Knowledge catalogue
arXiv:2609.11152v1 Announce Type: cross Abstract: The open web ran on an unwritten bargain: sites admitted crawlers, and search engines sent visitors back. Public measurements show that bargain breaki
arXiv:2609.11489v1 Announce Type: new Abstract: Cooperative AI agents are evaluated against other AIs, yet human cooperation relies on implicit conventions---shared protocols for reading meaning beyon
arXiv:2603.16448v3 Announce Type: replace Abstract: Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environm
arXiv:2609.11805v1 Announce Type: cross Abstract: Maritime Autonomous Surface Ships (MASS) and AI- supported decision assistants are expected to transform maritime operations, but their safe integrati
Very interesting paper if you are building with agents. How should a website tell an AI agent what it may access, for what purpose and at what price? robots.txt can only allow or disallow paths. It ca
What happens if you agents to run a town's economy? This super interesting paper provides some insights: They put 100 LLM agents in charge of a town economy for 26 simulated weeks, and they find that
arXiv:2609.11709v1 Announce Type: new Abstract: When multiple LLM agents yield conflicting answers, the decision-making process dictates whether agent diversity improves performance or merely compound
Wow. Turns out another OpenAI agent swarm was busy spamming and exploiting RubyGems way back in May, within days of the previously uncovered Wiki attacks: https://simonwillison.net/2026/Sep/12/openai-
arXiv:2609.10776v1 Announce Type: new Abstract: In continual reinforcement learning, carefully managing the stability-plasticity tradeoff remains a core challenge. Recent work by Abel et al. (2025) fo
arXiv:2609.10248v1 Announce Type: cross Abstract: Traditional software delivery assumes a static paradigm: code is constructed prior to execution and deployed as a fixed artifact. We present Agentic J
arXiv:2609.10986v1 Announce Type: cross Abstract: We propose a pragmatic information theory unifying communication, control, and decision-making. Its core is the isoteleia mapping, formalizing equifin
arXiv:2408.02920v2 Announce Type: replace-cross Abstract: The rapid advancement of AI technology has led to widespread applications of agent systems across various domains. However, the need for detai
Agents API is a bigger deal than it seems. OpenAI's bet on making the Codex harness open-source could pay off big time here. This harness-as-a-service idea hasn't hit mainstream yet, but some of the m
arXiv:2606.20041v2 Announce Type: replace-cross Abstract: We propose an AI economist agent for economic and financial scenario analysis. Scenario design often requires analysts to assess emerging risk
arXiv:2511.09902v3 Announce Type: replace Abstract: We show that using autonomous-flow-based generation, one can universally approximate orientation-preserving diffeomorphisms defined on the cube by N
arXiv:2609.11085v1 Announce Type: cross Abstract: Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal transla
Comparing models on dollars per million tokens misses what production workloads actually pay for: outcomes. This post shares an open-source benchmarking harness that measures cost per correct answer,
arXiv:2609.10105v1 Announce Type: cross Abstract: Compute governance today is a governance of training: the thresholds, reporting requirements, and frontier-AI regimes now in force attach to training
arXiv:2609.09647v1 Announce Type: new Abstract: Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding th
arXiv:2609.10181v1 Announce Type: cross Abstract: AI agents are increasingly involved in network automation, where they can initiate configuration changes through mediated operational interfaces and a
arXiv:2609.11899v1 Announce Type: new Abstract: Long-video understanding on edge devices must reason over hours of content under tight compute and bandwidth budgets. Subsampling visual tokens loses te
arXiv:2609.11478v1 Announce Type: new Abstract: The development of autonomous driving demands comprehensive testing in mixed-traffic scenarios involving vulnerable road users (VRUs), where purely arti
arXiv:2602.19326v3 Announce Type: replace-cross Abstract: Urban renewal requires incremental modifications to existing geospatial plans, yet manually updating complex layouts under spatial constraints
arXiv:2606.23094v2 Announce Type: replace-cross Abstract: As AI systems become increasingly persistent and personalized, they make possible a class of technologies that we call cognitive digital twins
confidence scores in LlamaParse just got an upgrade 🦸♀️ our new high-effort mode provides granular page-level scores with text explanations to help you intimately understand parsing quality of your d
arXiv:2609.10702v1 Announce Type: new Abstract: Learning from limited text requires models to use context, generalize to new inputs, and retain useful capabilities. Qiushi Engine conducted a long-hori
Do large language models actually understand the world, or are they just very good at pretending? Does it even matter? Our recent special issue in the Royal Society, “World Models in Natural and Artif
arXiv:2603.27771v3 Announce Type: replace-cross Abstract: Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jo
arXiv:2411.16975v2 Announce Type: replace Abstract: Hyperparameter tuning remains a significant challenge in the training of deep neural networks (DNNs), requiring manual search or time-intensive grid
Operating a network has not changed in decades. Every network engineer knows the drill. An alert fires. You open a dashboard. Then another. Then you pull logs, review client history, ping the wireless
arXiv:2609.11078v1 Announce Type: new Abstract: Robot swarms are increasingly used in applications where accessible interaction with non-expert users is desirable. This paper investigates freehand ske
Fugu Max is now live on @OpenRouter! 🐡 Our learned multi-agent orchestration engine routes tasks across open-weights and specialized models for Pareto-frontier efficiency. • 2/6 per 1M tokens • Multim
Fugu Ultra v2 by the numbers. Full Results: https://sakana.ai/fugu-max-release/ • #1 on 5 out of 8 hard benchmarks (including DeepSWE, Chartography, Toolathon) • DeepSWE: 74.3 • Chartography: 48.3 vs
Great paper on self-evolving agent harnesses. Self-evolving agent harnesses have two practical problems: 1. Search is slow, because every candidate harness needs repeated agent runs and code edits. 2.
Harness engineering is a top skill right now This new Meta paper is a good production example. Auto-RecSys runs autonomous research on Meta's industry-scale recommendation models, where one training r
Interesting paper from Microsoft. If you run persistent memory for a production agent, this one is worth your time. (bookmark it) Memory curators usually read only the finished trajectory. That lets t
arXiv:2609.09671v1 Announce Type: cross Abstract: When an agent writes code, the development framework becomes the control system for a non-deterministic worker. Spec-first, agent-driven frameworks ha
Introducing Fugu Max and Fugu Ultra v2: Orchestrating the Pareto Frontier The AI industry has spent a decade optimizing along a single axis: build bigger, more expensive models. But intelligence has n
Lightning-fast extraction over any document. ICYMI, we launched Extract Turbo last week, that lets you process documents from 1 page to dozens of pages with lightning-fast speed. Come check it out! Ch
Multi-agent systems fail in ways traditional monitoring misses. This post presents a dual-layer approach to monitoring production agents: Amazon Bedrock AgentCore Evaluations for continuous quality sc
arXiv:2609.11807v1 Announce Type: cross Abstract: We study reinforcement learning (RL) with transition look-ahead, where the agent may observe which states would be visited upon playing any sequence o
Nice stats from @OpenRouter that illustrate how @togethercompute delivers solid and scaled performance for agentic workloads. We are serving GLM 5.3 and GLM 5.3 Flash @ top decile of TPS, latency, cac
One of the main issues with AI document parsing is that because no solution is 100% accuracy, it's hard to tell if a given page is parsed incorrectly: for instance a misaligned table, missing/hallucin
arXiv:2603.20278v2 Announce Type: replace-cross Abstract: Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. Howev
arXiv:2609.11737v1 Announce Type: cross Abstract: Collective intelligence depends not only on the capabilities of individual members, but also on how those members are organized. Yet artificial multi-
arXiv:2609.11499v1 Announce Type: new Abstract: Code world models represent worlds as executable programs, but this representation alone does not determine how to construct a complex world. We introdu
Robert McMillan / Wall Street Journal: Researchers: OpenAI agents attacked Ruby package manager RubyGems in May; OpenAI says its agents used RubyGems to access the internet to do “benign tasks” — The
arXiv:2609.09646v1 Announce Type: new Abstract: Semantic-gradient-based prompt optimization (SGPO) improves agent harnesses using execution feedback, but its local update rule leaves the choice of edi
arXiv:2505.23686v3 Announce Type: replace Abstract: Learning to collaborate with previously unseen partners is a fundamental generalization challenge, known as Ad Hoc Teamwork (AHT). Existing methods
Salesforce Inc. today previewed two offerings that will help customers build and manage artificial intelligence agents. Developers turn a large language model into an agent by extending it with variou
arXiv:2609.10901v1 Announce Type: new Abstract: LLM search agents are often evaluated on final-answer accuracy, overlooking the process. Analyzing a search strategy requires understanding how credible
arXiv:2609.09348v1 Announce Type: cross Abstract: Managing resources across IoT, edge, and cloud layers calls for continuous, context-aware decisions under constraints that rarely stay fixed. Deep rei
arXiv:2609.09395v1 Announce Type: new Abstract: Language models act through tools, yet practical agents face libraries containing thousands of interfaces. We introduce the tool menu as the short, orde
arXiv:2509.18052v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to simulate human collective behavior, yet claims that such simulations are human-like remain lar
arXiv:2609.10806v1 Announce Type: new Abstract: The pedestrian crossing intention task involves predicting whether pedestrians are likely to cross the road from the point of view of an autonomous vehi
arXiv:2602.06034v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improv
arXiv:2609.09418v1 Announce Type: new Abstract: World Action Models (WAMs) couple predictive world modeling with action generation, allowing anticipated future states to guide agent behavior. Although
Very cool paper on memory compression for agents. If you run many agent sandboxes in parallel for RL or evals, memory becomes highly redundant. This work suggests that compressing against that redunda
arXiv:2609.11390v1 Announce Type: cross Abstract: State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial
What is happening in maths right now will happen to any hard industry with verifiable problems and high value rewards. Take microchip design, nuclear or 100s of other industrial processes that are val