Search: “chat”

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

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

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

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

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

Banger paper from Meta Superintelligence Labs on self-improving agents. (bookmark it) It's hard to know exactly what drives self-improvement, since so many variables are at play (notes, skills, tool c

Build your own harness, folks. Reading papers like this makes me realize how underexplored harness engineering really is. The authors find that on whole-repository migration, GPT-5.6 Sol goes from 6.5

LM Studio 0.4.26 is out now! • ⚡️ `/v1/systemone` and `/v1/decisions` APIs • 👾 Coexistence with Bionic • 🎨 UI updates and bug fixes Yes, you can now point your Bionic agent to models loaded in your LM

Another great paper from Salesforce AI Research. The finding is that a 31B open Gemma-4 web agent scores 74.6% on the 9-app WebArena Infinity set, above Gemini 3 Flash with browser use at 70.1%. They

Great paper from Google on program repair agents inside CI. (bookmark it) They propose FlowAgent, which runs a ReAct-style generate-and-validate loop on pre-submit test failures and shows the fix insi

Banger paper from NVIDIA. One exciting trend I am seeing is building verifiable environments for your agents and training the harness alongside the model. Co-evolving the harness and the model is a bi

Banger paper from Meta AI on research agents that decide what to investigate next. (bookmark it) If you run long-horizon research agents, choosing the next investigation is hard to learn, because thos

Context compression is a huge bottleneck for long-running agents. This work finds that context compression hurts long-horizon agents at a few specific points. They propose PAIR, which replays the agen

Great report from Google and MIT. Co-designing ML models and the accelerators is an exciting research direction. This report introduces Coco, an agent platform TPU architects use for hardware and mode

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

Banger paper from Microsoft and colleagues. If you run agents that search a large document collection, this one is worth your time. (bookmark it) They introduce CorpusMap, which resolves recurring ent

Does telling your agent to plan ahead actually help? It's standard practice to add a 'plan ahead' or 'think about the other players' instruction to an agent's prompt. In auctions and matching markets,

Great overview of context compression in LLM Agents And one interesting, unexpected finding. If your compaction policy is tuned to cut tokens, it may be making your agent run slower. Great study from

Huge release from EverMind AI. Raven is an open-source multi-agent system that builds a separate harness for each model and domain, evolves those harnesses from their failures, and coordinates them th

Learn to optimize your own harness, folks. You can squeeze much more performance and value from a harness. This work claims that a self-modified harness matched Codex for 4.03. Specifically, a coding

We turned Claude Code, Codex, Hermes, Pi, @opencode and other coding harnesses into RL environments. No changes to the harnesses, no changes to the training code. Any open model, any task set, fully o

50K likes on this!? Most of what Karpthy has shared is things we have been doing for over a year. No surprises, as many replies are highlighting. But I still think this raises an interesting discussio

Banger paper from Google. It's standard practice to sample several agent rollouts and trust the answers they agree on. This Google paper shows that agreement can hide shared errors, while disagreement

Banger paper from CMU on harness learning. (bookmark it) Also, pay attention to this important new AI engineering skill of improving agents by editing their harness code instead of their weights. Seei

First AutoHarness, then AutoContext, now AutoCompact. I am seeing a rising trend of work that trains models to natively support more of what the harness does. This work specifically trains agents to d

Banger paper from Google Research on multi-agent proof discovery. (bookmark it) It's really interesting to see this emerging multi-agent pattern: not enforcing too much execution structure and pairing

More agents don't mean higher performance. There is a coordination bottleneck to consider. Not to mention the unnecessary costs. So how many of a multi-agent team's actions actually help it finish the

The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guide to multi-harness RL, and it's one of

OpenAI launched Dots at DevDay. My thoughts. First, the good. Always-on is really really really what the market needed. It's why I find myself reaching for Instinct so often. I don’t have to think abo

Great paper from Amazon AGI on generating RL environments for agents. (bookmark it) Also, pay attention to this important new AI engineering skill of creating RL environments. Seeing a huge shift towa

Banger paper from Microsoft Research. (bookmark it) They run 1K+ coding agents at once to test a scalable self-organized multi-agent harness. This is an interesting test because most multi-agent syste

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

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

People on X: “CLAUDE IS BACK, baby!” Listen, Opus 5.5 is incredible and probably my favorite overall model right now, but it is still ridiculously verbose and over-justifies and over-qualifies everyth

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

Check out this week's updates and releases: — Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two of our most expressive audio generation models yet — Gemini 3.8 Live with Live Avatar, bringing ne

We’re building Copilot as a new OS for work that spans every model, every form factor, and every task. Today, we’re announcing our biggest update to Copilot to date, bringing four things together: · A

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

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

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

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

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

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

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