Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents

arXiv:2510.10931 · cs.AI · Submitted 2025-10-13 · Read on arXiv

cs.AI

Submitted: 2025-10-13

Updated: 2026-10-08

Code: https://github.com/vibrantlabsai/ragas

Terminology

• Adaptation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Sources

• LLM-Generated Black-box Explanations Can Be Adversarially Helpful
• Concrete Problems in AI Safety
• Constitutional AI: Harmlessness from AI Feedback
• How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions
• ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
• A Survey on LLM-as-a-Judge
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
• Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
• Search-o1: Agentic Search-Enhanced Large Reasoning Models
• The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation
• When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
• Categorizing Variants of Goodhart's Law
• Measuring and Narrowing the Compositionality Gap in Language Models
• Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Defining and Characterizing Reward Hacking
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
• MuSiQue: Multihop Questions via Single-hop Question Composition
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems