[![AI Newsletter](https://substackcdn.com/image/fetch/$s_!m7md!,w_40,h_40,c_fill,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F41327c80-fe59-416d-aa6f-ab6874177ac7_517x517.png)](https://nlp.elvissaravia.com/)
# [AI Newsletter](https://nlp.elvissaravia.com/)
SubscribeSign in
# 🤖AI Agents Weekly: Agentic Reasoning Survey, Claude's New Constitution, Devin Review, Codex Agent Loop, The Assistant Axis, D4RT, Skills.sh
### Agentic Reasoning Survey, Claude's New Constitution, Devin Review, Codex Agent Loop, The Assistant Axis, D4RT, Skills.sh
Jan 24, 2026
∙ Paid
29
2
Share
In today’s issue:
  * Comprehensive survey on agentic reasoning for LLMs
  * Anthropic releases Claude’s new constitution
  * Cognition launches Devin Review for AI-powered code review
  * OpenAI unrolls how the Codex agent loop works
  * Anthropic research reveals the “Assistant Axis” in LLMs
  * Google DeepMind introduces D4RT for 4D scene reconstruction
  * World Labs launches API for generating navigable 3D environments
  * Palantir details securing agents in production with Agentic Runtime
  * And all the top AI dev news, papers, and tools.


* * *
* * *
## Top Stories
### Agentic Reasoning for LLMs
[![](https://substackcdn.com/image/fetch/$s_!qhLw!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe22a76fa-d0c9-47a4-a184-93a21a935640_1950x1518.png)](https://substackcdn.com/image/fetch/$s_!qhLw!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe22a76fa-d0c9-47a4-a184-93a21a935640_1950x1518.png)
A team of 30+ researchers published a comprehensive survey on agentic reasoning, providing a unified framework for understanding how LLMs function as autonomous agents. The paper structures the field across three complementary layers that bridge cognitive processes with actionable behaviors.
  * **Three-layer framework** – The survey organizes agentic reasoning into foundational (single-agent planning, tool use, search), self-evolving (feedback, memory, adaptation), and collective levels (multi-agent coordination and knowledge sharing).
  * **Reasoning approaches** – Distinguishes between in-context reasoning that scales test-time interaction and post-training reasoning using reinforcement learning and fine-tuning techniques.
  * **Applied domains** – Reviews frameworks across science, robotics, healthcare, autonomous research, and mathematics, demonstrating the breadth of agentic applications.
  * **Open challenges** – Identifies key research directions, including personalization, extended interaction horizons, world modeling, scalable multi-agent training, and governance considerations for deploying autonomous agents.


**[Paper](https://arxiv.org/abs/2601.12538)**
* * *
### Unrolling the Codex Agent Loop
[![Diagram titled “Agent loop” illustrating how an AI system processes a user request, calls tools, observes results, updates its plan, and returns outputs. Arrows connect steps such as user input, model reasoning, tool actions, and final response.](https://substackcdn.com/image/fetch/$s_!0jnf!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8074acab-10d3-4af3-a3df-4e16c4556665_596x275.svg)](https://substackcdn.com/image/fetch/$s_!0jnf!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8074acab-10d3-4af3-a3df-4e16c4556665_596x275.svg)
OpenAI published a deep dive into how the Codex agent operates, revealing the iterative process that powers their coding assistant. The architecture follows a straightforward loop: take the prompt, call the model, execute tool calls, and append results, then repeat until returning a text response.
  * **Reasoning token persistence** – Reasoning tokens persist throughout the tool-calling loop but are discarded after each user turn, creating context preservation within tasks but potential information loss between interactions.
  * **Workaround strategies** – Developers have adopted writing progress updates to markdown files as persistent snapshots across context windows, effectively bridging gaps between separate user interactions.
  * **Lightweight architecture** – The Codex CLI has received praise for its performance, memory efficiency, and open-source codebase compared to alternatives, though users note limitations in visibility into model reasoning during execution.
  * **Missing features** – Current limitations include the inability to interrupt mid-process, a lack of hook support (which developers claim could reduce token consumption by 30%), and automatic changes without clear diff previews.


**[Blog](https://openai.com/index/unrolling-the-codex-agent-loop/)**
## This post is for paid subscribers
[Subscribe](https://nlp.elvissaravia.com/subscribe?simple=true&next=https%3A%2F%2Fnlp.elvissaravia.com%2Fp%2Fai-agents-weekly-agentic-reasoning%3Fopen%3Dfalse%23%25C2%25A7agentic-reasoning-for-llms&utm_source=paywall&utm_medium=web&utm_content=185586518)
[Already a paid subscriber? **Sign in**](https://substack.com/sign-in?redirect=%2Fp%2Fai-agents-weekly-agentic-reasoning%3Fopen%3Dfalse%23%25C2%25A7agentic-reasoning-for-llms&for_pub=nlpnews&change_user=false)
© 2026 elvis · [Privacy](https://substack.com/privacy) ∙ [Terms](https://substack.com/tos) ∙ [Collection notice](https://substack.com/ccpa#personal-data-collected)
[ Start your Substack](https://substack.com/signup?utm_source=substack&utm_medium=web&utm_content=footer)[Get the app](https://substack.com/app/app-store-redirect?utm_campaign=app-marketing&utm_content=web-footer-button)
[Substack](https://substack.com) is the home for great culture