不训练模型也能让大模型更准调用工具，关键在干预中间层激活。
ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents
- 通过单次中间层干预，用轻量控制器动态调节工具调用决策。
- 在MTU-Bench上工具调用准确率从0.18提升至0.50，误触发率降至0.05。
- 无需参数更新，仅20KB可移植资源，适合快速部署于新工具场景。
将大语言模型代理适配到特定领域工具调用仍面临接口演变下的脆弱性问题。提示工程易部署但对分布偏移敏感，持续的高效微调虽提升可靠性却需训练维护且有遗忘风险。我们发现一种‘懒惰代理’失效模式：工具调用需求几乎能从中间层激活中完美解码，但模型仍保守拒绝进入工具模式，暴露出表征与行为之间的鸿沟。为此提出激活引导适配器（ASA），一种无训练、推理时使用的控制器，通过单次中间层干预，利用路由器调控的转向向量混合，并以探针引导的符号门放大真实意图、抑制虚假触发。在使用Qwen2.5-1.5B模型的MTU-Bench测试中，ASA将严格工具调用的F1值从0.18提升至0.50，误报率由0.15降至0.05，仅需约20KB可移植资产，无需权重更新。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。