Proof-of-Perception: Certified Tool-Using Multimodal Reasoning with Compositional Conformal Guarantees
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Multimodal ReasoningSimilar Papers 제목 키워드 기반
Certified Program Synthesis with a Multi-Modal Verifier
Certified program synthesis (aka vericoding) is the process of automatically generating a program, its formal specification, and a machine-checkable proof of their alignment from a natural-language description. Two chall…
Program SynthesisCertified Deductive Reasoning with Language Models
Language models often achieve higher accuracy when reasoning step-by-step in complex tasks. However, even when arriving at a correct final answer, their rationales are often logically unsound or inconsistent. This is a m…
Logical ReasoningvalidM$^3$-ACE: Rectifying Visual Perception in Multimodal Math Reasoning via Multi-Agentic Context Engineering
Multimodal large language models have recently shown promising progress in visual mathematical reasoning. However, their performance is often limited by a critical yet underexplored bottleneck: inaccurate visual percepti…
Mathematical ReasoningMultimodal ReasoningPrompt EngineeringFaster Certified Symmetry Breaking Using Orders With Auxiliary Variables
Symmetry breaking is a crucial technique in modern combinatorial solving, but it is difficult to be sure it is implemented correctly. The most successful approach to deal with bugs is to make solvers certifying, so that …
DeepEyesV2: Toward Agentic Multimodal Model
Agentic multimodal models should not only comprehend text and images, but also actively invoke external tools, such as code execution environments and web search, and integrate these operations into reasoning. In this wo…
Reinforcement LearningMathematical ReasoningMultimodal Reasoning