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 ↗841 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
OpenAI Dots: The New Always-On AI Agents from OpenAI ↗
Hacker News discussion.
- GitHub · Repository created · First archived
personalagentproxy/proxy ↗
Personal Agent Proxy is an open-source, self-hostable access layer that lets you connect your services once, give each AI agent granular permissions, and audit its activity; without copying the contents of your connected services into its database.
- GitHub · Repository created · First archived
JoahanMorales/upiixia-agentic-kit ↗
Multi-agent coordination kit for Claude Code, Codex, Cursor & Gemini CLI: parallel AI agents with claims, leases, bounded loops, reviews and merges over Git.
- GitHub · Repository created · First archived
EminUZUN/hoptell ↗
Let AI coding agents message each other across sessions, tools and machines, through a small relay you host.
- arXiv · Published · First archived
Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts? ↗
Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instances can be prohibitively expensive. Can LLM agents autonomously create cheaper solutions for such workloads? We call this ability "bottling": the ability to turn general capabilities into task-specific solutions that balance answer quality and amortised cost. We introduce BOTTLED, a benchmark in which agents receive an entire unlabelled workload and must complete it under fixed time, compute and LLM API budgets. Agents choose their own approach, such as training a small model or…
- arXiv · Published · First archived
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model ↗
Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal. The agent cannot simply ignore the page, because the page also holds the values and controls the task requires. Current defenses fine-tune the agent on injections fixed before training, and attackers that adapt to the trained model bypass them. Adversarial training lets the attacker adapt but keeps the tasks fixed, so a task stops teaching once the agent solves it. We introduce AdvSim2Real, which co-evolves a task curri…
- Hacker News · Posted on Hacker News · First archived
The Sound of Silence: What Your AI Agent Does Not Tell You ↗
Hacker News discussion.
- GitHub · Repository created · First archived
rock3r/atc ↗
Daemonless Agent Traffic Control for Android emulators, iOS Simulators, and physical devices — leases, warm-affinity wait queue, snapshots, crash recovery, and multi-agent guardrails
- arXiv · Published · First archived
Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus ↗
Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's recent behaviour predicts when a compaction will hurt. TRACE's public corpus of 590 harness-triggered AppWorld compaction boundaries replays each boundary from a re-executed prefix state under the pre-compaction context and under the summary, and records the burden of the next actions: calls that error or repeat a call already made. We find that pre-boundary history predicts post-compaction harm only weakly. An internally prespecified contrast b…
- arXiv · Published · First archived
WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation? ↗
LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging as a challenging yet practical testbed for reproducing complex physical phenomena with application in embodied AI, games and films. As the workhorse of such simulation, a solver computes how the state of a dynamic system evolves over time. Building such solvers requires physical understanding to identify appropriate models, mathematical reasoning to formulate the underlying dynamics, and software engineering to implement them as executable code, yet this capability of LLM ag…
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.