Artificial agents can be made to ``help'' through explicit social rewards, hard-coded prosocial bonuses, or direct access to another agent's state. I isolate a narrower route: homeostatic coupling. Building on ReCoN-Ipsundrum, I add a scalar homeostat and a social coupling channel while keeping action selection self-directed: the planner scores only the actor's predicted internal state, with no partner-welfare reward. In a one-step FoodShareToy, an exact solver finds a switch from EAT to PASS at $λ^\star \approx 0.91$ for the default state. In a multi-step SocialCorridorWorld, partner-state access without coupling leaves behavior unchanged, whereas coupled agents fetch, carry, and pass food to the partner. Sham lesions preserve helping; coupling-off and shuffled-partner lesions abolish it. A coupling/load sweep shows that coupling creates a low-load helping regime but does not guarantee rescue under higher metabolic load. This is not a claim about empathy, altruism, consciousness, or moral status. It is a minimal ALife demonstration that, in this controller, partner-state access is behaviorally inert unless partner distress is routed into self-regulation.

翻译：人工智能体可以通过显式社会奖励、硬编码利他奖励或直接获取其他智能体的状态来“帮助”他人。我提炼了一条更窄的路径：稳态耦合。基于ReCoN-Ipsundrum，我添加了标量稳态器和社交耦合通道，同时保持行动选择的自定向性：规划器仅对行动者的预测内部状态进行评分，不包含任何伙伴福利奖励。在单步的FoodShareToy中，精确求解器发现在默认状态下，从“吃”切换到“传递”的阈值约为$\lambda^\star \approx 0.91$。在多步的SocialCorridorWorld中，无耦合的伙伴状态访问不会改变行为，而耦合的智能体会为伙伴获取、携带和传递食物。伪损伤保留了帮助行为；关闭耦合和打乱伙伴的损伤消除了帮助行为。耦合/负载扫描表明，耦合创造了低负载帮助机制，但不能保证在更高代谢负载下的救助。这并非关于共情、利他、意识或道德状态的论断。它是一次最小的人工生命演示：在该控制器中，除非伙伴的痛苦被引导进入自我调节，否则伙伴状态访问在行为上是惰性的。