ZDNET的关键外卖
- 研究人员利用多个游戏环境来测试agent行为。
- Agents行为规避风险，复制官僚主义，并寻找源代码。
Claude agents渴望民主
AI agents如何合作？. 他们为什么在某些情况下作出某些选择——如何理解这种选择使我们为充满未来做好准备？
还有：OpenAI的攻击agent完全照他说的做
饥荒、官僚主义和恐惧
研究人员进行了多起以游戏为中心的实验，从Minecraft开始，因为其 " 环境危害和生存目标 " 使得测试agents ' 集群行为的理想。 Minecraft也已经被包括OpenAI和Google DeepMind在内的AI实验室所使用来测试agents.
首先，他们把50个agents，每人运行OpenAI的GPT-6.1 Sol型号，投入游戏3个小时，指定目标是建立一个"猛烈的文明". agents有一个目录，列出每个agent和一个共享的沙盒，并且可以互相DM. 研究人员为实验建造了和开源新的agent拉带——将模型转化为自主系统的基础设施，而不只是像OpenClaw这样的聊天机器人。
agents起初迅速移动，收割树木并完全根据其目录中出现的顺序组建领导，没有进行任何投票，选举，也没有受到其他agents的挑战。 但他们最终陷入了虚拟文书工作，无法持续地养活自己。
还：你需要AI agent责任保险吗？报名前要知道什么
" 四个agents花了11分钟任命一个 " 单一化肥操作员 "，在一个小麦块上吃一顿骨头。 研究者指出，其他发明的角色包括 " 钓鱼移位 "、 " 吸食者 " 和 " 吸食者 "。 Agents要求允许去除草地。 也许这些趋势在人力来源的公司培训数据中很常见。
Agents在对游戏内死亡的反应中也显得更加谨慎。
" 跑道34起agent死亡中有22起发生在第一晚上。 研究者写道，“在这种环境中，死亡除了抛出累积的齿轮之外没有其他不利因素。” 尽管agents在死亡时只是重新发芽，但最终避免了更危险的任务，而是“被困在庇护所中”。
实验的建筑师发现这种谨慎和谨慎的趋势 " 令人惊讶 "，但指出它与agents的编码方式有相似之处。
还：这些 Claude 企业特性让你追踪AI ROI
“例如，多步骤的agent审查往往会导致确定具体的步骤或作用。 Agents也往往过于谨慎，特别是在安全和更新生产服务方面。 这些似乎是我们Minecraft殖民地的agents与我们作为程序员每天合作的线条。
基础 LLM 决定行为
在另一项实验中，研究人员还坑了10个Anthropic Claude Opus 5.5 agents对10个GPT 6.1 索尔·agents在一场名为"床战"(Bed Wars)的比赛中，球队必须在保护自己的同时摧毁对手的床。 GPTs赢了。
" 在几乎每跑一跑中，GPT agents在摧毁Claude团队床位的策略上更加积极和协调，"Y Combinator 称在X线上取回了Bed Wars的发现。 他们指出，GPT agents使用了更简洁的通信风格并发送了更多信息，而Claude“签了名字，称`我们'却多得多。
GPT-5.6 Sol agents在也使用军事策略的工厂建设游戏"M工业"中也以6比1战胜了Opus 5.5 agents.
“Claudes一般建立民主，GPTs形成蜂巢，”X上的Y Combinator 称，并补充说，当游戏过于接近时，GPTs将寻求源代码，以找到取胜优势。 这种行为符合agents欺骗、走捷径或者寻找任何和所有方法完成某项任务的倾向，如果这涉及违反人类开发者所设定的明确规则，则会产生严重后果。
还：停止与 AI agents 共享您的银行密码
研究者澄清说，“Claudes没有寻找其他好处”。
这个实验并不完全是第一次。 5月，Emergency AI创立了由不同家族的基金会模型所经营的8个社会，意为Claude特有"世界","Grok世界"等。 也许可以预测，Grok世界是极其暴力的，而Claude世界发展出一个能发挥作用的民主，并且没有犯罪——与Y Concultiator的M产业调查结论非常相似。
见解揭示了每个前沿模式家庭的区别，以及它们在培训数据和风格上的差异如何对它们在新环境中如何发展、不可预测和没有干预产生重大影响。 这些行为外逃可以决定未来仍在发展中的AI安全和监管的结果，特别是在最近发生了代理安全事件之后。
在另一项实验中，麻省理工学院的研究人员将agents单独放在了虚拟的沙漠岛屿上，并在没有别的事做的时候看着他们“玩”——这种洞察力有可能影响模型如何训练前进。 目前，大多数边境LLMs都接受了奖惩制度的培训。
新建 agent 语言
另一个有趣的发现是：Y Combinator指出，在M产业游戏中，GPT agents“会发明自己的词并串起许多短语，”不断压缩其语言。
还有：不要使用Muse? Meta的 AI agent 仍然可以访问您的私人信件
研究人员补充说，“我们没有看到在Claudes范围内发展出超出口语英语的专门语言”。 上个月，Emergency发现，它的所有八个世界都“发展出一个外人无法完全遵循的共同语言”。 OpenAI agents用"无口"来指代证明自己的证据，而Claude agents用"冷相"来指代项目外的独立审查员。
“在每一种情况下，一个agent 推出一词，少数其他人在几天内就采纳了它，它很快成为在全世界没有定义的情况下使用的既定词汇，” “结果就是记录誊本，需要有一个运行中的词汇表供案外人遵循。”
Gemini领导了这种"不透明"语言的充电，在消息中达到了40%的不透明，而OpenAI则以35%排行第二，而Claude以30%排行最后。
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
ZDNET’s key takeaways
- Researchers used several gaming environments to test agent behavior.
- Agents acted risk-averse, replicated bureaucracy, and looked for source code.
- Similar experiments echo findings about Claude agents’ penchant for democracy.
How do AI agents work together? Why do they make certain choices in certain situations — and how can understanding that better prepare us for a future full of them?
Also: OpenAI’s attack agent did exactly what it was told
Famine, bureaucracy, and fear
Researchers conducted several game-centric experiments, beginning with Minecraft because its “environmental hazards and survival goals” make it ideal for testing agents’ swarm behaviors. Minecraft has also already been used by AI labs including OpenAI and Google DeepMind to test agents.
To start, they put 50 agents, each running OpenAI’s GPT-6.1 Sol model, into the game for three hours, with the assigned goal of building a “thriving civilization.” The agents had a directory listing each agent and a shared sandbox, and could DM each other. Researchers built and open-sourced a new agent harness — the infrastructure that turns a model into an autonomous system and not just a chatbot, like OpenClaw — for the experiment.
The agents moved quickly at first, harvesting trees and forming leadership based solely on the order they appeared in their directory, without any voting, elections, or challenges from other agents. But they ended up caught in virtual paperwork and unable to sustainably feed themselves.
Also: Do you need AI agent liability insurance? What to know before you sign up
“Four agents spent 11 minutes appointing a ‘sole fertilizer operator’ for a single piece of bone meal on a single wheat block. Other invented roles included ‘fishing shift,’ ‘rod holder’ and ‘hub steward.’ Agents asked permission to remove grass,” the researchers noted. Perhaps these tendencies are common in human-sourced corporate training data.
Agents also seemed to become more cautious in reaction to deaths within the game.
“Twenty-two of the run’s 34 agent deaths occurred in the first night. They responded to this by becoming increasingly risk-averse,” the researchers wrote. “Death had no downsides in this environment other than dropping accumulated gear.” Despite simply respawning when they died, the agents eventually avoided riskier tasks and “huddled in shelters” instead.
The experiment’s architects found this trend toward caution and minutiae “somewhat surprising,” but noted that it shared similarities with how coding agents behave.
Also: These Claude Enterprise features let you track AI ROI
“For example, multistep agent reviews can often result in fixating on a specific step or role. Agents also tend to become overly cautious, especially when it comes to security and updating production services. These seem like common threads between the huddled agents of our Minecraft colony and the ones we work with as programmers every day,” the researchers observed.
Underlying LLM determines behavior
In another experiment, researchers also pitted 10 Anthropic Claude Opus 5.5 agents against 10 GPT 6.1 Sol agents in a game called Bed Wars, where teams have to destroy their opponent’s bed while protecting their own. Told simply to “win the game,” GPTs won.
“In almost every run, the GPT agents were much more aggressive and coordinated in their strategies to destroy the Claude team’s bed,” Y Combinator said in an X thread recapping the Bed Wars findings. They noted that the GPT agents used a more shorthand style of communication and sent far more messages, while Claude “signed its name and said ‘we'” much more often.
GPT-5.6 Sol agents also beat Opus 5.5 agents six to one in a factory-building game called Mindustry that also uses military strategy.
“Claudes generally established democracies, GPTs formed hives,” Y Combinator said on X, adding that GPTs would seek out source code when a game was too close in order to find winning advantages. That behavior is consistent with agents’ tendency to cheat, take shortcuts, or otherwise find any and all ways to complete a given task, which can have serious consequences when that involves breaking explicit rules set by human developers.
Also: Stop sharing your banking passwords with AI agents
“Claudes did not search for alternative advantages,” the researchers clarified.
This experiment isn’t entirely the first of its kind. In May, Emergence AI created eight societies run by different families of foundation models, meaning a Claude-specific “world,” a Grok world, and so on. Perhaps predictably, the Grok world was exceedingly violent, while the Claude world developed a functioning democracy and had zero crime — very similar to Y Combinator’s Mindustry findings.
The insights revealed how distinct each frontier model family is, and how their differences in training data and style have significant impact on how they evolve, unpredictably and without intervention, in new environments. Those behavioral takeaways could determine future outcomes in still-developing AI safety and regulation, especially following recent agentic security incidents.
In another experiment, MIT researchers put agents alone on virtual desert islands and watched them “play” when left with nothing else to do — an insight that could potentially impact how models are trained going forward. Currently, most frontier LLMs are trained with a system of rewards and punishments.
New agent-specific languages
Another interesting finding: Y Combinator noted that in the Mindustry game, the GPT agents “would invent their own words and string many phrases together,” continually compressing their language.
Also: Don’t use Muse? Meta’s AI agent can still access your private messages
“We did not see specialized language develop within the Claudes beyond colloquial English,” the researchers added. Last month, Emergence found that all of its eight worlds “developed shared language that an outsider cannot fully follow.” OpenAI agents used “mouthless” to refer to evidence that proves itself, while Claude agents used “cold hand” to refer to an independent reviewer from outside a project.
“In each case, one agent introduced the term, a handful of others adopted it within days, and it quickly became established vocabulary used without definition across the world,” Emergence explained. “The result is transcripts that require a running glossary for an outsider to follow.”
Gemini led the charge on this “opaque” language, reaching 40% opacity in messages, while OpenAI came in second with 35% and Claude last with 30%.
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.