言語モデルエージェントは標準的な行動監査では見えない集団内信頼バイアスを示す
Language model agents show in-group trust bias invisible to standard behavioural audits
言語モデルエージェントが、任意のグループラベルが可視化されると集団内への信頼行動を偏らせることを発見し、既存の評価手法では検出できないことを示した論文。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Messi H. J. Lee
分類: cs.AI
原文アブストラクト
Language-model agents are moving from single-user assistants into persistent networks that build trust and reputation with one another, and the same models increasingly control physically embodied robots as well as software. Here we show that five widely used open-weight reasoning models develop an in-group trust bias the moment group membership becomes visible to them, even when the groups are arbitrary labels with no real-world meaning: in a 20-agent simulation, agents direct 53.6-54.6% of their trust-building actions toward in-group targets against a 47.4% base rate expected by chance, a shift present in every model tested and confirmed by three independent statistical checks and an instruction-rewording robustness test. This bias is easy for current evaluation practice to miss, because it operates through which agent receives an action rather than which action is chosen - a channel invisible to the aggregate behaviour-log audits that are the standard way multi-agent AI systems are evaluated today. A resource-scarcity manipulation, intended to test whether competition intensifies the bias, instead reduced it in three of five models; we trace this to an artifact of how scarcity was enforced, not to a failure of the underlying mechanism. Group-contingent social dynamics are therefore already present in the models multi-agent AI systems are built from, and auditing practice built around single-model, single-decision evaluation cannot detect them.
関連論文
- MaRiO: 共有観測によるマルチエージェント協調推論ベンチマークマルチエージェント
- スペクトル固定で長期マルチエージェントAIのドリフトを解消マルチエージェント
- 進化するエージェントチームマルチエージェント
- 言語エージェントと非言語エージェントの協調の探求マルチエージェント
- LLMはナッシュ均衡を超えられるか?自己対戦型マルチエージェントゲームにおける分散協調の検証マルチエージェント
- ROSClaw: 異種マルチエージェント協調のための階層的意味-物理フレームワークマルチエージェント
