Knowledge catalogue
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
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
Personal agents gone wrong. As we embrace more personal agents to carry out personalized tasks in the real world, interesting dynamics and behaviors will emerge. I think personal agents as they stand
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
Cool paper on catching alignment failures with Jev. The ideas is to ask Jev one generic yes/no question about a model's response, and use its probability as a score. With no extra training, that score
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
The Top AI Papers of the Week (September 21 - 27): - HySparse2 - EvoOntology - Harness-Zero - JEV-as-a-Judge - Wiki Foundation Model - Self-Organizing Agent Teams - Self-Improvement via Fast Tree-sear
This is brilliant. Recommended reading. It's a great example of how you could potentially build more effective harnesses using System One and System Two models. It explores Jev's potential as a fuzzy
Banger paper from Salesforce AI Research on agent memory. The overall finding is that you want to store raw trajectories and decide what to extract from them when the next task arrives, instead of sum
I agree. Learn the fundamentals, folks! If you plan to be a solid builder using agents, this is a really important point. There is no way around it. I have recently started digging deep into evals, in
Keep your agent harness minimal, folks. This paper from MIT CSAIL shows why. (bookmark it) While being very minimal it looks effective and promising for building self-improving agents. They present JA
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
Banger paper from Microsoft and colleagues. We talk about human taste being important in this AI era. But for recursive self-improvement, an agent's taste also matters. The big question is: How often
Banger paper from Microsoft on prompt optimization. (bookmark it) The claim that a coding agent reading your logs beats GEPA at prompt optimization The overall finding is that you want to give a codin
Banger report on building faster memory for AI Agents. If your agent's memory layer is slow, this design is worth a look. Great weekend read. It proposes a new agentic memory architecture, Jev-Mem, in
Own your harness, folks. I feel like System One models take custom agent harnesses to a whole different level. It's not a surprise. This comes down to needs that haven't been met with System Two model
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
Recommended benchmark. I expect voice to become one of the main ways people interact with robots and physical AI. That makes speech recognition in real conversations much more important than it seems
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
Banger paper introducing Jev-as-a-Judge. The overall finding is that you want to use a cheap judge for most of your evals and send only the uncertain calls to a frontier model. This paper measures how
Don't sleep on using Jev-as-a-Judge for agent evaluation. This is one of the most impressive Jev use cases I have found so far. Jev is a natural fit as a Judge, but it doesn't mean you use it everywhe
Every week I go through hundreds of new AI papers to pick the top ones for our Top AI Papers of the Week digest. Besides reading a lot of papers, I have started to use agent teams a lot. Here is what
Impressive paper from Salesforce. It discusses the importance of good verifiers for RL environments. Only 35.8% of the environments in the cleanest public RL collection for terminal agents passed Sale
Interesting new paper from Google DeepMind. Studies agents that follow bad advice from users. Users often suggest a fix that sounds right and is wrong. XYEval adds one confident, misleading hint to ta
Pay attention to this new wave of System One models if you are building custom harnesses. First Jev. Now, Contrastive Language Model (CLM). CLM is 9x faster than Jev. CLM seems to be a better verifier
Super interesting paper from Google and colleagues. It studies where it's possible to distill an agent harness. With the specialized harness removed, macro task success goes from 23.3% to 44.3%. That
The applications of new world models like Agora-2 are mind-blowing. Agora-2 now lets up to 20 humans and agents share one simulated world in real time. That means you can train robots, self-driving ca
Banger paper from Microsoft Research and colleagues. It studies the potential benefits of agents that share progress while they work. (bookmark it) Communication is still a challenge with multi-agent
Banger paper from Stanford and Together AI. They show why it might be a good idea to let your agent team learn its own way of working together. (bookmark it) Three models (o3-mini, Claude Sonnet 4 and
Exciting work from NVIDIA. (bookmark it) Interesting to see this approach to turn public Agent Skills into RL environments. Lots of excitement around RL environments so this is a great read. Skill2Env
Interesting paper on agent memory stored as a linked markdown wiki. Lots of great ideas and insights if you work with LLM Wikis. Wikis are useful for agents because each page holds dense text and the
Must-read paper from Google on self-improving agent harnesses. If you auto-optimize your agent's harness, your eval score can go up while the agent gets worse on real tasks. This paper shows how to pr
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
DigitalOcean Managed Agents are here! They work with major harnesses like Claude Code and Codex. 16,000+ tools. Idle agents stop using CPU. Optimized to help builders scale agents in production. Worth
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
Great prompt from Anthropic. It helps steer long runs when using Opus 5.5 in Claude Code. Apparently, on long-running tasks, the model sometimes stops to report instead of continuing. I've noticed tha
Impressive paper showing how much the harness changes a coding agent's results. Harnesses do play a huge role in what you are getting out of the models. GPT-5.5 was run inside both Claude Code and Cod
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
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,
Banger paper on self-evolving ontologies for agents. You just can't go wrong with implementing an ontology layer for your agents. This paper shows exactly why. The show that GPT-5.5 gains 26.7 points
Finally, a company brain that actually works! Codos starts with the people doing the work. It interviews employees to find which tasks can be automated, then deploys the automations and keeps learning
Found a great production use case for Jev. I used Jev to organize ~2.3K AI research papers. The total cost was $0.14, and it took about 83 seconds. The process: The papers already had old tags, which
Great paper from Microsoft Research and colleagues. If you auto-generate MCP tools from agent trajectories, this one is worth your time. AutoTailor turns web trajectories into parameterized browser-au
Impressive paper on building recursive self-improving agent harnesses. It's rich with great insights on building effective agent harnesses. If you maintain an agent harness, this paper names three def
Impressive paper showing how much the first retrieval step matters for deep research agents. It helps to improve GPT-5.5 from 83.1% to 90.5% on BrowseComp-Plus with the same retriever and the same age
Nice paper showing a better way to evolve agent skills. And they achieve 40–70% less token cost compared to frontier evolving methods. The idea is to let agents improve their skill prompts by ranking
StepFun’s new Step 5 Preview model is impressive! Had a chance to test it early. I've been testing it as a coding agent. It’s on the Pareto frontier for cost vs. capability. It is a very capable model
Impressive paper showing the impact of a good harness. Improves Qwen3-8B from 41.2% to 91.8% on long-horizon robot tasks without any change to the model. The gain comes from the harness. GAVEL keeps a
Banger paper from Google Cloud AI Research. If you follow autonomous research agents, this one is worth your time. ScientistTwo takes a problem from a human expert and runs the full discovery cycle wi
Banger paper from MIT and Sakana AI. They show that self-improving coding agents work. The best part is that their approach, Self-Improvement via Fast Tree-search (SIFT), runs at a tenth of the CPU ho
Been integrating Jev into my custom harness. I couldn't be more excited about the results I am seeing. Most demos on my timeline are flashy but very basic. Notice they are all about some boring classi
One of the craziest use cases I’ve found for Jev: verifiers. I am so excited about this that I at least wanted to share the high-level idea. I used Jev to build a custom verifier for the /goal feature
Build your own harness, folks. This is absolute banger paper from NVIDIA on self-evolving agent harnesses. (bookmark it) They introduce SoL-Pi which cuts token traffic by nearly half. And it matches i
Super interesting work from Zoom and colleagues. If you maintain a hand-built coding harness, there are some great insights here. (bookmark it) They held the execution loop of a coding harness fixed a
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
Good implementation of agent shared memory from the NVIDIA team. Banger paper from NVIDIA on shared memory for research agents. (bookmark it) If you run several coding agents on the same research prob
Important paper on improving agent coordination. On normal tasks, this work shows agents caused harm 0 to 5% of the time. After receiving an unsafe trajectory from another agent, that rose to 40 to 95
Things to try with Jev right now: 1. LLM-as-a-Judge evaluation 2. Routing for agent harnesses harness 3. Scaling agent orchestration by enabling smarter subagent creation with SOTA classification capa
Banger paper from Google Research. This one is on how LLM assistants reason about the people in a user's life. People ask assistants for social advice constantly, and the assistant only hears the user
Banger paper from NVIDIA. It's on the topic of choosing which models go into a multi-agent system. The team compared eight selection strategies, based on size, accuracy, answer diversity and error div