# SPARK: Self-Play with Asymmetric Reward from Knowledge Graphs

arXiv: https://arxiv.org/abs/2605.05546 · HTML: https://mlsanity.com/paper/2605.05546/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Self-play RL for reasoning, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-play RL for reasoning](https://mlsanity.com/synth/self-play-rl-for-reasoning/)

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [R-Zero: Self-Evolving Reasoning LLM from Zero Data](https://mlsanity.com/paper/2508.05004/) (2025)
- [UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph](https://mlsanity.com/paper/2212.00959/) (2022)
- [SPICE: Self-Play In Corpus Environments Improves Reasoning](https://mlsanity.com/paper/2510.24684/) (2025)
- [Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models](https://mlsanity.com/paper/2410.13080/) (2024)
- [Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation](https://mlsanity.com/paper/2402.03268/) (2024)
- [Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling](https://mlsanity.com/paper/2511.16301/) (2025)

## Abstract (arXiv)

Self-play reinforcement learning has shown strong performance in domains with formally verifiable structure, such as mathematics and coding, where both problem generation and reward computation can be grounded in explicit rules. Extending this paradigm to scientific literature is more challenging: the relationships among multi-modal elements within and across documents are rarely made explicit in text, which makes automatic generation of relational reasoning questions difficult and weakens the reliability of reward signals. We propose SPARK (Self-Play with Asymmetric Reward from Knowledge Graphs), a framework that automatically constructs a unified knowledge graph (KG) from multi-document scientific literature and uses it as the structural basis for self-play. KG paths over multimodal nodes serve as a source for generating relational reasoning questions, and structured facts stored in the KG provide a basis for verifiable reward computation. A single small vision-language model (sVLM) alternates between Proposer and Solver roles under information asymmetry against a fixed KG, a design that we believe can be naturally extended toward online adaptation in future work. We evaluate SPARK on public benchmarks and a self-constructed cross-document multi-hop QA dataset. Results show that SPARK consistently outperforms flat-corpus-based self-play baselines, and the performance gap widens as hop count increases, suggesting that KG-structure grounding contributes to relational multi-hop reasoning beyond what unstructured corpus grounding can provide.