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 ↗837 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
Jev-Mobile: Jev as an Executor for Mobile GUI Agents ↗
Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both planning and action grounding at nearly every interaction step, leading to substantial latency and model-serving cost. We introduce Jev-Mobile, which shifts this paradigm to low-frequency VLM planning and high-frequency lightweight execution: the VLM specifies local goals, the accessibility tree defines a structured executable action space, and Jev, a fast typed decision model, repeatedly selects actions within this space. This design allows multipl…
- GitHub · Repository created · First archived
bugyal/skeptic ↗
Runs BOTH controls (nop + oracle) across EVERY task in a coding-agent benchmark, classifies the outcome, captures evidence, and lints leaks statically. One binary, zero LLM calls.
- Hacker News · Posted on Hacker News · First archived
Show HN: Busbar self-hosted execution boundary for Agentic Apps ↗
Came across this new project of Busbar for execution boundaries. looks very promising. Control where AI can go, what it may use, what authority it receives, what it may cost, and what evidence is retained—before it acts.
- arXiv · Published · First archived
GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI ↗
Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-quality natural language executable plans for complex tasks by introducing $\textbf{GRASP}$, a strategy-aware, multi-stage planning framework. GRASP decouples the planning pipeline across specialized, context-isolated modules: it pre-compiles global macro-guidelines (GenPlan), explores alternative localized strategies within isolated context windows (RevPlan), and independently evaluates trajectories using a multi-criteria dis…
- arXiv · Published · First archived
Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale ↗
Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Improving these agents, especially in regulated industries, is difficult: they must detect intent, follow complex operational policies and use tools reliably. Manual end-to-end testing offers limited coverage, while live experiments expose customers to failures that can erode trust. We present a hypothesis-driven simulation workflow for screening candidate CX agents before deployment. Synthetic customers react to agent responses…
- GitHub · Repository created · First archived
sley-lang/sley ↗
Sley — a machine-native programming language: typed semantic state, exact roots, deterministic execution
- GitHub · Repository created · First archived
zouyuxuan122/dsh-our-free-model ↗
在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 Muse Spark 1.3、MiMo V2.6 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, Muse Spark 1.3 and MiMo V2.6 among them. Completely free, with no usage cap.
- arXiv · Published · First archived
Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge ↗
In the Era by Eon benchmark, each question states the rules for its answer, and code computes the answer from a generated company's data. When agents can run code, the four strongest models each answer 22 to 25 of 27 such questions, so the benchmark barely separates them. We add eight question templates that depend on hidden facts. No question or document states a hidden fact, and the records that seem to hold it show something else. Other data implies it. For example, the sales system says a customer dropped a purchase because of timing. On a recorded call, the customer blames an outage. For…
- Hacker News · Posted on Hacker News · First archived
Agent-Manager: Reviewing code while an AI agent is still rewriting it ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Paperclip: Open-source orchestration for teams of AI agents ↗
Hacker News discussion.
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.