Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy to deploy but often fragile under distribution shift and strict parsers, while continual parameter-efficient fine-tuning improves reliability at the cost of training, maintenance, and potential forgetting. We identify a critical Lazy Agent failure mode where tool necessity is nearly perfectly decodable from mid-layer activations, yet the model remains conservative in entering tool mode, revealing a representation-behavior gap. We propose Activation Steering Adapter (ASA), a training-free, inference-time controller that performs a single-shot mid-layer intervention and targets tool domains via a router-conditioned mixture of steering vectors with a probe-guided signed gate to amplify true intent while suppressing spurious triggers. On MTU-Bench with Qwen2.5-1.5B, ASA improves strict tool-use F1 from 0.18 to 0.50 while reducing the false positive rate from 0.15 to 0.05, using only about 20KB of portable assets and no weight updates.

翻译：适配领域特定工具调用的大语言模型智能体在面对不断演变的接口时仍显脆弱。提示与模式工程易于部署，但在分布偏移和严格解析器下常显脆弱，而持续参数高效微调虽提升了可靠性，却以训练、维护和潜在遗忘为代价。我们识别出一种关键懒惰智能体故障模式：中层激活几乎可完美解码工具必要性，但模型在进入工具模式时仍趋于保守，暴露出表示-行为差距。为此提出激活调控适配器，这是一种免训练、推理时控制器，通过单次中层干预，借助路由条件混合调控向量及探针引导符号门，在抑制虚假触发的同时放大真实意图，实现面向工具领域的精准干预。在MTU-Bench基准上结合Qwen2.5-1.5B模型，ASA将严格工具使用F1值从0.18提升至0.50，同时将假阳性率从0.15降至0.05，且仅需约20KB可移植资源，无需更新权重。