127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “llm”

22,011 results

Agents

Memory Intelligence Agent

DGX agent

arXiv:2604.04503v3 Announce Type: replace Abstract: Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are es

agentsarxiv-cs-ai

13 Apr 2026

Agents

Multi-User Large Language Model Agents

DGX agent

arXiv:2604.08567v1 Announce Type: new Abstract: Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are

Search: “llm”

Memory Intelligence Agent

Multi-User Large Language Model Agents

SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support

Through Their Eyes: Fixation-aligned Tuning for Personalized User Emulation

When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning

ATANT: An Evaluation Framework for AI Continuity

Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules

E2Edev: Benchmarking Large Language Models in End-to-End Software Development Task

How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles

Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models

Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression

RAGEN-2: Reasoning Collapse in Agentic RL

Reasoning Graphs: Deterministic Agent Accuracy through Evidence-Centric Chain-of-Thought Feedback

exttt{SEM-CTRL}: Semantically Controlled Decoding

GLM-5.1: Towards Long-Horizon Tasks

CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF

Disagreement-Guided Weak-to-Strong Routing

FedSkillGit: Federated Skill Evolution via Version Control

FlashAttention with Statistics: Low-Overhead Attention Features for Compact Hallucination Detectors

Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction

INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems

KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents

Learning to Reason with Selective Internal Feedback

LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents

Matoi: Selective Revalidation of Consequence Evidence for Agent Authorization

Mind the Shift: Decoding Monetary Policy Stance from FOMC Statements with Large Language Models

Screwtape: Adversarial Transcript Editing for Monitor Red-Teaming

The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock

Tool-Augmented Large Language Models for Reliable Medical Calculation from Patient Notes

When Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free Evaluation

WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics

Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems

Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization

BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla

Correct Choices, Failed Sequences: Choice2Seq Benchmarks Correctness Retention Across Output Interfaces

Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering

Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric

Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher

FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation

GraphRAG-LTM: A Layered Threat Modeling Framework for Attacks on Graph Retrieval-Augmented Generation

Interlock: From Local Correctness to Task Completion in Long-Horizon Agents

JevGPT: Thinking Fast and Slow in Autonomous Research

Label-Centric Knowledge Retrieval for Zero-Shot Text Classification

Large Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers

Large language model-generated patterns for epidemiological modeling: a multi-benchmark evaluation framework

Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems

LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering

LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement