127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “reasoning”

19,026 results

Research

Delightful Exploration

DGX agent

arXiv:2605.13287v1 Announce Type: cross Abstract: Most exploration algorithms search broadly until uncertainty is resolved. When the action space is too large to resolve within budget, practitioners d

researcharxiv-cs-ai

14 May 2026

Research

Dual-Pathway Circuits of Object Hallucination in Vision-Language Models

DGX agent

arXiv:2605.13156v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated remarkable capabilities in bridging visual perception and natural language understanding, enabling a wid

Search: “reasoning”

Delightful Exploration

Dual-Pathway Circuits of Object Hallucination in Vision-Language Models

Effective Context in Transformers: An Analysis of Fragmentation and Tokenization

Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the Edge

FMC-DETR: Frequency-Decoupled Multi-Domain Coordination for Aerial-View Object Detection

FRAME: Forensic Routing and Adaptive Multi-path Evidence Fusion for Image Manipulation Detection

From Pixels to BFS: High Maze Accuracy Does Not Imply Visual Planning

Harnessing Agentic Evolution

(How) Do Large Language Models Understand High-Level Message Sequence Charts?

How to Interpret Agent Behavior

IdeaForge: A Knowledge Graph-Grounded Multi-Agent Framework for Cross-Methodology Innovation Analysis and Patent Claim Generation

Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task

Large Language Models Lack Temporal Awareness of Medical Knowledge

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall

MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving

Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization

NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy

OpenAaaS: An Open Agent-as-a-Service Framework for Distributed Materials-Informatics Research

PERCEIVE: A Benchmark for Personalized Emotion and Communication Behavior Understanding on Social Media

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records

PhysEditBench: A Protocol-Conditioned Benchmark for Dense Physical-Map Prediction with Image Editors

Progressively Sampled Equality-Constrained Optimization

RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records

Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle

RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning

SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models

ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles

SHM-Agents: A Generalist-Specialist Integrated Agent System for Structural Health Monitoring

State-Centric Decision Process

Teacher-Guided Policy Optimization for LLM Distillation

ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery

ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling Dialogues

Topo-R1: Detecting Topological Anomalies via Vision-Language Models

Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents

Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints

Uncertainty-Aware Prediction of Lung Tumor Growth from Sparse Longitudinal CT Data via Bayesian Physics-Informed Neural Networks

Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation

WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data

When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models

20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone

3D-Belief: Embodied Belief Inference via Generative 3D World Modeling

A Causal Language Modeling Detour Improves Encoder Continued Pretraining

A Survey of On-Policy Distillation for Large Language Models