# Knowledge-enhanced Agents for Interactive Text Games

arXiv: https://arxiv.org/abs/2305.05091 · HTML: https://mlsanity.com/paper/2305.05091/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 57 references that are in the map.
- First posted on arXiv 8 May 2023.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 29 of 29)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [Go-Explore: a New Approach for Hard-Exploration Problems](https://mlsanity.com/paper/1901.10995/) (2019)
- [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://mlsanity.com/paper/2302.02662/) (2023)
- [Interactive Fiction Games: A Colossal Adventure](https://mlsanity.com/paper/1909.05398/) (2019)
- [Keep CALM and Explore: Language Models for Action Generation in Text-based Games](https://mlsanity.com/paper/2010.02903/) (2020)
- [A Survey of Deep Meta-Learning](https://mlsanity.com/paper/2010.03522/) (2020)
- [Deep Reinforcement Learning with a Natural Language Action Space](https://mlsanity.com/paper/1511.04636/) (2015)
- [Graph Constrained Reinforcement Learning for Natural Language Action Spaces](https://mlsanity.com/paper/2001.08837/) (2020)
- [Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning](https://mlsanity.com/paper/1812.01628/) (2018)
- [CSKG: The CommonSense Knowledge Graph](https://mlsanity.com/paper/2012.11490/) (2020)
- [How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds](https://mlsanity.com/paper/2006.07409/) (2020)
- [Core Challenges in Embodied Vision-Language Planning](https://mlsanity.com/paper/2106.13948/) (2021)
- [Dimensions of Commonsense Knowledge](https://mlsanity.com/paper/2101.04640/) (2021)
- [Multi-Stage Episodic Control for Strategic Exploration in Text Games](https://mlsanity.com/paper/2201.01251/) (2022)
- [Exploration Based Language Learning for Text-Based Games](https://mlsanity.com/paper/2001.08868/) (2020)
- [Reshaping Robot Trajectories Using Natural Language Commands: A Study of Multi-Modal Data Alignment Using Transformers](https://mlsanity.com/paper/2203.13411/) (2022)
- [Generalization in Text-based Games via Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2109.09968/) (2021)
- [Coalescing Global and Local Information for Procedural Text Understanding](https://mlsanity.com/paper/2208.12848/) (2022)
- [Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spaces](https://mlsanity.com/paper/1905.09700/) (2019)
- [On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings](https://mlsanity.com/paper/2109.03334/) (2021)
- [An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs](https://mlsanity.com/paper/2205.10661/) (2022)
- [Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods](https://mlsanity.com/paper/2201.12126/) (2022)
- [Transferring Procedural Knowledge across Commonsense Tasks](https://mlsanity.com/paper/2304.13867/) (2023)

## Built on by (most cited first, 10 of 10)

- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay](https://mlsanity.com/paper/2310.14985/) (2023)
- [FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents](https://mlsanity.com/paper/2406.14884/) (2024)
- [PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents](https://mlsanity.com/paper/2402.12326/) (2024)
- [SWE Context Bench: A Benchmark for Context Learning in Coding](https://mlsanity.com/paper/2602.08316/) (2026)
- [Bridging the Agent-World Gap: Text World Models for LLM-based Agents](https://mlsanity.com/paper/2606.09032/) (2026)
- [Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay](https://mlsanity.com/paper/2608.26846/) (2026)
- [A Mixture-of-Experts Approach to Few-Shot Task Transfer in Open-Ended Text Worlds](https://mlsanity.com/paper/2405.06059/) (2024)
- [Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents](https://mlsanity.com/paper/2504.03185/) (2025)

## Abstract (arXiv)

Communication via natural language is a key aspect of machine intelligence, and it requires computational models to learn and reason about world concepts, with varying levels of supervision. Significant progress has been made on fully-supervised non-interactive tasks, such as question-answering and procedural text understanding. Yet, various sequential interactive tasks, as in text-based games, have revealed limitations of existing approaches in terms of coherence, contextual awareness, and their ability to learn effectively from the environment. In this paper, we propose a knowledge-injection framework for improved functional grounding of agents in text-based games. Specifically, we consider two forms of domain knowledge that we inject into learning-based agents: memory of previous correct actions and affordances of relevant objects in the environment. Our framework supports two representative model classes: reinforcement learning agents and language model agents. Furthermore, we devise multiple injection strategies for the above domain knowledge types and agent architectures, including injection via knowledge graphs and augmentation of the existing input encoding strategies. We experiment with four models on the 10 tasks in the ScienceWorld text-based game environment, to illustrate the impact of knowledge injection on various model configurations and challenging task settings. Our findings provide crucial insights into the interplay between task properties, model architectures, and domain knowledge for interactive contexts.