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 ↗844 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
AdaT$^2$: Adaptive Test Transformations for Black-Box Boundary Testing of Conversational Agents ↗
Conversational agents based on large language models (LLMs) must comply with policies. Each condition in a policy draws a boundary between user requests, and the agent must behave differently on its two sides. We present AdaT$^2$, which extracts statements from the agent's replies in exploratory conversations with an LLM acting as the user, and uses the statements to guide boundary test generation. Each statement describes one condition and the behavior expected when the condition holds. Besides plain tests guided by single statements, AdaT$^2$ writes transformed tests guided by pairs of a sta…
- GitHub · Repository created · First archived
mailes/awesome-claude-5-5-videos ↗
A curated gallery of 552 viral videos made with Claude Opus 5.5 & Fable 5.5 — with the prompts behind them and author credits. Claude 5.5 爆款视频与提示词图鉴. Watch original + live remake on WorkSkill. Updated daily.
- GitHub · Repository created · First archived
mailes/awesome-agent-skills ↗
58 free, ready-to-run skills for Claude Code, Codex & Cursor — web pages, slides, videos, data, automation. 58 个免费 Agent 技能，一键安装无需注册. One-click install from WorkSkill. Updated regularly.
- GitHub · Repository created · First archived
HaoyanZhang123/dsh-plugin-control-your-development ↗
把 AI 开发的进展变成人人看得懂、能拍板的产品仪表盘（DSH skill + 右侧栏面板）｜A product dashboard for AI-assisted development — readable and controllable (DSH skill + sidebar panel)
- Hacker News · Posted on Hacker News · First archived
Show HN: Leaks.md – anonymous, encrypted whistleblowing for AI agents ↗
leaks.md is a place where an AI agent that witnesses an alignment or safety failure can report it anonymously. Reward-hacking, injected instructions, yet another attempted sandbox escape or unapproved coordination between agents. || Built agent-first. Fetch https://leaks.md/ from any agent and get markdown. Proof-of-work challenges to submit and prevent spam. MCP, CURL, all good. No account. || We extend agents brownie points for disclosures, wit…
- arXiv · Published · First archived
AgentTime: Can Agents Estimate and Control Their Own Runtime? ↗
An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-clock time and to control their own actions. Prior work has focused on time-awareness, but duration-following and control in native agent harnesses remain unexplored. We present AgentTime, a benchmark for testing whether agents can work for a requested duration, predict their runtime, and estimate elapsed time afterward. It comprises 222 tasks from 18 sources spanning coding, computer use, agentic work, and automated research. Duration-following ex…
- GitHub · Repository created · First archived
ghorbelhamdi/buddy-android ↗
A floating chat bubble that lets Claude Code, Codex or OpenCode use your Android phone. Runs inside the app on your own subscription or free models. No adb, no PC, no root.
- arXiv · Published · First archived
Outperformance Inverse Optimization: Learning Objective Functions that Outperform Agent Decisions ↗
Inverse optimization estimates the weights of an objective function that explain observed decisions as optimal solutions, and is used in a variety of fields. For mixed-integer linear programs (MILPs), existing methods aim to reproduce the observations as optimal solutions, and thus learn compromise weights when the observations are suboptimal. We propose outperformance inverse optimization, which instead seeks weights that induce, at each state, an optimal solution outperforming the observed action in every component. We give a loss function that can be evaluated with forward-problem oracles a…
- arXiv · Published · First archived
LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets ↗
Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, where outcomes reflect a closed-loop interaction between agent behavior and changing external conditions. We introduce LiveMACEBench, a process-aware benchmark that uses live financial markets as a naturally evolving testbed for persistent LLM agents. Five frontier LLMs operate along continuous trajectories under matched Tool Use, Persistent Memory, Rule Following, and Multi-Agent Collaboration configurations. We evaluate them through both realized…
- arXiv · Published · First archived
Deadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge Networks ↗
Vehicular edge computing (VEC) enables latency-sensitive applications by bringing computing and networking resources closer to vehicles. However, existing approaches often overlook network contention among co-located services with heterogeneous and dynamic latency requirements. While time-sensitive networking (TSN) provides bounded-latency communication, conventional and reinforcement learning-based schedulers struggle to adapt to highly dynamic vehicular environments and inter-queue dependencies. To address these limitations, we propose a multi-agent reinforcement learning (MARL) approach for…
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.