# Learning to Construct Knowledge through Sparse Reference Selection with Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.05874 · HTML: https://mlsanity.com/paper/2509.05874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 7 Sep 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 6 of 6)

- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning](https://mlsanity.com/paper/1711.05851/) (2017)
- [Recovering Bandits](https://mlsanity.com/paper/1910.14354/) (2019)
- [Blocking Bandits](https://mlsanity.com/paper/1907.11975/) (2019)
- [ReasoNet: Learning to Stop Reading in Machine Comprehension](https://mlsanity.com/paper/1609.05284/) (2016)

## Abstract (arXiv)

The rapid expansion of scientific literature makes it increasingly difficult to acquire new knowledge, particularly in specialized domains where reasoning is complex, full-text access is restricted, and target references are sparse among a large set of candidates. We present a Deep Reinforcement Learning framework for sparse reference selection that emulates human knowledge construction, prioritizing which papers to read under limited time and cost. Evaluated on drug--gene relation discovery with access restricted to titles and abstracts, our approach demonstrates that both humans and machines can construct knowledge effectively from partial information.