127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “context”

14,981 results

Agents

TTHE: Test-Time Harness Evolution

DGX agent

arXiv:2607.08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context,

agentsarxiv-cs-lg

10 Jul 2026

Agents

When Does Continual Learning Require Learning

DGX agent

arXiv:2607.07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn? Today, the field largel

Search: “context”

TTHE: Test-Time Harness Evolution

When Does Continual Learning Require Learning

Distributed Sparse Interventions in Language Models

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization

Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety

Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity

aiAuthZ: Off-Host, Identity-Bound Authorization for AI Agents

Breaking Spurious Correlations via Generative Randomization and Cross-Variant Self-Supervised Learning

EvalLoop: A Methodology for Evaluation-Driven Iterative Improvement of Business AI Systems

OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding

PatchOptic for Shared-State LLM Workflows with Projected Views and Verified Structured Updates

Responsible Personalisation: The Double-Edged Sword of Personalisation in Human-Robot Interaction

Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots

TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting

A Vision Based System for Guided and Collaborative Reconstruction of Fragmented Documents

Adaptive Margin RLHF via Preference over Preferences

ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI

DriftST: One-Step Generative Inference of Spatial Transcriptomics from H&E Histology

Efficient Discovery of Conditional Dependencies with Desbordante

Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives

Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing

PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents

RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain

Robust Counterfactual Explanations under Model Multiplicity Using Multi-Objective Optimization

SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision

SelfMem: Self-Optimizing Memory for AI Agents

SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery

VideoSearcher: Empowering Video Deep Research with Multi-Tool Agentic Reasoning via Reinforcement Learning

A Dual-Helix Governance Approach Towards Reliable Agentic Artificial Intelligence for WebGIS Development

GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation

Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity

Repair the Amplifier, Not the Symptom: Stable World-Model Correction for Agent Rollouts

SPLIT: Cross-Lingual Empathy and Cultural Grounding in English and Ukrainian LLM Responses

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates

AGI Maze as a Benchmark Framework for World-Modeling Agents

Deep learning with missing data

Dual-Confidence Contrastive Decoding for Retrieval-Augmented Generation

FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel

GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache

Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization

Linkify: Learning from Interface-Augmented Assembly Graphs

Message Passing Enables Efficient Reasoning

Emergent Culture in Minimal LLM Systems

Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Driving

Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression