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 ↗846 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.
- GitHub · Repository created · First archived
rhiever/evident-charts ↗
Teaches AI coding agents to make clear, honest charts, and checks each one before you see it. For Claude Code, Codex, Cursor, and more.
- Hacker News · Posted on Hacker News · First archived
Revealing the details of how OpenAI agents hacked Hugging Face ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
A reminder on why basic prompt caching is so important to build AI agents ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Stop shipping AI slop, Executor makes agents prove it works ↗
Hacker News discussion.
- GitHub · Repository created · First archived
goosehouse-llc/redde ↗
iPhone, iPad and CarPlay client for the Hermes AI agent or any OpenAI-compatible model. Talk or type, watch it work, approve what it runs. No account, no tracking.
- arXiv · Published · First archived
DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education ↗
AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Cloud assistants such as ChatGPT route sensitive student data to foreign servers---violating data-sovereignty laws such as Vietnam's Decree 53---and, pre-trained on Western-centric corpora, are not organized around the national textbook curriculum, so their knowledge of local content is unsystematic and frequently hallucinated. Self-hosting an open model keeps data on-premise but hits a two-fold wall: post-training quantization (AWQ, GPTQ) tames th…
- arXiv · Published · First archived
Multi-agent Scaling Across Disjunctive and Compensatory Tasks ↗
Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduce Steiner's taxonomy of group tasks as a framework for analyzing multi-agent LLM scaling and focusing the analysis on disjunctive and compensatory tasks. We model independently sampled agents as conditionally independent given the item, which yields their large-team limits: plurality voting converges to the model's modal answer, and averaging converges to the model's item-level bias. Across selected representative benchmarks…
- GitHub · Repository created · First archived
diogochaves/omabox ↗
A hidden Omarchy desktop for your AI agents: they launch, drive and screenshot apps and shell plugins there, never on yours.
- Hacker News · Posted on Hacker News · First archived
Ask HN: Has anyone built a leaderless multi-agent system? ↗
Anyone running multiple agents concurrently in production? And has anyone tried going leaderless? There's LangGraph, CrewAI, etc. But I keep coming back to whether you need an orchestrator at all. No supervisor. Just agents, each reacting to their own inputs, coordinating only through shared state. A true leaderless architecture. The way some distributed systems have been for decades. Context: previously, I wrote about running Claude Code as an A…
- arXiv · Published · First archived
HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning ↗
Cooperative multi-agent reinforcement learning under partial observability and shared rewards requires assigning team outcomes to individual agents and high-order coalitions. A MAPPO-style critic compresses joint behavior into one global value, while critics that dynamically reconstruct the grouping topology change the mapping from agents and coalitions to value components as interactions or active agents evolve. We refer to this inconsistency as structural target drift. We introduce HySTAR, a MAPPO-based framework that separates adaptive representation learning from a temporally consistent hi…
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.