: LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widel

arXiv:2605.13501v1 Announce Type: cross Abstract: LLM-based generation of SystemVerilog Assertions (SVA) is often reported as nearing saturation, with the strongest specialized model reaching {sim}76%

arXiv:2605.12947v1 Announce Type: cross Abstract: LLM-enabled AI workflows increasingly produce outputs through iterative generate-evaluate-revise loops. Each iteration can improve the candidate, but

arXiv:2605.12197v1 Announce Type: new Abstract: Leveraging Graph Neural Networks (GNNs) as graph encoders and aligning the resulting representations with Large Language Models (LLMs) through alignment

arXiv:2605.11221v1 Announce Type: cross Abstract: Predictive models in biomedicine depend on structured assay data locked in the text, tables, and supplements of primary publications. This bottleneck

arXiv:2605.12177v1 Announce Type: new Abstract: [Abridged] Production LLM deployments receive feedback from a non-random fraction of users: thumbs sit mostly in the tails of the satisfaction distribut

arXiv:2602.09725v3 Announce Type: replace-cross Abstract: Remote KV cache reuse fetches KV cache for identical contexts from remote storage, avoiding recomputation, accelerating LLM inference. While i

arXiv:2605.11403v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, with Group Relative Policy Opti

arXiv:2605.11051v1 Announce Type: cross Abstract: LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promis

arXiv:2605.12419v1 Announce Type: new Abstract: Despite the rapid advancements in large language model (LLM) development, fine-tuning them for specific tasks often results in the catastrophic forgetti

arXiv:2605.11608v1 Announce Type: new Abstract: Comparing post-training LLM variants, such as quantized, LoRA-adapted, and distilled models, requires a diagnostic that identifies how a variant has dri

arXiv:2605.12260v1 Announce Type: new Abstract: Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to bot

arXiv:2605.11290v1 Announce Type: new Abstract: Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller on

arXiv:2605.12264v1 Announce Type: cross Abstract: Supervised Finetuning (SFT) has become one of the primary methods for adapting a large language model (LLM) with extensive pre-trained knowledge to do

arXiv:2605.10999v1 Announce Type: new Abstract: Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, h

arXiv:2503.18760v2 Announce Type: replace Abstract: A key consideration when training an LLM is whether the target language is more or less resourced, for example English compared to Welsh, or Python

arXiv:2602.22586v2 Announce Type: replace-cross Abstract: Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy.

arXiv:2605.10991v1 Announce Type: new Abstract: Existing approaches to LLM personalization focus on constructing better personalized models or inputs, while treating inference as a single-shot process

arXiv:2410.13181v2 Announce Type: replace Abstract: Recent advancements in large language models (LLMs) have been remarkable. Users face a choice between using cloud-based LLMs for generation quality

arXiv:2605.09992v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturb

arXiv:2605.10195v1 Announce Type: new Abstract: Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving compl

arXiv:2605.10598v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as powerful tools for automatic algorithm design (AAD). However, existing pipelines remain inefficient. They o

arXiv:2605.08439v1 Announce Type: new Abstract: Accurately communicating the side effects of cancer treatments to cancer survivors is critical, particularly in settings such as informed consent, where

arXiv:2604.01151v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human o