# Proof-of-Perception: Certified Tool-Using Multimodal Reasoning with Compositional Conformal Guarantees

arXiv: https://arxiv.org/abs/2603.00324 · HTML: https://mlsanity.com/paper/2603.00324/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 1 of its 31 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 1 of 1)

- [FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems](https://mlsanity.com/paper/2502.02966/) (2025)

## Built on by (most cited first, 3 of 3)

- [COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2605.30641/) (2026)
- [G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm](https://mlsanity.com/paper/2610.05563/) (2026)
- [The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow](https://mlsanity.com/paper/2610.17301/) (2026)

## Abstract (arXiv)

We present Proof-of-Perception (PoP), a tool-using framework that casts multimodal reasoning as an executable graph with explicit reliability guarantees. Each perception or logic node outputs a conformal set, yielding calibrated, stepwise uncertainty; a lightweight controller uses these certificates to allocate compute under a budget, expanding with extra tool calls only when needed and stopping early otherwise. This grounds answers in verifiable evidence, reduces error compounding and hallucinations, and enables principled accuracy-compute trade-offs. Across document, chart, and multi-image QA benchmarks, PoP improves performance and reliability over strong chain-of-thought, ReAct-style, and program-of-thought baselines while using computation more efficiently.