Search: “dair-ai--x”

This is all I will say on the matter: It’s alarming to see the constant effort to try to tell me how I should use AI, how I should build AI, and now how I should pace it. Is it just me, or are all the

Nice work from Adobe. It's standard practice to store a fixed reference answer for every eval case. When the underlying data changes daily, that stored answer goes stale. Adobe researchers write each

Great paper from Google and colleagues. Trains Text-to-SQL agents using multi-agent RL. (bookmark it) This work proposes DualSQL, which splits Text-to-SQL into two agents, one that links the question

Lots of JevRAG variants showing up. Interesting to say the least. You can’t really make any conclusions with these scoped tests but it raises discussions and exciting directions to find optimization i

I just ran a paper-research agent on an open stack and had this week's top 5 papers on agent memory in my terminal in about 10 seconds. How does it work? I used Tavily to pull the last 7 days of arXiv

Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to discover and explore the top AI papers. We carefully curate the papers, so you can expect mostly bangers. The index

Explore the top AI papers of the week with our brand-new MCP tools. Connect it to Codex, Claude Code, or Grok Bot. Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to

Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos

Nice paper on agent memory. It explores an effective routing mechanism for memory in agents. The overall finding is that you want a separate retrieval strategy for each type of memory instead of one e

Banger paper from Meta on AI research agents. (bookmark it) If you build AI-scientist systems, this one is worth your time. The result: A 27B open model beats the strongest open autoresearch baseline

The Top AI Papers of the Week (October 5 - October 11): - VERA - HERMES - CorpusMap - VeriHarness - Sharpening Tax - Harness Learning - Multi-Agent Self-Supervision Read on for more: https://x.com/i/a

Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's weights with RL and still

Nice paper on optimizing agents and their graders together. The key finding is that you want to update your LLM grader alongside the agent instead of keeping it fixed, because the agent's failure mode

New paper from Microsoft and colleagues on generating enterprise data for agents. If you train or evaluate agents on long-running business work, it's worth your time. (bookmark it) MiniCorp is an offi

Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos

Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes and results, those logs can become training data for the mode

This is all I will say on the matter: It’s alarming to see the constant effort to try to tell me how I should use AI, how I should build AI, and now how I should pace it. Is it just me, or are all the

Interesting work on long-horizon research agents. PrimeScientists can decide where a research agent spends its budget. Achieves 10.3% more reward with 50.6% fewer research attempts, under the same bud

Cool paper showing how effective tuning a system prompt for an agent can be. Recommended paper if you tune agent harnesses. This paper presents EvolveTrade, which treats a trading agent's system promp

An interesting idea is to continually train specialized models on skills. This paper explores that idea. They propose SkillGym which turns human-written skills into 2,756 training environments with co

Sharing some notes from OpenAI DevDay in parts. The first part matters, since it's on everyone's mind. How do you optimize for cost and performance? If you are building agentic applications today, the

New paper from Microsoft on compressing agent context at test time. If your agent gets worse as its interaction history grows, this method is worth a look. FOCUS asks which past interactions the agent

Recommended paper from Sakana AI on recursive self-improvement. They propose an interesting way to scale recursive self-improvement through multi-agent self-supervision. In this line of research, self

Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's weights with RL and still

Don't count out Gemini just yet. Feels like a new era of model releases. Models are so powerful that they now come with cyber variants. Love the pricing on Gemini 3.8 Flash. Performance not bad. Gemin

Another goated release by DeepSeek. Open weight, btw. Outperforms Opus 5 on key benchmarks, btw. Lower prices too. Looks like an extremely efficient model. What a legendary run. 🚀 Introducing DeepSeek

This is all I will say on the matter: It’s alarming to see the constant effort to try to tell me how I should use AI, how I should build AI, and now how I should pace it. Is it just me, or are all the

Banger release from NVIDIA. They just published a report on NeMo Data Designer, their open-source synthetic data tool. It's a declarative config which makes a synthetic data pipeline easy to review, s

Recommended if you work on agent memory. Retrieval is the hardest memory problem in most harnesses because agents keep pulling stale context. AML tests this with a coding track of 150 software tasks,

The era of omni agents is upon us. This is a great report by the Qwen Team on their omni-modal agents. They present Qwen3.8-Omni-Flash, a natively multimodal model trained for long-horizon agent tasks

Cool to see classification models resurge in the era of agents. The effects of Jev are insane. Also very cool to see our emotion dataset built at @dair_ai used to test this new model, Julia-1. I spent

1M-token, multimodal decision models are here! But there is more to this one. You can classify, extract, and summarize with 1M tokens of text and image input. ScaleDown's Constrained Decoding Models r

Great paper from Google and colleagues. Trains Text-to-SQL agents using multi-agent RL. (bookmark it) This work proposes DualSQL, which splits Text-to-SQL into two agents, one that links the question

Cool paper showing how effective tuning a system prompt for an agent can be. Recommended paper if you tune agent harnesses. This paper presents EvolveTrade, which treats a trading agent's system promp

Pay attention to System One models if you are building custom harnesses and agentic workflows. Great to see DSPy integrate Jev and now support System One models for calibrating agentic workflows. I'm

This is one of the strongest use cases I've seen for System One models like Jev. Pay close attention if you build custom harnesses. Jev is now available as a packaged router. What is it? You send the

It's an engineering problem! This topic has gotten too political. Let's get back to the fundamentals. 'Trust and innovation are not in conflict. Safety is how trust is earned.' Today, with over 100 in

Great paper from Meta on agent harness optimization. Meta-Harness-style search uses one development set and one proposal policy, so every edit follows a single path and can get stuck in a local optimu

Really nice paper on harness-aware distillation for small language model agents. (bookmark it) It's a super interesting distillation framework for small language model agents that are deployed with a

Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's weights with RL and still