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 ↗844 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.
- OpenAlex · Published · First archived
LLM-agent-based urban trajectory prediction for behavior-aware and sustainable mobility modeling under geographical constraints ↗
Understanding and modeling urban mobility behaviors are essential for sustainable transportation planning and intelligent mobility management. However, existing trajectory prediction approaches largely rely on historical mobility patterns and task-specific training, limiting their ability to capture the contextual reasoning, heterogeneous behaviors, and adaptive decision-making processes underlying traveler movements. To address this gap, this study proposes TransAgent, an interpretable LLM-agent framework that leverages the semantic reasoning and contextual understanding capabilities of Large…
- OpenAlex · Published · First archived
Agency, Cognition and Mathematical Learning in Agentic Human–AI Ecosystems ↗
Background The rise of artificial intelligence systems that can make their own goals plan several steps and take initiative in tasks that involve people is changing how students learn math. Earlier technology was mostly a tool thatwaited for instructions. Currently, agentic AI systems are becoming increasingly popular. They share the initiative to negotiate goals and help manage parts of learning with the student. This change raises several questions. How is agency shared? What does this mean for thinking? How good is the math understanding that comes from the long-term collaboration between h…
- Hacker News · Posted on Hacker News · First archived
An OpenAI agent reached four Australian government systems. Nobody noticed ↗
Hacker News discussion.
- GitHub · Repository created · First archived
omarqaterge/hermes-mobile-app ↗
Your agent, on your phone. A native Android app for Hermes Agent, running entirely on-device (Termux).
- Hacker News · Posted on Hacker News · First archived
Agentic Compliance in Finance ↗
Hacker News discussion.
- GitHub · Repository created · First archived
OpenInterpretability/ekbasis ↗
Ekbasis: an open world model for agents. What an action will do, before it is done.
- GitHub · Repository created · First archived
capthvnsen/alans-way-agents ↗
Hermes — Alan's Way agent plugin: proactivity, workspace browser tools, and Mac/VPS auto-routing for your Hermes bots
- GitHub · Repository created · First archived
mhmtsrfglu/superwiki ↗
Agent skills that turn docs/ into an LLM-maintained wiki and task tracker. Obsidian-friendly. Works with Claude Code, Codex and Copilot CLI.
- Hacker News · Posted on Hacker News · First archived
Show HN : How I am talking to my agents from my WhatsApp ↗
I recently built this repo : agent-bridge which allows you to reach your agents like claude-code, codex, opencode, etc.. from your WhatsApp self-chat. This is fully open-sourced and comes with a npm package as well (@mayurathavale18/agent-bridge) Do check this out and any improvement suggestions, contributions are greatly appreciated ! https://github.com/mayurathavale18/agent-bridge
- Hacker News · Posted on Hacker News · First archived
Writing Evals for Agentic Systems as a 4 Step Loop ↗
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.