Implicit Manipulation for Skill Selection in LLM Agents with Semantic Matching

arXiv:2609.02035 · cs.CR · Submitted 2026-09-02 · Read on arXiv

cs.CR

Submitted: 2026-09-02

Updated: 2026-09-02

Comments: 20 pages, 9 figures, 5 tables

Code: https://github.com/dair-ai/Prompt-Engineering-Guide

Project page: https://yangzhangalmo.github.io/papers/EMNLP24-PromptEvolution.pdf

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Steering — 49× in this paper · explained in 2 episodes
• Target-Selection Rate — 10× in this paper
• Adam — 6× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Generalization — 4× in this paper · explained in 13 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• Native False-Positive Rate — 3× in this paper
• Random Keywords — 3× in this paper
• Selection Bias — 3× in this paper · explained in 4 episodes
• Semantic Similarity — 3× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Agent Skills — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Metacognition — 1× in this paper · explained in 5 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Defeating Prompt Injections by Design
• AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
• BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
• TAI3: Testing Agent Integrity in Interpreting User Intent
• Measuring Pragmatic Influence in Large Language Model Instructions
• The Llama 3 Herd of Models
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
• Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
• MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
• ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
• Qwen2.5-Coder Technical Report
• GPT-4o System Card
• Baseline Defenses for Adversarial Attacks Against Aligned Language Models
• A Critical Evaluation of Defenses against Prompt Injection Attacks
• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
• Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Gorilla: Large Language Model Connected with Massive APIs
• Toolformer: Language Models Can Teach Themselves to Use Tools
• ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs