Knowledge catalogue
// Beyond Individual Intelligence // One of the more useful multi-agent surveys I've read this year. 200+ papers mapped along three axes: collaboration mechanisms, failure attribution, and self-evolut
Great paper discussing agentic search vs. vector search. // Is Grep All You Need? // Pay attention to this on, AI devs. (bookmark it) They find that grep-style text search, when wrapped in the right a
// Harnessing Agentic Evolution // Pay attention to this one if you run iterative agentic search loops. (bookmark it) AEvo splits the self-improvement loop into two jobs: > One proposes the next candi
Interesting position paper on agentic AI as a foreseeable pathway to AGI. (bookmark it) There has been strong debate on whether a larger single model get us there or a multi-agent system. The authors
Do multi-agent systems make LLM reasoning better? Most AI devs assume that it should. But this new paper shows that this is often not the case. It ran 22,500 deterministic trajectories across GAIA, SW
HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kin
// δ-mem: Efficient Online Memory for LLMs // One of the more elegant memory mechanisms I've seen this month. Most long-term memory work either inflates context or retrains the model. This paper shows
Cool idea from Nous Research. What if you could speed up long-context pretraining with a subquadratic wrapper that you remove before deployment? That is the idea behind Lighthouse Attention. The metho
NEW paper from Google DeepMind. (bookmark it) AI Co-Mathematician is an agentic research workbench for mathematicians, and it just hit 48% on FrontierMath Tier 4, a new high score among AI systems eva
Pay attention to this one if you build research or knowledge-work agents. Most research-agent systems produce uniform outputs regardless of who is driving them. This new work, NanoResearch, argues tha
Cool paper from PwC. 'Earlier is always better' is the default intuition for agent clarification. New paper claims that's mostly wrong. Goal clarification loses nearly all of its value after just 10%
Great essay by Tobi. Building an AI-native company? Go read it now. I couldn't resist visualizing it with my artifact generator. Biggest takeaway for me: 'The risk isn't that AI does the work. It's th
// LLMs Improving LLMs // Interesting progress the past of couple of weeks around self-improving AI agents. If autoresearch was interesting, you will like this read. (bookmark it) We've been hand-tuni
// The Memory Curse in LLM Agents // (bookmark it) Long histories apparently degrades agents as they become increasingly history-following and risk-minimizing. Across 7 LLMs and 4 social dilemma games
The Top AI Papers of the Week (May 4 - 10) - Conductor - HeavySkill - Horizon Generalization - 1,000 Synthetic Computers - Self-Improving Pretraining - Coordination as Architecture - Connect Four Alph
This is just mindblowing stuff! I couldn't resist replicating this workflow to generate 3D biological structures. In a few minutes, I designed an artifact specifically built to generate these for any
My favourite new stack: Agents + MCP + Markdown + HTML “Files over apps” is a vibe! LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis ca
For those interested, I will be doing a live session on this topic soon: https://academy.dair.ai/events/cmovobp97000904l5h0n9a2yz Sign up if you are interested in some of the tools we are releasing so
LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important information that lets you and your agents do meaningful wor
Hacker News → LLM Artifact I built the most personalized HN feed. It only tracks topics I do research around based on memory and LLM wiki. No point in storing bookmarks. With a few automations, rules,
DAIR.AI is hosting a live educational session where instructor Omar Saro will demonstrate how to build a project or system similar to one referenced in their academy platform. The session aims to prov
Top skill to learn today: AI Agent Evaluation. Anyone can build AI agents now but the difference is in the quality that's only possible via proper evals. Wrote some thoughts on evaluating production A
arXiv Papers → LLM Artifacts This is how I keep up with AI research now. It's like having access to the most personalized arXiv feed. Automations run everyday to curate papers based a set of rules and
NEW paper from Microsoft Research. (bookmark it) The entire interpretability literature is built around human readers. As more analysis gets delegated to agents, the right target of interpretability s
Wiki-Builder, a tool for creating LLM-powered wikis, was featured on Hacker News' front page, announced by DAIR.AI. The post indicates upcoming updates and improvements to make wiki creation more acce
// HeavySkill // One of the cleaner takes on agentic harness design I've read. They argue that what actually drives agent harness performance is not the orchestration code. It's a single inner skill:
NEW paper from Microsoft Research. Nice study on long-horizon agent generalization. (bookmark it) The team runs a study where the only variable is task horizon length. They use the same decision rules
// Skills as Verifiable Artifacts // Pay attention to this one, AI devs. If you ship agent skills, your runtime is treating signed-and-cleared skills as trusted by default. This paper argues a skill i
Banger paper from Meta FAIR. They introduce Autodata, an agentic data scientist that builds high-quality training and evaluation data autonomously. The headline result: on a CS research QA task, an Ag
NEW paper from Sakana AI (ICLR 2026). A 7B Conductor model just hit SOTA on GPQA-Diamond and LiveCodeBench by orchestrating other LLMs instead of solving problems itself. (great paper! bookmark it!) T
DAIR.AI released a skill or tool designed to assist in building wikis powered by large language models (LLMs), likely enabling users to create structured knowledge bases with AI capabilities. The reso
The Top AI Papers of the Week (April 26 - May 3) - Latent Agents - RecursiveMAS - OneManCompany - AgenticQwen-30B-A3B - Agentic World Modeling - Agentic Harness Engineering - From Skill Text to Skill
We have released a little skill to help you build LLM Wikis with your agents. Releasing a little skill to help build LLM Wikis. More people should be building LLM wikis. I hope the skill is useful for
Claude Opus 4.7 just implemented an AlphaZero-style self-play pipeline from scratch. It did this on consumer hardware in three hours, then beat the Pascal Pons solver 7 of 8 as first-mover on Connect
// Contextual Agentic Memory is a Memo, not True Memory // Most agent memory today isn't memory. They are more like memos. A new paper argues that vector stores, RAG buffers, and scratchpads implement
Cool paper from Meta FAIR. It's on self-improving LLMs but on the pretraining side. (bookmark it) Most LLM safety, factuality, and reasoning fixes get bolted on at post-training. By then, the patterns
I have been testing DeepSeek-V4-Pro with the Pi coding agent. I am mindblown by how well it works out of the box. A few notes: I spent a few hours building an LLM wiki with an agent powered entirely b
NEW paper from Microsoft Research. If you care about training computer-use agents, this is one to keep. (bookmark it) The team builds 1,000 synthetic computers (each with realistic directory structure
NEW paper: Recursive Multi-Agent Systems // Recursive Multi-Agent Systems // Great read for the weekend. (bookmark it) Multi-agent systems often pass full text messages between agents at every step. T
You don't have to choose between either. It's best to use a combination of them. My advice is to learn how to use a few of these models in different harnesses. Learn to combine their strengths. Open-w
// OCR-Memory // Well this is a unique approach to store memory for long-horizon agents. Most of the agent memory systems compress trajectories into text summaries and hope the model remembers what ma
// When to Retrieve During Reasoning // Pay attention to this one, AI devs. (bookmark it) Most RAG systems retrieve once, before the model starts reasoning. Large reasoning models like o1 and R1 don't
// Agentic Harness Engineering // Pay attention to this one, AI devs. (bookmark it) Most coding-agent harnesses are still tuned by hand or brittle trial-and-error self-evolution. This new work introdu
// Latent Agents // Multi-agent debate makes models reason better. It also burns tokens generating long transcripts before any answer comes out. This new research distills the entire debate into a sin
A few notes on how to get started with building LLM Knowledge Bases. @karpathy popularized it but most people don't know where to start. Everyone should be creating LLM Wikis. Live session tomorrow. S
// From Skill Text to Skill Structure // One of the more practical skill papers I've seen this month. SKILL.md files entangle invocation interface, execution flow, and tool/resource side effects in on
Pay attention to this one, AI devs, especially if you're thinking about agentic commerce or any agent network where many agents share hosts. A correct route to a cold agent is still a failed request f
// Skill Retrieval Augmentation for Agentic AI // Great read for AI devs. (bookmark it) It's on finding efficient ways to incorporate skills for agents. The work introduces Skill Retrieval Augmentatio
// Agentic World Modeling // Massive 40-author survey just dropped. Cleanest taxonomy of world models in agent research I've seen. (bookmark it) The paper proposes a 'levels × laws' framework. Three c
'AI should elevate your thinking, not replace it.' I don't disagree, but the issue is that current LLMs are not really trained to support that out of the box. I've solved this by building my own agent
Don't try to build a self-improving AI agent without evals. You are just wasting time and compute. An agent can't improve from traces it can't evaluate. This is why it's exciting to see @FutureAGI_ go
How do AI Agents spend your money? Most teams treat agent token costs as a rounding error even though the data says they shouldn't. New paper presents the first systematic study of how agents actually
Pay attention to this one, AI devs. If you're building multi-agent systems, you're probably wiring static org charts. New research argues they should look more like a labor market. The paper introduce
Here is a very common problem when building complex agents. Long-horizon agents (in particular) fail in two ways: the decision-maker can't decompose well, or the skill library goes stale. This new res
NEW paper from Alibaba. A 30B MoE with only 3B active params matches Qwen3-235B on real tool-use workloads. AgenticQwen-30B-A3B: 50.2 average on TAU-2 + BFCL-V4 Multi-Turn. AgenticQwen-8B: 47.4. Both
The Top AI Papers of the Week (April 19 - 26) - Skill-RAG - DeepSeek V4 - Autogenesis - Attention to Mamba - Stateless Decision Memory - Self-Evolving Logic Synthesis - Self-Generated World Knowledge
Great paper on improving proactive agents. (bookmark it) Proactive agents act before you do. But how do you evaluate something that's supposed to anticipate needs you haven't expressed? This work intr
A nice paper worth checking out. (bookmark it) For a long time, we have had machines that work astonishingly well before we had a real theory of why. This paper argues that the scattered pieces are be
Good agent memory paper. And great insights on the benefits of structured memory for long-horizon behavior in LLMs. Why it matters: It treats memory less like search and more like a system that will n
Really impressed by how smooth switching most of my coding tasks to Codex (GPT-5.5) from Claude Code (Opus 4.7) has been. I thought it was going to be more difficult and that I would be 'fighting' wit