Incentivizing Neuro-symbolic Language-based Reasoning in VLMs via Reinforcement Learning
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
There are 7,407 languages in the world. But, what about the languages that are not there in the world? Are humans so narrow minded that we don't care about the languages aliens communicate in? Aliens are humans too! In the 2016 movie Arrival, Amy Adams plays a linguist, Dr. Louise Banks who, by learning to think in an alien language (Heptapod) formed of non-sequential sentences, gains the ability to transcend time and look into the future. In this work, I aim to explore the representation and reasoning of vision-language concepts in a neuro-symbolic language, and study improvement in analytical reasoning abilities and efficiency of "thinking systems". With Qwen3-VL-2B-Instruct as base model and 4 × Nvidia H200 GPU nodes, I achieve an accuracy improvement of 3.33% on a vision-language evaluation dataset consisting of math, science, and general knowledge questions, while reducing the reasoning tokens by 75% over SymPy. I've documented the compute challenges faced, scaling possibilities, and the future work to improve thinking in a neuro-symbolic language in vision-language models. The training and inference setup can be found here: https://github.com/i-like-bfs-and-dfs/wolfram-reasoning.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 0 of its 19 references that are in the map. First posted on arXiv 23 Apr 2026.
Builds on
0 of 19 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2022Mind's Eye: Grounded Language Model Reasoning through Simulation
- 2025Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?
- 2025Language and Thought: The View from LLMs
- 2025Evaluating Large Language Models on the Frame and Symbol Grounding Problems: A Zero-shot Benchmark
- 2024Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Models
- 2023Visual cognition in multimodal large language models
- 2024Zero, Finite, and Infinite Belief History of Theory of Mind Reasoning in Large Language Models
- 2024Vision Language Models See What You Want but not What You See