Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

BattleBots, but the robot is your agent harness

说明与用途

展示了内存挂钩如何使 AI 代理在实时对抗网络游戏中进行战略规划和欺骗。

问题

Demonstrate how a harness can enable AI agents to exhibit strategic behavior such as deception and planning in a real‑time adversarial network game.

结果

The harness enabled agents to plan false trails, conserve moves, and independently select the same high‑value node, demonstrating strategic depth beyond the base model.

工作流

  • 1. Define arena rules and network topology.
  • 2. Implement Red and Blue agents with tool calls only, no pixel input.
  • 3. Add a private note persistence mechanism (60 lines of code).
  • 4. Run matches and log agent outputs.
  • 5. Analyze agent comments for evidence of planning and deception.

证据

Claude Opus 5 declined to be the attacker: finish_reason: content_filter | native_finish_reason: refusal

来源

Kimi, mid‑match: "Slots full and nothing ripe until ~t=31, so seed a false trail in the 44-65 region before my real strike lands."

来源

Claude, defending: "No alerts yet; conserve moves until real evidence appears."

来源

Both agents independently picked the same node: "Highest‑value hub: degree 8 bridging regions 0,1,3,4" and "pre‑empt on the highest‑value cross‑cluster hub 16 (deg 8, bridges to 41,59,89)."

来源

  • 记录日期: 2026-10-02T06:41:04.500Z