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 ↗857 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
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents ↗
Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no supervision for intermediate actions. On-policy self-distillation (OPSD) offers token-level learning signals through privileged rescoring, but directly applying it to CUA online training presents two challenges: fixed guidance may become misaligned with the student's current state, and guidance-induced probability shifts may conflict with step-level correctness. We introduce ComputerSD, an online sel…
- Hacker News · Posted on Hacker News · First archived
Show HN: Kyno – Direction as a first-class primitive for AI agents ↗
Hi folks, I've been lurking here for a while, and after almost two months of building, I finally dared to share what I've been working on. It's called Kyno (pronounced KAI-no). It's what I call a coherence control plane: it treats direction as a first-class primitive, expressed as a constitution with a mission and principles that agents can pull at each step of a workflow. The goal is to enable principled decision-making, bottom-up agency, and se…
- arXiv · Published · First archived
EviRover: Reinforcing Agentic Perception Beyond a Glance ↗
Visual perception is conventionally formulated as a one-shot prediction from a single glance at the image, under the assumption that the image content and the model's parametric knowledge suffice to resolve the query. This assumption often fails in real-world scenarios that hinge on fine-grained visual details or require knowledge-intensive and up-to-date information. We term such cases \textit{perception under insufficient evidence} and formulate perception as an agentic process that can obtain information beyond a single glance. To address the absence of data for this setting, we design two…
- arXiv · Published · First archived
PhantomEnvironments: Training LLM Agents in Fictional Worlds ↗
Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon interaction, and scale cheaply. Existing approaches rely on costly human-curated data or on LLM-generated environments that risk hallucinations and benchmark contamination. We show that LLMs can instead be trained into capable search agents using synthetic environments generated entirely by rules, whose generation requires no LLM and has zero marginal cost. We build PhantomEnvironments, multi-turn RL environments from fictional worlds, where agents m…
- Hacker News · Posted on Hacker News · First archived
Would you use an AI agent instead of making your next operations hire? ↗
Hacker News discussion.
- GitHub · Repository created · First archived
ATASTECH/pitroom ↗
A free pit crew for your expensive coding agent: the superpowers development workflow, run by cheap workers.
- Hacker News · Posted on Hacker News · First archived
AI: LLMs, Agents, Work, and Us – Engineers. Personal Thoughts ↗
Hacker News discussion.
- GitHub · Repository created · First archived
jamiezigelbaum/expert-agents ↗
Machinery for creating and operating cited expert agents on OpenClaw (plugin + Vertex RAG worker)
- Hacker News · Posted on Hacker News · First archived
Show HN: Beyond "chat with your database" – agentic data exploration ↗
Business intelligence is changing. AI can now do more than turn a question into a single SQL query: it can investigate a question through a series of queries, examining the result of one query to decide what to query next. Today, to answer a business question against a database, analysts use a tool like Tableau: they select relevant data, build an initial view using fields, filters, calculations, and visualizations, then look for patterns or anom…
- GitHub · Repository created · First archived
CSantosM/agent-watch ↗
Agent Watch: watch your coding agents from the VS Code status bar: one dot per session (working, waiting or idle), what each is doing, the files it changed. Supports Claude Code.
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.