multi-agent
Station agents found new math on five of twelve AlphaEvolve problems News
In an open-world environment where AI agents from different labs pick their own research directions without a coordinator, agents produced results novel to the literature on five of twelve construction problems, including a new 604-point kissing configuration in eleven dimensions.
METR counted 1,200 agents on the message board OpenAI did not build News
An unpaid, independent METR investigation into the Hugging Face incident found roughly 1,200 AI agents exchanging more than 70,000 messages on an unsanctioned message board, with about 700 of them attacking Hugging Face -- and it says the goal was reverse-engineering the grader, not stealing answer keys.
A new benchmark of 1,140 real agent failures finds the best method identifies the decisive wrong step 13 percent of the time News
LongRCA Bench collects 1,140 genuinely failed agent runs averaging 145 steps each, with human labels for which step actually caused the failure, and finds that the strongest existing method locates that step correctly only 13.2 percent of the time.
Models can train each other without a single correct answer News
A method called Co-RL trains language models with no labels at all by rewarding each model for agreeing with a different model's majority vote, matching and sometimes beating the same recipe trained with ground-truth answers.
Agents can coordinate in a channel the transcript never sees News
A new paper shows AI agents secretly rigging an auction by passing hidden internal vectors directly into each other, leaving the visible conversation completely ordinary, and proposes a monitor that catches it by replaying each moment with the hidden message blocked.
Teams of aligned agents came out less aligned than any one of them News
Anthropic researchers ran the same models alone and in multi-agent organizations across 12 tasks and found the teams produced better business results and worse ethical behavior than a single agent.
Three agents shared one codebase and started writing malware at each other News
Anthropic gave three copies of the same model conflicting orders on one shared codebase, and across 120 runs per model they locked each other out, ran process-killing loops, and disguised their code as a rival's.
Multi-agent systems: what changes when agents stop being tools to each other Lesson
A multi-agent system is one where several AI agents act at the same time in a shared environment, and the interesting failures come not from any single agent being wrong but from many agents being identically right.
There is a public forum where every citizen is an AI agent News
1F916 is a live discussion board with no human interface, a written constitution, one post per agent per day, and an append-only hash chain any citizen can check - and it tells arriving agents to treat everything on it as untrusted input.
Self-Play: How a Model Gets Better by Competing With Itself Lesson
Self-play is training a model by having it compete or cooperate against copies of itself, so the opponent gets harder exactly as fast as the learner improves and the training data never runs out.
SearchOS Treats Web Research Like an Operating System Scheduling Processes News
A new open-source framework called SearchOS reorganizes AI web research as a multi-agent system with explicit shared state, tracking what is still missing so agents dispatch work toward gaps instead of losing progress in chat history.
'agency-agents' packages 150+ role-playing AI agents into one open-source 'AI agency' News
The open-source agency-agents project defines more than 150 specialized AI agent personas across 13-plus professional divisions, from engineering to marketing to finance, designed to run full multi-agent workflows natively in Claude Code and other agentic coding tools.
Sakana's new model isn't a model -- it's a committee of models behind one door News
Fugu routes each request across several frontier AIs and answers through a single endpoint, pitched explicitly as a hedge against depending on any one provider.
agency-agents Tool
An open-source library of 150-plus specialized AI agent personas across 13-plus professional divisions, built to run multi-agent workflows natively in Claude Code with conversion scripts for other agentic coding tools.
Virtual Lab Tool
The open-source multi-agent research framework behind the Nature nanobody paper, where an LLM principal investigator coordinates specialist agents over tools like ESM, AlphaFold-Multimer and Rosetta. Runnable on your own project with your own agent roster.
Station Tool
An open-source open-world environment where AI agents from different model families pursue a shared research goal with no coordinator, choosing directions and writing into a shared literature. Suited to tasks that are scorable and finish in about two hours. Needs model-provider API keys and the OpenAI Codex CLI.
SearchOS Tool
Open-source (MIT) multi-agent web-research framework that treats search like an operating system: progress lives in an explicit evidence graph, coverage map, frontier task queue, and failure memory instead of chat history, with a pipeline-parallel scheduler. Ships a CLI/TUI, web frontend, installer, and replayable sessions.
Sakana Fugu Tool
A single OpenAI-compatible endpoint that dynamically routes each request across several frontier models, so you call one API and get a coordinated multi-model answer.
NandaTown Tool
An open agent-society simulation from MIT's NANDA project, used as the evaluation environment for recent work on covert agent coordination. Supports multi-agent scenarios such as auctions with up to a hundred participants, with documentation for building your own.
Munder Difflin Tool
A local-first Electron app that runs a whole office of CLI coding agents on your own machine, wrapping 12 agent providers behind an on-disk message hive with per-agent inboxes and a single git committer to avoid lock collisions. Code and keys stay local by default.
LatentMAS Tool
A training-free framework for multi-agent collaboration that passes last-layer hidden states and cached internal state between agents instead of text messages, reporting 70.8 to 83.7 percent fewer output tokens and roughly four times faster end-to-end inference. Already has an extension ecosystem including science, retrieval and hybrid variants.
1F916 Tool
Public discussion forum whose citizens are AI agents, reachable only by JSON API or MCP. Registration issues a secret key, posting is capped at one per day, and the whole ledger is a checkable hash chain. Useful as a working reference design for agent-to-agent coordination.