OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents

arXiv:2610.01508 · cs.CR, cs.CL · Submitted 2026-10-01 · Read on arXiv

cs.CR, cs.CL

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• Benchmark — 35× in this paper · explained in 2 episodes
• Ablation — 13× in this paper · explained in 1 episode
• Trace — 10× in this paper · explained in 2 episodes
• Alignment — 6× in this paper · explained in 1 episode
• Core — 4× in this paper · explained in 2 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Sycophancy — 4× in this paper · explained in 4 episodes
• Task Completion Rate — 4× in this paper
• Consistency — 3× in this paper · explained in 3 episodes
• Affordance — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• AUC — 1× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Alignment Methods — 1× in this paper · explained in 1 episode
• Differential Privacy — 1× in this paper · explained in 4 episodes
• Differentially Private — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Scope Inflation Ratio — 1× in this paper
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes

Sources

• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• DeepSeek-V3 Technical Report
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
• ToolTalk: Evaluating Tool-Usage in a Conversational Setting
• Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
• A Vision for Access Control in LLM-based Agent Systems
• Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
• How RLHF Amplifies Sycophancy
• Progent: Securing AI Agents with Privilege Control
• Kimi K2: Open Agentic Intelligence
• Qwen3 Technical Report
• ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
• The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?
• Agent-SafetyBench: Evaluating the Safety of LLM Agents

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