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 ↗854 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.
- Hacker News · Posted on Hacker News · First archived
Slowly, then all at once: AI agents that know how a company works ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
GPT-6 Astra plays World of Warcraft for the first time with agent-wow ↗
Hacker News discussion.
- GitHub · Repository created · First archived
hamzafer/claude-code-mods ↗
Claude Code mods: plugins built on hooks that add live lines above the prompt, guards, panes and games. Context bar, usage meter, Codex review watch, Markdown preview, Spotify now playing and more.
- Hacker News · Posted on Hacker News · First archived
Show HN: Moon-dev-tools – rust and egui agentic task board, shell and reviews ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
How to Almost Fry Your AI Agent (and Your Mac Mini) ↗
Hacker News discussion.
- arXiv · Published · First archived
D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels? ↗
GPU kernels generated by large language model (LLM) agents can remain less efficient than expert implementations, but runtime alone does not reveal how the gap relates to design discovery and implementation. We introduce D2K-Bench, a diagnostic benchmark of 26 tasks and 85 workloads that measures how effectively agents translate expert design guidance into efficient GPU kernels. The guidance covers L1: high-level algorithmic insights, L2: dataflow design, and L3: low-level optimization tricks, including dependencies among these levels. Pairwise runs with and without guidance share task descrip…
- arXiv · Published · First archived
AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement Learning ↗
Long-horizon LLM agents are typically trained with sparse outcome rewards, making trajectory-level objectives too coarse to distinguish the contribution of individual decisions. Step-level credit assignment provides finer-grained supervision, but its estimates can be unreliable because observed returns also depend on subsequent actions, environment transitions, and trajectory length. We propose AdaStep, an Adaptive Step-credit weighting method that controls how strongly each group-derived local advantage modifies the trajectory-level signal. We formulate this weighting as a mean-squared-error…
- Hacker News · Posted on Hacker News · First archived
WSP WordPress MCP – Connect AI Agents to WordPress ↗
Hacker News discussion.
- arXiv · Published · First archived
Toward SLM-based agentic task-tool intent matching ↗
Tool-equipped AI agents use tool calls to access data and act on external systems. Horizontal growth of agentic systems increases the number of these interactions, and further motivates the need for automated, per-call oversight that can operate at low latency and/or on-prem. Conventional authorization schemes can determine whether an agent is allowed to invoke a tool, but cannot assess the agent's underlying cognition, specifically, whether the tool selection represents a logical, relevant step toward satisfying the intent of the task or not. Consequently, an allowed call may still deviate fr…
- arXiv · Published · First archived
Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It ↗
As LLM agents decide on users' behalf which product to buy, which hotel to book, or which paper to cite, a preference for items from certain sources (the sites or services they come from) shapes what users receive and which sources are selected. We study source preference in end-to-end search with 12 agent models across three domains. Comparing items from different sources that satisfy the same requirements at the same position, we find that each model prefers some sources and avoids others in every domain, largely agreeing on which. This preference can outweigh how well items satisfy the requ…
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.