127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “llm”

19,389 results

Research

Goal-driven Variant Categorization

DGX agent

arXiv:2609.22475v1 Announce Type: new Abstract: Process discovery rarely yields a single coherent process structure. For analysis, a common step is to cluster process variants based on structural simi

researcharxiv-cs-ai

23 Sept 2026

Model Releases

Search: “llm”

Goal-driven Variant Categorization

Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training

IntLawNER: A Named Entity Recognition Dataset and Benchmark in International Law

Learning Diagnostic Reasoning for Decision Support in Toxicology

Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models

Modality-Gated Deep Adapters: Adding a Modality to a Frozen Embedding Model with Exact Preservation

ProcessLight: Process Supervision for Large Language Model Based Traffic Signal Control

Semantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval

Small-world Networks of Agents Brainstorm AI Risks to Support Ideation

An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture

From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness

Guiding the coarse levels of semantic IDs makes the fine levels learnable

HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback

Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models

Multiple latent orderings better predict language model preferences

Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation

PRISM-RAG: Multimodal Hypergraph Retrieval-Augmented Generation for Tobacco Product and Legislative Policy Reasoning

Used, Mentioned, or Condemned? A Controlled Contrast-Set Diagnostic for the Use-Mention Distinction in Code-Mixed Hinglish Misogyny Detection

Aligning with Lived Experience: Heterogeneous Benefits of Fine Tuning in Mental Health Support Generation

CESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT Devices

Clinician-Grounded Quality Assurance for AI-Assisted Psychiatric Intake

Conformal Privacy Auditing: Calibrated Re-identification Attacks with Statistical Guarantees

From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers

VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits

Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks

Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems

Kinematics-Grounded Agentic AI for Robotic Additive Manufacturing Process Planning

Redact or Keep? A Fully Local AI Cascade for Educational Dialogue De-Identification

A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality

AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution

An Agentic Framework for Neuro-Symbolic Programming

Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It

Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Decentralized Optimal Equilibrium Learning Over Dynamic Networks

Democratizing Clinical Tumor Whole Genome Sequencing: 18-hour End-to-end Analysis via Trillion-parameter Large Language Models Locally Deployed on Consumer-grade Hardware

DistAL: Distance-based Advantage Learning for VLA Fine-Tuning

Echo: Learning-based Matching Decompilation using Trusted Back Translation

Evolution of US Oral Political Language

Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization

GVD: Governed Versioning and Deduplication for Document Repositories

HALT: Hallucination Assessment via Log-probs as Time series

How Calibration Content Shapes Attention-Based Reranking

How Much is a Human Right Worth? ECtHR-NPD: A Benchmark for Predicting Non-Pecuniary Damage Awards

Lost in Perception: Isolating Perceptual and Reasoning Failures in Multimodal Physics and Geometry Reasoning