# ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents

arXiv: https://arxiv.org/abs/2602.04935 · HTML: https://mlsanity.com/paper/2602.04935/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)
- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 14 of 14)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities](https://mlsanity.com/paper/2409.03444/) (2024)
- [NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls](https://mlsanity.com/paper/2409.03797/) (2024)
- [Controlling Large Language Model Agents with Entropic Activation Steering](https://mlsanity.com/paper/2406.00244/) (2024)
- [Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates](https://mlsanity.com/paper/2509.18076/) (2025)

## Built on by (most cited first, 6 of 6)

- [Tool Calling is Linearly Readable and Steerable in Language Models](https://mlsanity.com/paper/2605.07990/) (2026)
- [Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use](https://mlsanity.com/paper/2605.14038/) (2026)
- [A Few Neurons Reveal When LLMs Misuse Tools: Sparse Detection and Selective Steering for Reliable Tool Use](https://mlsanity.com/paper/2608.00218/) (2026)
- [Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes](https://mlsanity.com/paper/2605.05715/) (2026)
- [When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs](https://mlsanity.com/paper/2609.36138/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

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.