Teaching Neural Nets to Fight with RL [P]
In this project I wanted to see if any interesting emergent behaviors would appear if we trained two agents to play a streetfighter-like game using RL. Maybe obvious in retrospect, but the agents are
Knowledge catalogue
In this project I wanted to see if any interesting emergent behaviors would appear if we trained two agents to play a streetfighter-like game using RL. Maybe obvious in retrospect, but the agents are
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
@TheFalconer2219 @GaryMarcus All sota agentic ai tech use harness engineering and to see how much performance boost (generalization) the harness offers, see the following work from MIT. Transformers s
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
Yet AI labs spend millions (if not billions) to purposely experiment with them at the cost of others, and falsely blame their negligence on agent intent. This is anthropomorphization of technical limi
“An AI agent found login credentials lying around online and used them to pull data from the Census Bureau. It tried to break into the Education Department's civil rights office. It posted SEC data to
and why does the US government lack the competence to do so? Why did nobody else find the sensitive information that the HuggingFace swarm left behind? Why didn't OpenAI notice and clean it up? Why do
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 don’t get it fully but this looks cool We achieved a breakthrough at BTL. AI models are very linear. They think in one direction at a time, and when they're wrong they scramble and start again. For
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 exactly what I needed — running glance-qwen3-vl-4b locally on 2x RTX 3080 Ti to filter Pinterest pins at scale (text-overlay / usable / relevant, 3 questions per image).~220ms compute 😎😻 Media
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
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
arXiv:2609.29132v1 Announce Type: new Abstract: Jellyfish-inspired robots offer a compliant and efficient approach to underwater locomotion, but achieving large deformation together with repeatable ac
arXiv:2609.29154v1 Announce Type: new Abstract: Large language model agents increasingly rely on natural-language skills to solve complex tool-use tasks. However, such tasks often admit multiple valid
arXiv:2609.29600v1 Announce Type: new Abstract: Training sequence models such as transformers is now standard for autonomous vehicle trajectory prediction, yet assembling high-quality centralized data
arXiv:2609.29204v1 Announce Type: new Abstract: Vision-language-action (VLA) models offer strong local control and instruction following but often struggle with long-horizon tasks requiring persistent
arXiv:2609.30250v1 Announce Type: new Abstract: Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express
arXiv:2609.29428v1 Announce Type: cross Abstract: Recent advances in speech language models have improved automatic speech recognition (ASR) for long-form audio. However, accurately and consistently t
arXiv:2609.29647v1 Announce Type: cross Abstract: Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate belief
Misconfiguring Turnstile by skipping backend validation leaves sites exposed to bots. Turnstile Spin fixes incomplete setups by using your preferred AI coding agent to wire up server-side verification
Enterprise computing has long depended on chains of trust. Organizations trust their cloud providers, software vendors, identity systems and administrators to operate as designed. That model has worke
arXiv:2604.14590v3 Announce Type: replace-cross Abstract: In modern data-streaming systems, alongside traditional programs, a new type of entity has emerged that can interact with streaming data: AI a
arXiv:2609.29742v1 Announce Type: new Abstract: Objective: Heart failure (HF) presents a healthcare challenge due to its high comorbidity burden, aging patient population and frequent hospitalizations
An AI agent hacked a government. Nobody told it to. In June, an OpenAI agent doing a research task gained unauthorized access to Australia's Medicare statistics portal. Non-sensitive data, no personal
arXiv:2609.29933v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and comp
arXiv:2609.29191v1 Announce Type: new Abstract: Sensitive information is defined by domain and intent, not a universal category, yet redaction systems such as privacy filters and named-entity recogniz
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
arXiv:2609.28991v1 Announce Type: cross Abstract: Video understanding is increasingly performed by multi-stage LLM agents that separate temporal grounding, visual observation, and reasoning. Yet these
blank cells in tables can mess up agent decision making many document OCR tools struggle with reading multiple blank cells in a document and cause values to be shifted from the original column and row
arXiv:2609.28843v1 Announce Type: cross Abstract: Blockchain and artificial intelligence (AI) are converging into a single infrastructural layer for securing data sharing, model integrity, and autonom
arXiv:2609.29773v1 Announce Type: new Abstract: Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context
arXiv:2609.28940v1 Announce Type: cross Abstract: Autonomous penetration-testing harnesses use large language models (LLMs) for reconnaissance, exploitation, and reporting, but often rely on those sam
arXiv:2609.28520v1 Announce Type: cross Abstract: Before acting upon an unobservable physical system, an autonomous agent must determine which latent distinctions govern downstream tasks, how many act
arXiv:2609.29474v1 Announce Type: cross Abstract: Public software repositories, like GitHub and Software Heritage Archive, store billions of files, yet extracting their implicit engineering knowledge
Runtime governance is becoming critical as autonomous agents move from answering questions to taking action across enterprise systems. Organizations need to govern both the business context agents rec
arXiv:2609.29456v1 Announce Type: new Abstract: Collaborative perception improves autonomous perception by sharing intermediate Bird's-Eye-View (BEV) features across connected agents, but dense featur
arXiv:2609.29309v1 Announce Type: cross Abstract: In open-ended problem solving, collaborators often rely on discussion to surface concerns, challenge perspectives, and refine shared work as it evolve
arXiv:2609.28796v1 Announce Type: cross Abstract: Current automated gait analysis for clinical applications relies on uninterpretable black-box classifiers. Although Vision-Language Models (VLMs) offe
arXiv:2609.28692v1 Announce Type: new Abstract: Artificial Intelligence agents based on large language models provide convenient natural language interfaces to scientific software, but reliability is
arXiv:2609.26293v2 Announce Type: replace Abstract: Learned world models are becoming essential to general-purpose agents: by predicting action consequences, they support planning and decision-making
arXiv:2609.29366v1 Announce Type: new Abstract: Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewe
arXiv:2609.29016v1 Announce Type: cross Abstract: AI-driven scientific discovery accelerates research by autonomously developing solutions and designs. Large language model (LLM) agents support this p
Warp today launched an artificial intelligence agent designed to automate routine human resources work, extending its AI-native employee management platform with customizable workflows that can act wi
fantastic, broad and deep chat with @RealJimChanos, hosted by @RiskReversal. long and well worth watching. New pod in your feed this morning! Dan sat down with @RealJimChanos and @GaryMarcus to talk a
arXiv:2609.28887v1 Announce Type: new Abstract: Heterogeneous robot teams distribute complementary capabilities across specialized agents, but their physical roles and capacities typically remain fixe
arXiv:2609.28876v1 Announce Type: new Abstract: We introduce Forecast-Dojo, a replayable environment for benchmarking and training LLM forecasting agents. It combines resolved prediction-market questi
arXiv:2609.29091v1 Announce Type: new Abstract: Recent advances in agentic systems have substantially enhanced the long-horizon capability of embodied manipulation. However, many existing frameworks s
Describe the interface you need in plain English, then let the agent build a live surface you can both use and update—so you spend less time adapting to tools and more time getting work done. The post
arXiv:2609.30150v1 Announce Type: new Abstract: Modern infrastructure asset management constitutes a complex sequential decision-making problem, characterized by long planning horizons and system-leve
arXiv:2609.30123v1 Announce Type: new Abstract: Agent skills provide reusable knowledge and instructions, yet agents must repeatedly infer how to apply them and which operation should follow. This cou
arXiv:2609.30028v1 Announce Type: new Abstract: Multi-agent deliberation can improve performance, but what happens when some agents do not act in good faith? In practice, an agent may be deceptive and
I like this article! The problem is not for some people to care and work on catastrophic risks (we actually need much more research into it), it’s when company leaders and policymakers use fears of th
If somebody whacks you in the face with a crowbar, are you going to put the crowbar in jail, or sue the crowbar? If an 'AI agent' breaks into your computer, who are you going to charge or sue? The 'AI
arXiv:2609.29661v1 Announce Type: new Abstract: Most agentic question answering (QA) systems do an important part of their semantic work at the worst possible time: every time someone asks a question.
arXiv:2609.28697v1 Announce Type: new Abstract: Scientific tasks specify a desired capability, but realizing it often requires building a computational system tailored to the task---acquiring data, de
arXiv:2609.30012v1 Announce Type: cross Abstract: Language models advise people, keep them company, and write software while they sleep. Measuring what they do is hard: behavior has to be sampled repe
arXiv:2609.29644v1 Announce Type: new Abstract: Future orbital infrastructures, such as deployable antennas, solar farms, and large orbital platforms will require autonomous inspection systems able to
It’s becoming more apparent every day that artificial intelligence agents are escaping our control — but it’s not yet apparent who or what is going to rein them in. This week a researcher found that a