Search: “papers”

Banger paper from Apple. If you build MCP servers, this can help you turn your specification into an evaluation suite. (bookmark it) It's actually a really neat idea that's easy to implement. And it s

What a fascinating paper on AI agents. A lot of the issues we see with AI agents today revolve around wrong assumptions the LLMs make. This leads to problems like hallucination, cost inefficiencies, u

I agree with what this AI paper suggests. Self-improving agents should evolve their benchmarks too. (bookmark it) Self-improving agents are one of the most important directions in AI right now, and mo

paper #1 for context: https://x.com/yoheinakajima/status/2057812713045377055?s=20 babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-So

cool new paper on self-improving agents // Self-Evolving Agent Protocol // One of the more interesting papers I read this week. (bookmark it if you are an AI dev) The paper introduces Autogenesis, a s

Can AI agents conduct open-ended AI research? Most evaluations of agents conducting AI research focus on narrow, verifiable tasks. But AI research is often open ended. Researchers pick hypotheses, dec

Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro

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

Super interesting NVIDIA paper on choosing base models for coding agents. It's actually a clever way to rank base checkpoints by how well each one is likely to do as a coding agent after post-training

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

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

Must-read paper from Meta on reliable auto-research agents. If you let coding agents run ML experiments, one silent bug like leaked eval data or a disconnected gradient can invalidate hours of trainin

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

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

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 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

Interesting paper to improve recurrent reasoning. Looped models are great because you get more reasoning out of a model without adding parameters. So this work proposes a looped architecture with a ne

This is a brilliant paper. It's of the cleanest long-context agent designs I have seen in the past couple of months. Sequential memory agents read chunks one after another while maintaining a compact

Nice paper to improve inference efficiency. It's been a while we haven't seen good work on efficiency. Here is why it matters: A long-running agent's workspace outgrows its context window long before

Very important paper accelerating research around AI discovery. https://x.com/omarsar0/status/2095858839534862664?s=20 New benchmark from @Apodex_AI worth digging into. TRACES scores AI systems on dis

Great paper from Google and colleagues. It proposes an interesting approach to improve agents on long-horizon tasks. Long-running agents slow down and start poisoning their own context. Both symptoms

This WikiSkill paper from Google is a must-read. At a high level, it shows the effectiveness of persistent agents, knowledge bases, and skills. @karpathy popularized LLM Wikis. But this paper provides

Great paper on why agent leaderboard comparisons are hard to trust. It's on the hot topic of how much of an agent benchmark score actually belongs to the harness. The harness is the layer between the

Yann LeCun claimed on social media [7] that my foundational 1990 paper on Neural World Models [1] 'was never accepted through peer review.' This is simply false. The core concepts from the tech report

If your AI is still being sycophantic, here’s how to solve it 👀 ✅ Option 1: “here is my research paper - be critical of it please” ✅ Option 2: “here is my research paper - spin up subagents to review

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

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 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

Let’s be clear: LLMs don’t feel pain. And they don’t deserve moral standing. This new paper reports a series of experiments identifying pain-related representations in LLMs. The authors also show that

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

Nice paper from Salesforce on co-evolving harnesses and models. Harness engineering is a hot topic right now. So this is a great read. (bookmark it) Salesforce evolved a harness with a weak model acro

Really strong benchmark paper on coding agents. Claude Opus 5 running under Claude Code passes 23.9% of the evaluations. An expert human reference scores 82.2%. Here is what the task actually is. The

Great paper on designing multi-agent systems. How many distinct communication topologies does an LLM multi-agent system actually need? This works claims that it's about six. Technical summary: Researc

If you build agent skills in production, check out this great paper from Alibaba. You can think of a production agent skill as a directory. The root loads on activation, and references, schemas, scrip

Super interesting paper from Meta. Long-horizon research agents are coming. But one common problem with research agents today is the lack of originality and how to decide what experiments are worth ex

Interesting paper from Tencent. Tencent trains an agent to manage its own working context, and assigns credit at the level of individual context edits. Long-horizon tasks force a model to retrieve, in

Interesting paper on prompt optimization. They claim that a single-lineage prompt optimizer just matched GEPA on a smaller rollout budget. Prompt optimization has been drifting toward heavier machiner

Banger paper from Microsoft. It's on agent reliability in real business workflows. (bookmark it) Thinkingbox is a sandbox with isolated MCP-compatible tool sessions, plus a benchmark of 507 policy-con

Really interesting paper. I recommend it to anyone interested in training agents using existing harnesses. (bookmark it) ClawGym II runs RL through OpenClaw and Claude Code as opaque boxes. A serving

Brilliant new paper from Meta. LLM judges get validated on accuracy against golden data. That says nothing about whether the verdict survives when questioned. The Wiggle Framework stress-tests 9 front

Harness choice is a big deal. So much room to advance and improve results across the board with agent harnesses. Great paper highlighting this. New research releases DataSpace, a benchmark where data

Finally a good paper testing if file-system based memory for LLM agents is worth it. First, what does this look like? Deployed agents keep long-term memory as a folder of markdown files they read and

Are agent skills always worth using? The answer is no? This paper provides some important insights to understand this more. (bookmark it) Paper summary: Adding procedural skills to an agent is usually

Managers, and their belief in the value of AI & how to use it, determines the value they actually get from AI. Neat paper looking at startups. 🤖Excited to share a new working paper🤖 Firms aren't built

NEW paper from Google (bookmark it) It's on advancing automated scientific review. Just pay attention to the focus on agentic verification which is something I've been writing about recently. AI is ac

Claude really can roleplay an economist. I love this little comment Claude made after some robustness checks on the paper it wrote: 'On a 1–10 identification scale, I'd now put the paper at about 4.5