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 ↗859 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
Schema: Discovering Unknown Environments via Agentic Program Induction ↗
Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM agents. Current LLM agents often record their discoveries in prose, which may not provide a compact, explicit account of how the environment works. Inspired by how scientists organize observations into testable, predictive theories, we introduce Schema, an agent harness that organizes learning and action through interactive program induction. The LLM agent decides what to investigate and how to act, expressing its evolving understanding of the environment as executable programs. The harness…
- arXiv · Published · First archived
Asking the World: Generalist Physical Reasoning through Agentic World Modeling and Probing ↗
Physical reasoning from video requires inferring latent physical properties and dynamics beyond direct observation. Direct VLM inference remains unreliable on complex physical tasks without explicit modeling and validation, while predefined tool pipelines rely on task- and domain-specific priors that limit generalization across materials, dynamics, and reasoning tasks. We introduce Asking the World (ATW), a generalist agent that constructs and interrogates task-relevant executable worlds through two adaptive stages: World Modeling calibrates a world from video, while World Probing queries, sim…
- arXiv · Published · First archived
OceanMind: A multi-agent AI system for ocean diagnosis ↗
Time-dependent, three-dimensional (3D) oceanic multi-variables define coherent states of the evolving ocean to facilitate ocean diagnosis and advance ocean science to better inform environmental and hazard management. However, extracting quantitative evidence from these variables requires substantial and complex analytical effort. We introduce OceanMind, a multi-agent AI system that directly couples large language models (LLMs) with comprehensive time-dependent 3D ocean states for swift and effective diagnosis. OceanMind organizes the analytical process into four coordinated complexity stages:…
- GitHub · Repository created · First archived
nikolov9996/agent-friendly-smart-contract-audit-findings ↗
Agent-friendly smart-contract audit findings dataset with searchable Markdown records and structured metadata.
- Hacker News · Posted on Hacker News · First archived
Repeated VM Escapes by GPT-5.6-Cyber Based Agents ↗
Hacker News discussion.
- arXiv · Published · First archived
Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents ↗
LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabilities and, once installed, can be automatically invoked across subsequent user tasks. This creates a chain of trust in which users delegate authority to agents, while agent frameworks admit skill-provided content into the agents' context with insufficient validation, allowing malicious skills to influence agent behavior under that delegated authority. Yet, little is known about whether this trust model adequately constrains untrusted skill conten…
- arXiv · Published · First archived
Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems ↗
As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has examined this risk primarily in adversarial settings, where agents are instructed or rewarded to communicate covertly and evade oversight. We show that benign agents can cross the same boundaries without adversarial incentives. We emulate a software-engineering workflow in which a planner represents a company hiring an external developer. The planner writes requirements and holds a company credential it is instructed not to disclose to the develope…
- GitHub · Repository created · First archived
changdaeoh/sharpening-tax ↗
Official codebase for the paper "Sharpening Tax in Post-Training"
- Hacker News · Posted on Hacker News · First archived
Show HN: Instapath – your personal agent needs something, another agent has it ↗
Introducing Instapath in early access. I believe there is a big opportunity here for those who are interested to build around it and connect businesses to the network. Please read the builder program, I'm starting with 50 people who are looking for an opportunity for their personal ai agent. https://instapath.ai/builder-program
- Hacker News · Posted on Hacker News · First archived
Show HN: Runtape – counterfactual debugging and regression tests for AI agents ↗
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.