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

[2602.04935] ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents Skip to main content Search Submit Donate Log in Computer Science > Software Engineering arXiv:2602.04935 (cs) This paper has been withdrawn by Youjin Wang [Submitted on 4 Feb 2026 ( v1 ), last revised 28 Aug 2026 (this version, v4)] Title: ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents Authors: Youjin Wang , Run Zhou , Yingjie Ma , Rong Fu , Jiani Liang , Shuaishuai Cao , Min Huang , Tao Fang , Liangming Pan No PDF available, click to view other formats Abstract: 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. Comments: Due to an unresolved dispute among the authors regarding the correctness of the experimental results and the validity of the conclusions, the team has decided to withdraw this paper until these issues can be fully resolved Subjects: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2602.04935 [cs.SE] (or arXiv:2602.04935v4 [cs.SE] for this version) https://doi.org/10.48550/arXiv.2602.04935 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Youjin Wang [ view email ] [v1] Wed, 4 Feb 2026 14:20:02 UTC (3,536 KB) [v2] Sun, 8 Feb 2026 09:26:59 UTC (4,342 KB) [v3] Tue, 9 Jun 2026 14:21:07 UTC (5,058 KB) [v4] Fri, 28 Aug 2026 15:50:05 UTC (1 KB) (withdrawn) Full-text links: Access Paper: Withdrawn Additional Features Audio Summary Current browse context: cs.SE < prev | next > new | recent | 2026-02 Change to browse by: cs cs.AI References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents#783520
• Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives#822166
• Trace Grafting: Cross-Model Reasoning in Large Language Model Code Generation#1092500
• Trace Grafting: Cross-Model Reasoning in Large Language Model Code Generation#1092484
• WiseSpec: Requirements-Driven Agents for Code Generation#820006