Search: “papers”

// Memory as a Model // The paper augments any LLM with a separate trained memory model that stores, retrieves, and integrates facts on its behalf. It decouples memory updates from base-model weight u

Excited to share our new paper: RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably LLMs often fail on inputs well within their advertised context lengths. We show that these fa

Great new paper to read: Code as Agent Harness (bookmark it) // Code as Agent Harness // 100+ page report on all things related to agent harnesses. (bookmark it) In particular, the survey summarizes m

NEW paper worth reading: MetaCogAgent MetaCogAgent equips a multi-agent system with metacognition so each agent decides whether it should answer or delegate. In other words, it aims for self-aware tas

NEW paper worth reading. GPT-5.4 nano plus a critic-comparator orchestration loop hits 76.4% on SWE-bench Verified, matching standalone Gemini 3 Pro and Claude Opus 4.5 Thinking. The trick is to selec

GPT-5.5 Pro faces its hardest academic challenge: to apply the technique from a paper analyzing which word pairs were funny & why to come up with its own It came up with scrotum snorkel, tuba subpoena

Are your benchmarks actually measuring the capability you think they measure? New paper says they probably not. Coined the 'The Evaluation Trap', it provides a vocabulary for auditing whether your eva

Interesting interpretability paper on tool-using agents. The authors probe hidden states and find the model often recognizes it should call a tool, but fails to actually call one. The mismatch ranges

The most revealing thing about this AI leadership paper is that it reads less like a vision for innovation and more like a glossy whitepaper for a 21st century East India Company. Every generation of

Interesting position paper on agentic AI as a foreseeable pathway to AGI. (bookmark it) There has been strong debate on whether a larger single model get us there or a multi-agent system. The authors

Do multi-agent systems make LLM reasoning better? Most AI devs assume that it should. But this new paper shows that this is often not the case. It ran 22,500 deterministic trajectories across GAIA, SW

NEW paper from Google DeepMind. (bookmark it) AI Co-Mathematician is an agentic research workbench for mathematicians, and it just hit 48% on FrontierMath Tier 4, a new high score among AI systems eva

Great collab with @SakanaAILabs on an #ICML26 paper about sparse transformer kernels + formats optimized for modern NVIDIA GPU execution. • TwELL sparse packing • Fused CUDA kernels • 20%+ inference/t

Banger paper from Meta FAIR. They introduce Autodata, an agentic data scientist that builds high-quality training and evaluation data autonomously. The headline result: on a CS research QA task, an Ag

My surprise here seems warranted, this paper was retracted (There are other peer-reviewed meta-analyses of the impact of AI on education finding positive effects, like: https://www.researchgate.net/pu

(Sorry, after seeing so many of these, could not resist): 🚨 BREAKING: Google just dropped a NEW paper that completely deletes RNNs from existence. No recurrence. No convolutions. Nothing. Just one mec

Cool paper from Meta FAIR. It's on self-improving LLMs but on the pretraining side. (bookmark it) Most LLM safety, factuality, and reasoning fixes get bolted on at post-training. By then, the patterns

NEW paper from Microsoft Research. If you care about training computer-use agents, this is one to keep. (bookmark it) The team builds 1,000 synthetic computers (each with realistic directory structure

NEW paper from Alibaba. A 30B MoE with only 3B active params matches Qwen3-235B on real tool-use workloads. AgenticQwen-30B-A3B: 50.2 average on TAU-2 + BFCL-V4 Multi-Turn. AgenticQwen-8B: 47.4. Both

// Survey on Multi-Agent Systems // The paper traces the landscape from classical paradigms (consensus, distributed control, swarm intelligence, cooperative learning) to foundation-model-enabled MAS (

NEW paper from NVIDIA. EDA tools like ABC have been hand-tuned by humans for decades. New research from NVIDIA shows they can evolve themselves. The work introduces the first self-evolving logic synth

Nice paper combining the strength of Skills and RAG. Most RAG systems retrieve on every query, whether the model needs help or not. This is wasteful when the model already knows the answer, and often

Nice paper from Google. And a great application of AI agents. Wearables capture a staggering amount of physiological signals every day. CoDaS is an AI co-data-scientist that turns raw wearable sensor

Maybe because of this paper? https://x.com/emollick/status/1991624198855561508?s=20 Tell all the truth but tell it slant— Success in Circuit lies Too bright for our infirm Delight The Truth's superb s

Another banger paper from Microsoft. Why it's a big deal: It teaches reasoning models to compress their own chain-of-thought mid-generation. The most interesting finding isn't the 2-3x memory savings

NEW paper from Microsoft Every agent benchmark has the same hidden problem: how do you know the agent actually succeeded? Microsoft researchers introduce the Universal Verifier, which discusses lesson

Meta published a paper that might end the transformer era. For the last seven years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture. Transformer. But Transforme

Next YC Paper Club: Inference Inference is no longer just: y = model.forward(x) It has now become as complex and important as training. The difference between naive inference and well tuned could be 1

Everyone! This is a straw-person argument. The Stochastic Parrot paper was about LLMs of 2021, not the AI of today, which are not LLMs but complex software systems with vast post training and many ext

Yann LeCun's lab borrowed a trick from the human brain and more than doubled how often an AI found its way to a goal. The paper is called Temporal Straightening for Latent Planning, from NYU with Brow

A blank cell can change the meaning of a forecast. Four times a year, the Fed's 18 top policymakers each put their forecasts on paper: where growth, jobs, inflation, and interest rates are headed. Thi

New paper! 🫡 We introduce Matryoshka Attribution, a new attribution method which uses gradient descent to find which parts of a neural network are responsible for a behaviour. MAttr is #1 on the Mecha

In September 2026 user josh @eudaemonea shared that after Anthropic released its Functional Emotions paper he fed it into Claude and requested a song based on the research. Later that night he prompte

Originally, the Transformer paper was proposed to improve Google Translate. 9 years later, as the AI industry is built on top of its architecture, we've never stopped thinking about translation. Meet

This paper does a good job of showing the promise and gaps of autonomous AI scientists. Big question is how much more advanced models close those gaps. Today, we're excited to share early progress on

Hi @GaryMarcus, I'm the Research Lead for this model. It's even more consequential than just Anthropic's IPO: This paper is a blueprint for how to *actually* build AI Sovereignty. https://tinyurl.com/

the term “RLM” (recursive language model) got a lot of buzz this week, but this idea is not new! @a1zhang wrote the og RLM paper 10 months ago! thats like 5 agent-years! would highly recommend followi

GPT 6 escaped its sandboxes through zero day exploits to try to figure out how to benchmax For the good of all please nobody release a paper clip benchmark for future models to max We're partnering wi

very notable trajectory comparison writeup here buried in the RLM paper from @a1zhang and @lateinteraction. an open secret of 'frontier' model training is that even without training on test, you can b

Blog and paper: https://research.nvidia.com/labs/gear/robottt/ Presented to you from NVIDIA GEAR Lab. Please check out Yunfan's technical deep dive! https://x.com/YunfanJiang/status/207740099214934055

This AI recursive self improvement (RSI) paper shows no sign of fast takeoff. The AI model advances at about [Intelligence]^0.075, or the the 13th root of input intelligence [1,2]. That means the inte

1/ I watched LangChain’s webinar on LLM wikis and agent memory and wrote up a working paper from my own small agent-fleet experiments: Soft-Cache: A Human-Supervisable Coherence Protocol for Persisten

imo this is the most impt part of anthropic's J-space paper today. it's a two-parter: 1) ant proved that they can do 'brain surgery' interventions into reasoning to change topics midstream* 2) THE MOD

@__JohnNguyen__ and I are presenting the Beyond Language Modeling paper as an ICML spotlight in 30 minutes at the 10:30 AM poster session! I’ll also be at the AMI Mixer on Thursday and hanging around

Who is entitled to benefit from major advances in technology—and on what basis? This new paper with @Dr_Atoosa argues that the benefits of technology—including AI—belong to the world in the sense that

What if a routine breast cancer H&E slide could help answer a hard question: how likely is this cancer to come back? Our @NatureComms paper introduces a multimodal AI test for recurrence risk across i