Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Youjin, Zhou, Run, Fu, Rong, Cao, Shuaishuai, Zeng, Hongwei, Lu, Jiaxuan, Fan, Sicheng, Zhao, Jiaqiao, Pan, Liangming
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Online-Optimized RAG for Tool Use and Function Calling
by: Pan, Yu, et al.
Published: (2025)

The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
by: Xu, Haoyuan, et al.
Published: (2026)

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
by: Chen, Xuan, et al.
Published: (2026)

ScaleCall -- Agentic Tool Calling at Scale for Fintech: Challenges, Methods, and Deployment Insights
by: Osuagwu, Richard, et al.
Published: (2025)

SEAlign: Alignment Training for Software Engineering Agent
by: Zhang, Kechi, et al.
Published: (2025)

Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls
by: Zhang, Zeyu, et al.
Published: (2026)

Training Software Engineering Agents and Verifiers with SWE-Gym
by: Pan, Jiayi, et al.
Published: (2024)

RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement
by: LeVine, Will, et al.
Published: (2026)

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
by: Dong, Ben, et al.
Published: (2026)

A Tool for Automatically Cataloguing and Selecting Pre-Trained Models and Datasets for Software Engineering
by: González, Alexandra, et al.
Published: (2026)

From User Interface to Agent Interface: Efficiency Optimization of UI Representations for LLM Agents
by: Ran, Dezhi, et al.
Published: (2025)

SWE-World: Building Software Engineering Agents in Docker-Free Environments
by: Sun, Shuang, et al.
Published: (2026)

Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs
by: Lu, Yuxuan, et al.
Published: (2026)

CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios
by: Huang, Shiting, et al.
Published: (2025)

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
by: Song, Huatong, et al.
Published: (2026)

Who's actually being Studied? A Call for Population Analysis in Software Engineering Research
by: Molléri, Jefferson Seide
Published: (2024)

Beyond Autonomy: A Dynamic Tiered AgentRunner Framework for Governable and Resilient Enterprise AI Execution
by: Pan, Kai, et al.
Published: (2026)

"ENERGY STAR" LLM-Enabled Software Engineering Tools
by: Thakur, Himon, et al.
Published: (2026)

Practical Feasibility of Sustainable Software Engineering Tools and Techniques
by: Ghanta, Satwik, et al.
Published: (2026)

GeoJSON Agents:A Multi-Agent LLM Architecture for Geospatial Analysis-Function Calling vs Code Generation
by: Luo, Qianqian, et al.
Published: (2025)

Repairing Tool Calls Using Post-tool Execution Reflection and RAG
by: Tsay, Jason, et al.
Published: (2025)

A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks
by: Yin, Zhuowen, et al.
Published: (2025)

Leveraging Creativity as a Problem Solving Tool in Software Engineering
by: Groeneveld, Wouter
Published: (2025)

SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations
by: Wang, Shuaiqi, et al.
Published: (2026)

Towards Verifiably Safe Tool Use for LLM Agents
by: Doshi, Aarya, et al.
Published: (2026)

Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors
by: Li, Henger, et al.
Published: (2025)

On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset
by: Bhat, Vishvesh, et al.
Published: (2025)

Software Product Line Engineering: Adoption, Tooling and AI Era Challenges
by: Nazar, Najam
Published: (2026)

Sentiment Analysis Tools in Software Engineering: A Systematic Mapping Study
by: Obaidi, Martin, et al.
Published: (2025)

Preconceptual Modeling in Software Engineering: Metaphysics of Diagrammatic Representations
by: Al-Fedaghi, Sabah
Published: (2024)

Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents
by: Cartagena, Arnold, et al.
Published: (2026)

VerifyThisBench: Generating Code, Specifications, and Proofs All at Once
by: Deng, Xun, et al.
Published: (2025)

ToolFuzz -- Automated Agent Tool Testing
by: Milev, Ivan, et al.
Published: (2025)

Requirements Engineering for a Web-based Research, Technology & Innovation Monitoring Tool
by: Mazak-Huemer, Alexandra, et al.
Published: (2025)

Mind the Gap: The Missing Features of the Tools to Support User Studies in Software Engineering
by: Costa, Lázaro, et al.
Published: (2025)

Evaluation of LLM-Based Software Engineering Tools: Practices, Challenges, and Future Directions
by: Torun, Utku Boran, et al.
Published: (2026)

Towards Trustworthy Sentiment Analysis in Software Engineering: Dataset Characteristics and Tool Selection
by: Obaidi, Martin, et al.
Published: (2025)

Live API-Bench: 2500+ Live APIs for Testing Multi-Step Tool Calling
by: Elder, Benjamin, et al.
Published: (2025)

Morphis: SLO-Aware Resource Scheduling for Microservices with Time-Varying Call Graphs
by: Tang, Yu, et al.
Published: (2026)

PAGENT: Learning to Patch Software Engineering Agents
by: Xue, Haoran, et al.
Published: (2025)