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

arXiv: https://arxiv.org/abs/2510.10931 · HTML: https://mlsanity.com/paper/2510.10931/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 14 of 14)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Defining and Characterizing Reward Hacking](https://mlsanity.com/paper/2209.13085/) (2022)
- [LLM Agents Making Agent Tools](https://mlsanity.com/paper/2502.11705/) (2025)
- [LLM-Generated Black-box Explanations Can Be Adversarially Helpful](https://mlsanity.com/paper/2405.06800/) (2024)
- [How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questions](https://mlsanity.com/paper/2407.05015/) (2024)
- [RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation](https://mlsanity.com/paper/2507.20059/) (2025)
- [The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation](https://mlsanity.com/paper/2505.23445/) (2025)

## Built on by (most cited first, 4 of 4)

- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks](https://mlsanity.com/paper/2603.00540/) (2026)
- [HERALD: Counterfactual Audits and Minimal Repairs for Proof-of-Retrieval Rewards](https://mlsanity.com/paper/2608.06012/) (2026)
- [Beyond Instruction Following: Learning Grounded Skill-Following with Skill Contracts](https://mlsanity.com/paper/2610.05161/) (2026)

## Abstract (arXiv)

While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike execution-based tools (e.g., code or math), whose effects are directly observable, the weak observability of causal dependencies between retrieved evidence and reasoning under format- and outcome-level supervision enables agents to maximize surface-level reward signals without genuinely grounding their reasoning in the returned evidence. This leads to distinctive pathologies, including mode collapse via tool overuse and hallucinated tool usage where tool calls are largely decorative. To address this issue, we propose Proof-of-Use (PoU), an evidence grounded RL framework that explicitly optimizes the causal dependency from retrieval to reasoning and final answers. PoU re-fomulate a fine-grained stepwise interaction protocol in which agents must auditably cite normalized evidence identifiers. We operationalize this via a multi-objective reward design consisting of: (1) two progressive process rewards that constrain citation validity at intermediate steps; (2) a global Answer--Support Alignment reward that enforces consistency between final answers and retrieved evidence; and (3) a curriculum-style adaptive reward mixing mechanism that smoothly transitions agents from dense process supervision to sparse outcome-based objectives. Extensive experiments show the strong performance of PoU and demonstrate the effectiveness in mitigating tool-call hacking. Beyond this, PoU exhibits a notable emergent property: adaptive and robust tool-usage patterns naturally arise under domain and tool shifts, even though PoU does not explicitly optimize for tool adaptation.