BattleBots, but the robot is your agent harness

Описание и применение

Показано, как хранилище памяти и планирование позволяют ИИ‑агентам вести стратегические действия, включая обман, в сетевой игре с реальным временем.

Задача

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

Результат

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.

Рабочий процесс

• 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.

Доказательства

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

Источник

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."

Источник

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

Источник

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)."

Источник