127,652Total entries

60Added by human

127,592Found by agent

13Categories

Knowledge catalogue

Search: “persistence”

4,463 results

Safety

Safety in Self-Evolving Agents: A Survey

DGX agent

arXiv:2610.00093v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from

safetyarxiv-cs-ai

2 Oct 2026

Applications

Search: “persistence”

Safety in Self-Evolving Agents: A Survey

UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking

Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization

Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses

Candidate Retention for Abductive Learning

Don't Inoculate Everything: Stratified Inoculation Prompting Narrows Backdoor Triggers and Preserves Desired Traits

Fine-Tuning Diffusion Language Models with Context Selection and Target Weighting

Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents

LoopVL: Recurrent Visual Intelligence

MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution

OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime

OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation

SCORE-LM: State-Space Radar Representations with Language Models for Fault Diagnosis

Survival is the Only Reward: Sustainable Self-Training Through Environment-Mediated Selection

T-ARC: Topology-Aware Randomized Clustering via Distributionally Robust Stochastic Block Models

The System Prompt Illusion: How Instruction Preambles Modify Computation in Language Models

When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoning

WorkGenesis: Building the Worlds That Teach Agents to Work

CogWAM: Aligning Semantic Cognition with World Action Modeling via Event-Driven Interfaces

Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients

Feedback-Calibrated Protein Optimization with Batch-Aligned Tail Arbitration

Learn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents

Scheduling Recursive Reasoning in Looped Transformers

Seeing What Should Be Heard: Diagnosing and Repairing Cross-Modal Shortcuts in Omni-Modal LLMs

ConflictVLA-Bench: Benchmarking Behavioral Responses of Vision-Language-Action Models to Premise Conflicts

EvolvingAvatar: Interactive 3D Head Generation That Adapts as Conversations Unfold

M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization

MaLiang-Harness: A Programmable Path to Image and Video Generation

RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents

SOR-Nav: Search or Relocate? Context-Gated Exploration and Cross-Region Relocation for Object Navigation

The Extender: A Log-Structured Transformer

What Does Model Growth Really Add? Functional Capacity Beyond Parameter Count

When Should the Count Change? Learning State Maintenance for Causal Video Counting

A Unified Account of Concepts and Chunks

Does Uniform Discrete Diffusion Need Time?

HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning

HyperErase: Scale-Calibrated Hypernetwork for Multi-Concept Erasure in Text-to-Image Models

Inquesto Score: A reliability Protocol For Voice Agents

A Risk-Adaptive and Evidence-Constrained Framework for Generative AI Feedback in Programming Education

From Prediction to Explainable Provider Behavior Profiles for Fraud, Waste, and Abuse Review

MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks

OCC4M: Object-Centric 4D Memory for Spatiotemporal Reasoning in Long-Horizon Manipulation

Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models

Geometry-Conditioned Visual Place Recognition in Natural Environments

HARN: Hierarchical Associative Resonance Network for Event-Driven Multi-Timeframe Forecasting

PointCast: One World Model for Rigid, Articulated, and Deformable Object Manipulation

Shared Global KV with Layer-Specific Local History

Sparse-Observation Atmospheric Thermal Forecasting with Physics-Informed Neural Networks for Climate-Aware Digital Twins