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 ↗856 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.
- GitHub · Repository created · First archived
nanaism/yomiyasu ↗
AI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese
- Hacker News · Posted on Hacker News · First archived
HN: Humanbound|Open-source red teaming for AI agents, free hosted tier ↗
Hacker News discussion.
- GitHub · Repository created · First archived
fdtaljaard/claude-skills ↗
Reference-backed ERP assistants for Claude Code — Sage 300 (Accpac), Sage 200 Evolution (Pastel), and SAP Business One. A Claude Code plugin marketplace for consultants and integrators.
- Hacker News · Posted on Hacker News · First archived
AA-AgentPerf-Local: Benchmarking local AI agents on laptops and workstations ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN:I built an AI agent team that recreates the style of any video ↗
Hacker News discussion.
- GitHub · Repository created · First archived
AFK-surf/Comma ↗
The sessionless, relentless personal agent. Open source alternative to Muse, Dots, Instinct and Town.
- Hacker News · Posted on Hacker News · First archived
How to Manage a Team of AI Agents at Month-End ↗
Hacker News discussion.
- arXiv · Published · First archived
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents ↗
Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existing skill evolution remains largely confined to the text space: an optimizer must diagnose success and failure patterns, and revise skills solely from long execution trajectories and sparse task outcomes. This text-only paradigm leaves the agent's internal representations, which contain rich records of its evolving execution state, outside the skill optimization loop. We ask whether an agent can improve its external textual skills by reflecting o…
- arXiv · Published · First archived
MADBench: Benchmarking the Security of Multi-Agent Debate ↗
Multi-agent debate (MAD) can improve large language model (LLM) reasoning by allowing multiple agents to exchange and critique their answers to the same task. However, the interactions that enable agents to correct mistakes can also spread adversarial errors and steer the agents toward an incorrect answer. Although some efforts have been made to examine particular attack types on MAD, systematic evaluation of MAD under diverse attacks remains limited. A central question is whether debate mitigates adversarial influence or amplifies it. In this paper, we present MADBench, a benchmark for evalua…
- arXiv · Published · First archived
RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent ↗
Long-horizon agent interactions generate useful but noisy experience, and retraining models to absorb it is expensive. Context-evolving agents therefore need memory extraction methods that improve with more test-time compute without relying on gold labels. We propose RefCon, which combines sequential self-refinement with parallel self-contrast to extract higher-quality memories without gold labels. Evaluated on AppWorld and BFCL-V3 across multiple context-evolving agent frameworks, RefCon delivers strong and consistent gains, including relative improvements of 21.6% on ACE and 16.6% on ReMe ov…
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.