TechniqueRLHF / Alignment8 recent entries24 Aug 2026This is one of the most useful writeups I have seen on keeping an LLM judge effective in production. (bookmark it) Netflix runs judges over …This is one of the most useful writeups I have seen on keeping an LLM judge effective in production. (bookmark it) Netflix runs judges over hundreds of thousands of show-level recommendation explanati→2 Sept 2026Nice paper with great insights on improving self-evolving agents. Self-evolving agents fail in three specific ways: 1. Terminal-only feedbac…Nice paper with great insights on improving self-evolving agents. Self-evolving agents fail in three specific ways: 1. Terminal-only feedback makes it ambiguous which step caused the error. 2. Agents
TechniqueRAG8 recent entries13 Sept 2026This 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,…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→16 Sept 2026Nice work from Adobe. It's standard practice to store a fixed reference answer for every eval case. When the underlying data changes daily, …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 →22 Sept 2026Great paper from Google and colleagues. Trains Text-to-SQL agents using multi-agent RL. (bookmark it) This work proposes DualSQL, which spli…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 →28 Sept 2026Lots of JevRAG variants showing up. Interesting to say the least. You can’t really make any conclusions with these scoped tests but it raise…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→28 Sept 2026I 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 …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→7 Oct 2026Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to discover and explore the top AI papers. We carefully cu…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→7 Oct 2026Explore the top AI papers of the week with our brand-new MCP tools. Connect it to Codex, Claude Code, or Grok Bot.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 →12 Oct 2026Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent …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
TechniqueAgents8 recent entries10 Oct 2026Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B goes…Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B goes from 22.2% to 54.8% on Spider 2.0-SQLite when it is trained→10 Oct 2026Nice paper on agent memory. It explores an effective routing mechanism for memory in agents. The overall finding is that you want a separate…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→10 Oct 2026Banger paper from Meta on AI research agents. (bookmark it) If you build AI-scientist systems, this one is worth your time. The result: A 27…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 →11 Oct 2026The Top AI Papers of the Week (October 5 - October 11): - VERA - HERMES - CorpusMap - VeriHarness - Sharpening Tax - Harness Learning - Mult…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→12 Oct 2026Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is th…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→12 Oct 2026Nice paper on optimizing agents and their graders together. The key finding is that you want to update your LLM grader alongside the agent i…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→12 Oct 2026New paper from Microsoft and colleagues on generating enterprise data for agents. If you train or evaluate agents on long-running business w…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→12 Oct 2026Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent …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
TechniqueFine-tuning8 recent entries13 Sept 2026This 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,…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→22 Sept 2026Interesting work on long-horizon research agents. PrimeScientists can decide where a research agent spends its budget. Achieves 10.3% more r…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→22 Sept 2026Cool paper showing how effective tuning a system prompt for an agent can be. Recommended paper if you tune agent harnesses. This paper prese…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→27 Sept 2026An interesting idea is to continually train specialized models on skills. This paper explores that idea. They propose SkillGym which turns h…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→2 Oct 2026Sharing 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 perf…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→2 Oct 2026New paper from Microsoft on compressing agent context at test time. If your agent gets worse as its interaction history grows, this method i…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→10 Oct 2026Recommended paper from Sakana AI on recursive self-improvement. They propose an interesting way to scale recursive self-improvement through …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→12 Oct 2026Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is th…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
TechniqueMultimodal8 recent entries28 Aug 2026Impressive new work from Google DeepMind showing real-world applications of agents for scientific research.Impressive new work from Google DeepMind showing real-world applications of agents for scientific research. Impressive new paper from Google DeepMind. (bookmark it) It takes Co-Scientist out of simula→2 Sept 2026Don'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…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→10 Sept 2026Another goated release by DeepSeek. Open weight, btw. Outperforms Opus 5 on key benchmarks, btw. Lower prices too. Looks like an extremely e…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→13 Sept 2026This 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,…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→17 Sept 2026Banger release from NVIDIA. They just published a report on NeMo Data Designer, their open-source synthetic data tool. It's a declarative co…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→22 Sept 2026Recommended if you work on agent memory. Retrieval is the hardest memory problem in most harnesses because agents keep pulling stale context…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, →25 Sept 2026The 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 na…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→27 Sept 2026Cool to see classification models resurge in the era of agents. The effects of Jev are insane. Also very cool to see our emotion dataset bui…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
TechniqueSafety8 recent entries22 Sept 2026Great paper from Google and colleagues. Trains Text-to-SQL agents using multi-agent RL. (bookmark it) This work proposes DualSQL, which spli…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 →22 Sept 2026Cool paper showing how effective tuning a system prompt for an agent can be. Recommended paper if you tune agent harnesses. This paper prese…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→25 Sept 2026Pay attention to System One models if you are building custom harnesses and agentic workflows. Great to see DSPy integrate Jev and now suppo…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 →26 Sept 2026This 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 n…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 →28 Sept 2026It's an engineering problem! This topic has gotten too political. Let's get back to the fundamentals. 'Trust and innovation are not in confl…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→1 Oct 2026Great paper from Meta on agent harness optimization. Meta-Harness-style search uses one development set and one proposal policy, so every ed…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→6 Oct 2026Really nice paper on harness-aware distillation for small language model agents. (bookmark it) It's a super interesting distillation framewo…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 →12 Oct 2026Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is th…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