Agent Architecture

Opening — Why this matters now We are reaching the awkward teenage years of AI agents. LLMs can already do things: book hotels, navigate apps, coordinate workflows. But once deployed, most agents are frozen in time. Improving them usually means retraining or fine-tuning models—slow, expensive, and deeply incompatible with mobile and edge environments. The paper “Beyond Training: Enabling Self-Evolution of Agents with MOBIMEM” takes a blunt stance: continual agent improvement should not depend on continual model training. Instead, evolution should happen where operating systems have always handled adaptation best—memory. ...

The dominant paradigm in LLM agents today is autoregressive reasoning: think step by step, commit token by token. This approach works decently for small tasks — write a tweet, answer a math question — but it quickly falters when the goal requires deep planning, multiple decision branches, or adapting to partially observable environments. Imagine trying to plan a vacation or operate a flight search website while thinking only one move ahead. ...

What will the future AI agent look like—a collection of specialized tools or a Swiss army knife of intelligence? As researchers and builders edge closer to Artificial General Intelligence (AGI), the design and structure of multi-domain agents becomes both a technical and economic question. Recent proposals like NGENT1 highlight a clear vision: agents that can simultaneously perceive, plan, act, and learn across text, vision, robotics, emotion, and decision-making. But is this convergence inevitable—or even desirable? ...

The next generation of quantitative investment agents must be more than data-driven—they must be logic-aware and structurally adaptive. Two recently published research efforts provide important insights into how reasoning patterns and evolving workflows can be integrated to create intelligent, verticalized financial agents. Kimina-Prover explores how reinforcement learning can embed formal reasoning capabilities within a language model for theorem proving. Learning to Be a Doctor shows how workflows can evolve dynamically based on diagnostic feedback, creating adaptable multi-agent frameworks. While each stems from distinct domains—formal logic and medical diagnostics—their approaches are deeply relevant to two classic quant strategies: the Black-Litterman portfolio optimizer and a sentiment/technical-driven Bitcoin perpetual futures trader. ...