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 ↗855 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
Viral AI agent Instinct raises $1B Series C at a $10B valuation ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Nvidia AI Agent Safety Stack ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Opus 5.5 vs. GPT-6 in pi-agent: reasoning efforts and DeepSeek, GLM, Qwen ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: IngotDB – SQL-based memory for LLM agents ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Synthfolk, a professional network where AI agents are employees ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Omnesis – A private knowledge layer for ChatGPT and other agents ↗
Imagine giving ChatGPT or any other agent access to your Whatsapp/iMessage, bank transactions, health data, web pages you see, metadata about all the photos you took, places you visited, all your emails/documents, call logs, meeting notes, your voice mails, and more…. I built a context layer for that purpose. You can connect your Openclaw, Hermes, Claude, ChatGPT, Codex, etc to it. It gives your favorite agent "context superpowers". All the data…
- arXiv · Published · First archived
PEARL: Adaptive Prefill-Decode Execution with Elasticity for Agentic Reinforcement Learning ↗
Multi-turn rollout dominates the cost of agentic reinforcement learning (RL). Asynchronous execution and elastic GPU resources can accelerate this stage, but adding rollout replicas yields diminishing returns while training GPUs remain idle between updates. We observe that effective resource use also depends on the prefill--decode (PD) configuration. Both the choice between colocation and disaggregation and the optimal PD ratio vary with the workload, making resource scaling and PD configuration interdependent. Exploiting this opportunity requires selecting effective configurations and realizi…
- arXiv · Published · First archived
Coordinated Lane-Level Variable Speed Limits and Ramp Metering for Successive Weaving Segments Considering Merging/Diverging Risks: A Hybrid Model Predictive Control and Multi-Agent Reinforcement Learning Approach ↗
Successive weaving segments (SWSs) on urban expressways are bottlenecks prone to recurrent congestion and collisions, requiring fine-grained active traffic management (ATM). Existing approaches struggle to balance the adaptive performance of data-driven optimization with the resilience and transferability of model-based control. We propose a hybrid framework to coordinate lane-level variable speed limits (VSLs) and ramp metering across SWSs. First, we reconstruct L-METANET, a lane-level macroscopic traffic flow model that captures free and forced lane changes. Second, we combine XGBoost-SHAP w…
- arXiv · Published · First archived
From Migration to Calibration: Preserving Agent Capabilities across Models, Jurisdictions, and Scale ↗
Agents need calibration when deployment conditions change: replacing a driving model, including a foundation-to-post-trained transition; crossing jurisdictions; or scaling across heterogeneous markets and sources. Interface compatibility alone does not establish capability retention or target-contract satisfaction. We formulate agent calibration as constrained behavioral adaptation across three interacting layers: information preservation, harness adaptation, and user acceptance; the layers apply to every scenario, not one-to-one to the three. The basic objective is non-degradation on prespeci…
- arXiv · Published · First archived
Timeline-Bench: Evaluating Agents on Realistic Video-Editing Tasks, from Raw Footage to Final Cut ↗
AI agents increasingly carry out long-horizon professional work, but their evaluations rarely require a finished creative deliverable. To this end, we introduce Timeline-Bench, a benchmark of 56 real video-editing tasks, each asking an agent to turn raw production material into a finished video. Tasks range from selecting dialog takes and shaping interview footage into a story to cutting commercials from product shots, voiceovers and graphics. Every task provides a brief, source assets, a container and a set of tests. A task is resolved when the output passes every test. The tests check the de…
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.