127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “llm”

22,011 results

Model Releases

LLM Inference in a Flash!

DGX agent

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

model-releasesarxiv-cs-lg

16 Sept 2026

Agents

Shared Selective Persistent Memory for Agentic LLM Systems

DGX agent

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

Search: “llm”

LLM Inference in a Flash!

Shared Selective Persistent Memory for Agentic LLM Systems

Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data

Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization

Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coordination

OpWeave: Flexible Operator Disaggregation for Heterogeneous LLM Serving

The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents

Vibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents

BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines

Dissecting GPU Utilization for LLM Inference on Nvidia Hopper

Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows

How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding

Characterizing Narrative Content in Web-scale LLM Pretraining Data

LLM-Anchored Paralinguistic Enrichment for Alzheimer's Disease Detection

Agent-Based ML-LLM Fusion with Self-Optimizing Prompts for Plateau Weather Alerts

AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories

Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

Beyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents

Characterizing Contention-Induced Reliability Collapse in KV-Cache Timing Side Channels for Multi-Tenant LLM Serving

Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces

Forward-Free LLM Depth Pruning via Weight Redundancy

From Review to Authorization: Key-Isolated Threshold Signing for LLM Agents

HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization

Inference-Time Graph Engineering for Multi-Agent LLM Workflows

It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction

LEBGen: An LLM-Enhanced Bayesian Network Framework for Few-Shot Travel Survey Data Generation

LLM-Generated or Human-Written? Comparing Review and Non-Review Papers on ArXiv

Localizing and Correcting Errors for LLM-based Planners

Measuring LLM Sycophancy under Sustained Multi-Turn Pressure

Neutralizing Popularity Bias in LLM-based Recommendation via Counterfactual Reasoning Guidelines

Personalizing LLM Agent Memory Using Biometrics

Quality Metrics for LLM-Generated Asset Administration Shells: A Perturbation-Based Evaluation Approach

Adapting Technical-Service LLM Agents with Latent Logic Augmentation, Robust Noise Reduction, and Hybrid Reward Modeling

AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories

CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation

Cost-Optimal LLM Routing with Limited User Feedback under User Satisfaction Guarantees

ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies

LLM-Guided Program Evolution for Circle Packing: Breaking 10 Packomania Records for $28

TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors

BASP: Communication-Efficient Batch-Aware Sequence Parallelism for LLM Training

Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory

From Zero to Hero: An Open LLM Ecosystem for Armenian

LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games

No country for old linguists: LLM-brain alignment underdetermines neural computation

Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning

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 tha…

MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts