Agents in the Large: Perception-Centered Architecture for Persistent Agents

arXiv:2608.30478 · cs.CL · Submitted 2026-08-31 · Read on arXiv

cs.CL

Submitted: 2026-08-31

Updated: 2026-08-31

Comments: 41 pages, 5 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 27× in this paper · explained in 3 episodes
• Active Perception — 18× in this paper · explained in 2 episodes
• Adaptation — 14× in this paper · explained in 1 episode
• Benchmark — 10× in this paper · explained in 2 episodes
• Benchmarking — 10× in this paper · explained in 3 episodes
• Core — 10× in this paper · explained in 2 episodes
• AI Agents — 8× in this paper · explained in 2 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Adam — 6× in this paper · explained in 2 episodes
• Agent Core — 6× in this paper · explained in 2 episodes
• Agent Architectures — 5× in this paper · explained in 1 episode
• Action Space — 4× in this paper · explained in 1 episode
• Agentic System — 4× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Continual Learning — 4× in this paper · explained in 2 episodes
• Self-Evolving Agents — 4× in this paper · explained in 2 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• International Conference on Software Engineering — 3× in this paper
• Abstraction — 2× in this paper · explained in 1 episode
• Agent Harness — 2× in this paper · explained in 2 episodes
• Agent Skills — 2× in this paper · explained in 1 episode
• Generative AI — 2× in this paper · explained in 2 episodes
• International Joint Conference on Artificial Intelligence — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adaptive Safety — 1× in this paper · explained in 1 episode
• Affordance — 1× in this paper · explained in 1 episode
• Agent Memory — 1× in this paper · explained in 1 episode
• Agentic Coding — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Calibration — 1× in this paper · explained in 7 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Dynamic Adaptation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Metacognition — 1× in this paper · explained in 5 episodes
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Research Review — 1× in this paper · explained in 6 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
• Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
• STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
• From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
• MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence
• VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
• Cordon: Semantic Transactions for Tool-Using LLM Agents
• Task-Aware Scanning Parameter Configuration for Robotic Inspection Using Vision Language Embeddings and Hyperdimensional Computing
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Dynamic Planning with a LLM
• CL-bench Life: Can Language Models Learn from Real-Life Context?
• CL-bench: A Benchmark for Context Learning
• PaLM-E: An Embodied Multimodal Language Model
• Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
• From Cognitive Architectures to Language Agents: A Mechanism-Level Review of Lineage, Convergence, and Migration Gaps
• A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
• AgentScope: A Flexible yet Robust Multi-Agent Platform
• A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
• LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering