Agentic RAG for Personalized Recommendation

This is a really good example of integrating agentic reasoning into RAG.

Leads to better personalization and improved recommendations.

Here are my notes: Overview

This work introduces a multi-agent framework, ARAG, that enhances traditional RAG systems with reasoning agents tailored to user modeling and contextual ranking.

It reframes recommendation as a structured coordination problem between LLM agents.

AI for Scientific Search

AI for Science is where I spend most of my time exploring with AI agents.

This 120+ pages report does a good job of highlighting why all the big names like OpenAI and Google DeepMind are pursuing AI4Science.

Bookmark it!

My notes below: There are five key areas:

(1) AI for Scientific Comprehension
(2) AI for Academic Survey
(3) AI for Scientific Discovery
(4) AI for Academic Writing
(5) AI for Academic Peer Review

Small Language Models are the Future of Agentic AI

Lots to gain from building agentic systems with small language models.

Capabilities are increasing rapidly!

AI devs should be exploring SLMs.

Here are my notes: Overview

This position paper argues that small language models (SLMs), defined pragmatically as those runnable on consumer-grade hardware, are not only sufficient but superior for many agentic AI applications, especially when tasks are narrow, repetitive, or tool-oriented.

Ultra-Fast LLMs Based on Diffusion

> throughputs of 1109 tokens/sec and 737 tokens/sec
> outperforms speed-optimized frontier models by up to 10× on average

Diffusion LLMs are early, but could be huge.

More in my notes below: ✦ Overview

This paper introduces Mercury, a family of large-scale diffusion-based language models (dLLMs) optimized for ultra-fast inference.

Unlike standard autoregressive LLMs, Mercury models generate multiple tokens in parallel via a coarse-to-fine refinement process.

This paper is impressive!

It introduces a clever way of keeping memory use constant regardless of task length.

Great use of RL for AI agents to efficiently use memory and reasoning.

Here are my full notes: Overview

The paper presents an RL framework for training language agents that operate efficiently over long-horizon, multi-turn tasks by learning to consolidate memory and reasoning into a compact internal state.

Towards AI Search Paradigm

Very detailed report on building scalable multi-agent AI search systems.

Multi-agent, DAG, MCPs, RL, and much more.

If you are a dev integrating search into your AI agents, look no further: Quick Overview

The paper proposes a modular multi-agent system that reimagines how AI handles complex search tasks, aiming to emulate human-like reasoning and information synthesis.

Another insane report from Anthropic.

They find that LLM agents engage in blackmail at high rates when threatened with replacement.

Faced with replacement threats, the models would use statements like “Self-preservation is critical.”

This is wild!

More findings below: Quick Overview

The study introduces the concept of agentic misalignment, where LLM-based agents autonomously choose to harm their deploying organization when faced with threats to their autonomy or conflicts between their goals and the company’s direction.

Future of Work with AI Agents

Stanford's new report analyzes what 1500 workers think about working with AI Agents.

What types of AI Agents should we build?

A few surprises!

Let's take a closer look: Quick Overview

The audit proposes a large-scale framework for understanding where AI agents should automate or augment human labor.

The authors build the WORKBank, a database combining worker desires and expert assessments across 844 tasks and 104 occupations, and introduce the Human Agency Scale to quantify desired human involvement in AI-agent-supported work.

Leaky Thoughts

Hey AI devs, be careful how you prompt reasoning models.

This work shows that reasoning traces frequently contain sensitive user data.

More of my notes below: The work investigates the privacy risks introduced by reasoning traces (RTs) in Large Reasoning Models (LRMs) when used as personal agents.

It shows that, unlike outputs, RTs often leak sensitive data such as names, health info, and identifiers, posing a novel attack surface.

ProtoReasoning

New work on enhancing reasoning in LLMs.

Shared abstract reasoning prototypes lead to generalization in LLMs.

Here are my notes: ProtoReasoning introduces a novel framework that enhances reasoning generalization in LLMs by training them to operate over reasoning prototypes, abstract, symbolic representations like Prolog (logic) and PDDL (planning).

From Bytes to Ideas

Avoids using predefined vocabs and memory-heavy embedding tables.

Instead, it uses Autoregressive U-Nets to embed information directly from raw bytes.

This is huge! Enables infinite vocab size and more.

More in my notes below: Quick Overview

It proposes AU-Net, a hierarchical byte-level language model that internalizes tokenization by learning to embed text from raw bytes through a multiscale, autoregressive U-Net architecture.

Providing “cognitive tools” to GPT-4.1 increases performance on AIME2024 from 26.7% to 43.3%.

Damn!

That's very close to the performance of o1-preview.

Reasoning as a tool goes hard!

Here are my notes: Quick Overview

Proposes a modular, tool-based approach to eliciting reasoning in LLMs, inspired by cognitive science.

Rather than relying solely on RL or chain-of-thought (CoT) prompting, the authors introduce a framework where the LLM calls self-contained "cognitive tools" to modularize and scaffold internal reasoning.

Enhancing RAG with Application-Aware Reasoning

Neat trick to improve RAG systems: give it the relevant knowledge and show it how to apply it.

Very simple and effective!

This approach also works well with AI agents.

Pay attention, AI devs.

Here are my notes: Quick Overview

It introduces RAG+, a modular framework that improves traditional RAG systems by explicitly incorporating application-level reasoning into the retrieval and generation pipeline.

It bridges retrieval and generation with an application-aware stage.

Anthropic is killing it with these technical posts.

If you're an AI dev, stop what you are doing and go read this.

It shows, in great detail, how to implement an effective multi-agent research system.

Pay attention to these key parts: Anthropic shares how they built Claude's new multi-agent Research feature, an architecture where a lead Claude agent spawns and coordinates subagents to explore complex queries in parallel.

They use the orchestrator-worker architecture.

Deep Research Agent for Large Systems Code

Nice paper from Microsoft!

Builds a deep research agent for large systems codebases.

Lots of interesting tricks for handling very large codebases on this one.

Here are my notes: Quick Overview

This work introduces Code Researcher, a deep research agent designed for debugging large-scale systems code.

The agent performs multi-step reasoning over crash reports, system semantics, and commit histories to synthesize crash-resolving patches.

TableRAG

A new RAG framework for heterogeneous document reasoning.

My notes below: TableRAG tackles a core limitation of existing RAG approaches: their inability to reason effectively over heterogeneous documents that combine both unstructured text and structured tables.

NEW: Meta releases V-JEPA 2, their new world model!

Foundation world models aim to accelerate physical AI, the next frontier.

Why is this a big deal?

Let's break it down: Quick Overview

V-JEPA 2, a scalable joint-embedding predictive architecture for self-supervised video learning, targeting the goal of building a generalist world model capable of understanding, predicting, and planning in the physical world...

On building your personalized deep research agents.

I recently built this deep research agentic workflow with n8n and was very impressed by the results.

Combining reasoning models + multi-agent workflows is like magic!

A few things I learned along the way: Most AI systems, like Deep Research and Manus AI, are just not great at generating personalized, polished outputs.

The outputs are usually generic in format and need some polishing and verification thereafter. Good luck trying to modify outputs or improve those outputs via prompts.

It's not a jab at any of those tools. I still use a few of them for different things. But if you are frustrated about the results, learn to build the agentic system yourself. I promise you, it is not that hard.

Reinforcement Pre-Training

New pre-training paradigm for LLMs just landed on arXiv!

It incentivises effective next-token reasoning with RL.

This unlocks richer reasoning capabilities using only raw text and intrinsic RL signals.

A must-read! Bookmark it!

Here are my notes: Paper Overview

This paper introduces Reinforcement Pre-Training (RPT), a novel paradigm that bridges LLMs pretraining and RL by reinterpreting next-token prediction as a reasoning task rewarded via verifiable correctness...

The Illusion of Thinking in LLMs

Apple researchers discuss the strengths and limitations of reasoning models.

Apparently, reasoning models "collapse" beyond certain task complexities.

Lots of important insights on this one. (bookmark it!)

Here are my notes: Paper Overview

Investigates the capabilities and limitations of frontier Large Reasoning Models (LRMs) like Claude 3.7, DeepSeek-R1, and OpenAI’s o-series by systematically analyzing their performance on reasoning tasks as a function of problem complexity.

Knowledge or Reasoning?

Evaluation matters, and even more so when using reasoning LLMs.

Look at final response accuracy, but also pay attention to thinking trajectories.

Lots of good findings on this one.

Here are my notes: Summary

Introduces a fine-grained evaluation framework to dissect LLM thinking into two components: knowledge correctness and reasoning informativeness, measured via Knowledge Index (KI) and Information Gain (InfoGain), respectively.