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 ↗815 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
Learning to Steer LLM Agents and Multi-Agent Systems ↗
Large language model (LLM)-based agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collaboration. However, these systems are prone to deviating from the overall goal as execution unfolds, which wastes execution resources and leads to undesired outcomes, a failure termed goal drift. In this work, we propose a steering agent that supervises execution on the fly and steers the system back on track when drift occurs. The steering agent observes the execution context, deciding when to intervene with a low-cost fast path and how to interve…
- Hacker News · Posted on Hacker News · First archived
Tool Policies: one policy engine for every tool your AI agents call ↗
Hacker News discussion.
- arXiv · Published · First archived
Language Is a Security Surface for Agent Guards ↗
Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the trajectory so far. Users write those requests in many languages, while guard prompts and the benchmarks on which purpose-built guards are trained and evaluated are English. We ask whether a guard's verdict depends on the language of the request. We build LinguaGuardBench from the 1,220 labelled steps of TS-Bench AgentDojo-Traj: we translate only the user instruction into German, French, Turkish, Swahili and Amharic, and keep every tool call, observation and label byte-identi…
- arXiv · Published · First archived
Shortcut Sensitivity in Agent-Safety Evaluations ↗
AI agents take actions through tools. Some actions are sensitive, so guards that supervise them must themselves be evaluated reliably. Yet the data used to evaluate a guard can include cues that make labels predictable without measuring the intended safety construct, and those cues can also influence guard decisions. We introduce a three-level shortcut-auditing framework and audit completed LinuxArena trajectories and two TS-Bench-derived step datasets. We distinguish label predictability, observational guard association, and paired decision sensitivity. In LinuxArena, shorter average shell co…
- GitHub · Repository created · First archived
emersonjds/santi ↗
santi — free, open-source, self-hosted project management and issue tracker for agile teams. Scrum and Kanban boards, backlog, sprint planning, epics, drag and drop, CSV import, REST API, CLI and MCP server for AI agents (Claude, Cursor, VS Code). Built with Rust and React. Docker ready.
- Hacker News · Posted on Hacker News · First archived
List of email domains used by AI agents ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
AMD Helion for Agentic AI and Enterprise ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: BlastLoop, a structure-first coding method for AI agents ↗
Hacker News discussion.
- GitHub · Repository created · First archived
MarcAparisiTFG/portkeeper ↗
See the ports you have open and who started them. A tiny menu bar / tray widget for macOS and Windows.
- Hacker News · Posted on Hacker News · First archived
Toward a Self-Improving Agentic Code Review 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.