127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “agents”

18,727 results

Safety

World State Generator

DGX agent

arXiv:2609.24744v1 Announce Type: new Abstract: Language agents solve complex tasks through plans and actions. A single step the world refuses puts the goal out of reach, and what the agent does next

safetyarxiv-cs-ai

23 Sept 2026

Agents

Active Spatial Inspection for Effective and Efficient Embodied Exploration

DGX agent

arXiv:2609.22385v1 Announce Type: cross Abstract: Achieving high task success and efficiency remains a central pursuit in embodied exploration. Existing frameworks typically guide agent behavior throu

Search: “agents”

World State Generator

Active Spatial Inspection for Effective and Efficient Embodied Exploration

FRAMES: Failure Recovery And Monitoring of Embodied Skills for Humanoid Loco-Manipulation

SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm

Towards Full Pipeline FP8 Reinforcement Learning for LLMs

SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?

VeriFuse: Bounded Vision-Language Arbitration and Reason-Guided Refinement for Cooperative 3D Perception

Continual Enterprise World Model Discovery in Dynamic Systems

Robust Federated Q-Learning with Almost No Communication

Composite-Gradient Learning for Shared Control Authority Between Deep Reinforcement Learning and Model Predictive Control

LEAP: Learning Emergent Active Perception for Quadruped Navigation

Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier Models

Exploring 2D backbone effects for indoor semantic occupancy prediction

Mapping U.S. Federal AI Governance Against Sector Vulnerability

Metacognitive Steering: Learning the Structure of Scientific Judgment

The MAL Simulator: Cyber Operations Simulation based on Attack & Defense Graphs

AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation

Chance-Constrained Belief-Space Maneuver Planning for Autonomous Collision Avoidance Under Uncertainty

Data Security in Large Language Models: Risks, Defense, and Directions

Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models

GLAM: Training a latent world model over global spatiotemporal memory for active exploration and navigation

Homeostatic Continual Learning

MedSAM3: Delving into Segment Anything with Medical Concepts

Predictive audio representations for early detection and tracking of hidden dynamic objects

Sensory Precision Inference for Multimodal Arbitration under Uncertainty

LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?

Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code

Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations

OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows

Smart Adaptive Computing Across the Continuum: LLMs in IoT-Edge-Cloud Resource Management

Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

A Computational Implementation of a Goal-Directed Theory of Affect

Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability

Compiling VGDL into Causal Models

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Online Inverse Integer Linear Optimization via Small-Gradient Skipping: Constant Regret and Finite Mistakes

Safe Learning Under Irreversible Dynamics via Asking for Help

WorldAgen: Unified State-Action Prediction with Test-Time World Model Training

Efficient Exploration Is Enough

Input-to-State Stability Framework for Fully Distributed Primal-Dual Dynamics for Quadratic GNEPs Without Multiplier Consensus

Memory in Deep Time-Series Models

Non-Adaptive 1-Bit Mean Estimation: Minimax Rates and the Sample-Interval Tradeoff

One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints

Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discovery

RoMu4o: A Robotic Manipulation Unit For Orchard Operations Automating Proximal Hyperspectral Leaf Sensing

Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics

Pack It My Way: Triadic Human-Robot Collaboration for Personalized Autonomous Packing