# Interactive Machine Comprehension with Information Seeking Agents

arXiv: https://arxiv.org/abs/1908.10449 · HTML: https://mlsanity.com/paper/1908.10449/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2019.

## Built on by (most cited first, 13 of 13)

- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024)
- [LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models](https://mlsanity.com/paper/2311.18232/) (2023)
- [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://mlsanity.com/paper/2408.15232/) (2024)
- [ChatShop: Interactive Information Seeking with Language Agents](https://mlsanity.com/paper/2404.09911/) (2024)
- [Boosting Search Engines with Interactive Agents](https://mlsanity.com/paper/2109.00527/) (2021)
- [debug-gym: A Text-Based Environment for Interactive Debugging](https://mlsanity.com/paper/2503.21557/) (2025)
- [Hey AI, Can You Solve Complex Tasks by Talking to Agents?](https://mlsanity.com/paper/2110.08542/) (2021)
- [PRInTS: Reward Modeling for Long-Horizon Information Seeking](https://mlsanity.com/paper/2511.19314/) (2025)
- [Interactive Machine Comprehension with Dynamic Knowledge Graphs](https://mlsanity.com/paper/2109.00077/) (2021)
- [DeLIVeR: Decomposed Learning for Information-grounded Veracity Recognition via Reinforced Knowledge Graph Exploration](https://mlsanity.com/paper/2607.17935/) (2026)

## Abstract (arXiv)

Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA). We argue that this stems from the nature of MRC datasets: most of these are static environments wherein the supporting documents and all necessary information are fully observed. In this paper, we propose a simple method that reframes existing MRC datasets as interactive, partially observable environments. Specifically, we "occlude" the majority of a document's text and add context-sensitive commands that reveal "glimpses" of the hidden text to a model. We repurpose SQuAD and NewsQA as an initial case study, and then show how the interactive corpora can be used to train a model that seeks relevant information through sequential decision making. We believe that this setting can contribute in scaling models to web-level QA scenarios.