THE INTERNET IS THINKING
Earlier sources: AI agents
AI agents use models to choose actions, call tools, and work toward a goal. This thread follows agent frameworks, memory, orchestration, evaluation, and safeguards; autonomy and reliability vary between systems.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗843 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- arXiv · Published · First archived
Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent Training ↗
Graphical User Interface (GUI) agents have emerged as a promising paradigm for automating complex digital workflows across diverse applications. However, training highly capable and generalizable agents fundamentally relies on massive, high-fidelity visual-action trajectories, which are notoriously difficult to acquire. While human demonstrations are unscalable, existing GUI world models rely on text descriptions or HTML rendering, discarding crucial pixel-level visual details like icons and layout styles. To address this issue, we introduce Infinite-Dreamer, a simulation-free data synthesis m…
- arXiv · Published · First archived
Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents ↗
Long-running agents repeatedly call an LLM while retaining most of their document window, evicting old documents, and appending new ones. These rolling updates break exact prefix caching and motivate non-prefix KV-cache reuse with selective recomputation. We show that persistent KV-cache reuse with selective recomputation can be history-dependent: in our rolling-agent workload, an unchanged prompt can produce different answers depending on the requests processed before it. At a matched 5% recomputation budget, document-aligned recomputation reduces answer variation across request orders from 6…
- arXiv · Published · First archived
Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training ↗
Terminal agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored. We study the \emph{supervision horizon}, the number of trajectory tokens retained for training, and show that it is a key design axis for reliability and cost. Reliability improves with longer horizons but saturates: on Terminal-Bench, a 12K-token horizon solves more tasks than 16K ($29\pm0.7$ vs.\ $26\pm0.8$) while requiring 30\% less training time. The horizon also shapes agent behavior: short horizons cause premature termination, intermediate horizons…
- arXiv · Published · First archived
Measurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer Validation ↗
Agentic leaderboards increasingly evaluate systems on public benchmarks whose task statements and solution-bearing artifacts can remain accessible. We propose a measurement-first audit framework that distinguishes contamination claims according to the evidence required to support them. It separates three channels that require different evidence: training-time exposure, evaluation-time retrieval, and pipeline/scaffold leakage. Each channel is coded as open, partial, closed, or unknown under a fail-closed rule. Across nine Holistic Agent Leaderboard (HAL) configurations, none of the 27 channel a…
- arXiv · Published · First archived
Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement ↗
Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing zero trust introduces significant challenges in safety, reliability, and policy compliance. This paper presents Agentic AI based zero trust architecture (Agentic-ZTA) that operationalizes the NIST SP 800-207 ZTA architecture control loop through coordinated multi- agent decision pipeline. In the proposed framework, policy knowledge is embedded into a retrieval-augmented generation pipeline and retrieved at inference time as top-k relevant policies. Access requests are interce…
- Hacker News · Posted on Hacker News · First archived
Show HN: Recursant, the agent-aware model router built for hybrid workloads ↗
Sharing Recursant, the agent-aware model router for private/public workloads. Cut your AI agent bill by 30% and seamlessly operate agents across private and public inference infrastructure. Recursant is agent-aware, routes intelligently, built to be fast (C), and intended for privacy. github.com/ajensenwaud/re… It’s still rough around the edges, but good enough to run across private/public routing to your own vLLMs and OpenRouter. I am working on…
- Hacker News · Posted on Hacker News · First archived
Decision making is becoming the agentic coding bottleneck ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
L402 edge cache for AI agents paying over Lightning ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: The Poteto Frontier for AI Agents ↗
I made this lil meme app based on @poteto (lauren tan)'s amazing talk asking: how many agents do you generally have working on your behalf? her original talk: https://x.com/poteto/status/2102050467505430555 source: https://github.com/transitive-bullshit/poteto-frontier
- OpenAlex · Published · First archived
A critical assessment of the rise of agentic AI, its capabilities, task domains and open challenges ↗
The tremendous advancement in Large Language Models (LLMs) has triggered a fundamental reorientation in AI: from basic, single-prompt-based systems to agentic systems that can perceive the world, break down problems into multiple steps, use external tools, and continuously revise the generated response through a long-range dialogue. Although such a revolution is driven by four major technologies: instruction-following models, structured tool APIs, retrieval-augmented generation, and multi-agent orchestration systems, no holistic survey of this emergent field from a task-oriented unified point…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI agents
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.