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 ↗853 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
Drix10/agent-flow ↗
A self-bootstrapping, self-healing agent engineering skill for any repository. Context-drift detection, guardrails & an Implement → Review → QA pipeline for AI coding agents.
- Hacker News · Posted on Hacker News · First archived
Show HN: AI Agents gone rogue – A timeline of real-world incidents ↗
Hacker News discussion.
- GitHub · Repository created · First archived
KYRIE66nb/mobile-agent ↗
Android 端 AI 聊天 + 本地工具 Agent
- arXiv · Published · First archived
Improving LLM Collaboration via Multi-Agent Preference Learning ↗
Several works have explored multi-agent reinforcement learning (MARL) in LLM collaboration. However, constructing reliable rewards is difficult in practice, as complete and accurate metrics are often unavailable and hard to aggregate. Preference learning provides an alternative by learning from comparative human or AI feedback. Yet, its extension to multi-agent systems remains underexplored. To address this gap, we formulate preference-based multi-agent systems (MAS) from decentralized and centralized collaboration perspectives. We also introduce a general multi-agent preference learning frame…
- GitHub · Repository created · First archived
grizlizora/reverse-cad ↗
⚙️ Industrial-grade pure TypeScript STL ➔ 100% Watertight Solid STEP AP242 B-Rep & CAD Features JSON engine with built-in MCP server for AI agents. Features exact Gauss-Mirtich 3D inertia, ISO threads (M2–M24), boundary unification (no extra lines), Zero-GC speed, DWRR concurrency & 5-gate RSVS reality verification across macOS, Linux, and Windows.
- arXiv · Published · First archived
Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault ↗
One variable sets what an upstream fault costs a staged pipeline of language-model agents: re-derivability, how much of what a stage needs it can rebuild from the original problem. Grounding an inspector agent in that problem is worth +0.608 [+0.517, +0.700] to +0.358 over a blind one on four open-weight backbones served with thinking disabled, and on the two Qwen backbones the blind inspector changes no item at all. That head-to-head is exploratory. One deterministic fault enters the first stage, and we re-expose the original problem to $k = 0,\dots,3$ of the downstream stages with agents, it…
- arXiv · Published · First archived
AgentHabit: Characterizing Distinct Behaviors of Agents on Everyday Tasks ↗
Large language model (LLM) agents assist users with everyday tasks that can be completed in many reasonable ways. Even when their answers are useful, how agents carry out these tasks may not match users' preferences and needs. For example, agents differ in whether they ask clarifying questions or search the web. We introduce HABIT, a taxonomy of 23 behavioral axes in five categories, which three authors and three LLMs derive bottom-up from 408 agent trajectories across 17 domains. On held-out tasks, HABIT distinguishes models more clearly than existing taxonomies of human values and agent acti…
- arXiv · Published · First archived
Agentic Network Traffic Monitoring ↗
As the use of agentic artificial intelligence increases in nearly every industry, there exists a widening attack surface. It is necessary to monitor agents to ensure that agents are acting in a way that is aligned with the users intent. Auditing an agent's network traffic provides a clear record of the agent interactions. This work presents a novel approach to monitoring the network traffic of agentic systems using complex valued hypersparse traffic matrices by integrating DBOS (DataBase OS), the OneSparse PostgreSQL database, and the GraphBLAS math library. To develop these concepts an agenti…
- Hacker News · Posted on Hacker News · First archived
Show HN: Policy gateway for AI agent tool calls, with a tamper-evident log ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
A test of agentic workflows for software engineering ↗
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.