# Descriptive History Representations: Learning Representations by Answering Questions

arXiv: https://arxiv.org/abs/2506.02125 · HTML: https://mlsanity.com/paper/2506.02125/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning](https://mlsanity.com/paper/2004.14646/) (2020)
- [Bridging State and History Representations: Understanding Self-Predictive RL](https://mlsanity.com/paper/2401.08898/) (2024)
- [Harnessing Large Language Models for Text-Rich Sequential Recommendation](https://mlsanity.com/paper/2403.13325/) (2024)
- [PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence](https://mlsanity.com/paper/2503.02398/) (2025)
- [Semantic HELM: A Human-Readable Memory for Reinforcement Learning](https://mlsanity.com/paper/2306.09312/) (2023)
- [Demystifying Embedding Spaces using Large Language Models](https://mlsanity.com/paper/2310.04475/) (2023)
- [Predictive State Recurrent Neural Networks](https://mlsanity.com/paper/1705.09353/) (2017)
- [Predictive-State Decoders: Encoding the Future into Recurrent Networks](https://mlsanity.com/paper/1709.08520/) (2017)
- [The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models](https://mlsanity.com/paper/2303.03284/) (2023)
- [Embedding-Aligned Language Models](https://mlsanity.com/paper/2406.00024/) (2024)
- [Towards Explainable Temporal User Profiling with LLMs](https://mlsanity.com/paper/2505.00886/) (2025)

## Abstract (arXiv)

Effective decision making in partially observable environments requires compressing long interaction histories into informative representations. We introduce Descriptive History Representations (DHRs): sufficient statistics characterized by their capacity to answer relevant questions about past interactions and potential future outcomes. DHRs focus on capturing the information necessary to address task-relevant queries, providing a structured way to summarize a history for optimal control. We propose a multi-agent learning framework, involving representation, decision, and question-asking components, optimized using a joint objective that balances reward maximization with the representation's ability to answer informative questions. This yields representations that capture the salient historical details and predictive structures needed for effective decision making. We validate our approach on user modeling tasks with public movie and shopping datasets, generating interpretable textual user profiles which serve as sufficient statistics for predicting preference-driven behavior of users.