# AI use cases for Awesome AI for Games (Eurekaleo/awesome-ai-for-games) Repo: [Eurekaleo/awesome-ai-for-games](https://github.com/Eurekaleo/awesome-ai-for-games) | Use cases: 4 | Page: https://dedupedai.com/use-cases/eurekaleo-awesome-ai-for-games/ A curated, searchable collection of research papers on AI and foundation models across the game lifecycle, organized into six roles. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Build a reading list for LLM game NPC agents: https://dedupedai.com/use-cases/eurekaleo-awesome-ai-for-games/build-reading-list-for-game-npc-agents/ - Find benchmarks for evaluating LLM agents on games: https://dedupedai.com/use-cases/eurekaleo-awesome-ai-for-games/find-benchmarks-for-testing-game-agents/ - Map AI-for-games research across six lifecycle roles: https://dedupedai.com/use-cases/eurekaleo-awesome-ai-for-games/map-ai-game-research-by-lifecycle-role/ - Review bias evaluation methods for game NPC LLMs: https://dedupedai.com/use-cases/eurekaleo-awesome-ai-for-games/review-bias-in-game-npc-llms/ ## How to build a reading list for LLM game NPC agents with Awesome AI for Games Repo: [Eurekaleo/awesome-ai-for-games](https://github.com/Eurekaleo/awesome-ai-for-games) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Collect the Play and Act papers on LLM and RL agents that control game characters. **Who it is for:** A game AI researcher or NPC designer who needs a starting set of papers before prototyping character behavior. **The problem:** Papers on game agents are spread across many venues and years, and it is slow to find the ones that match a specific task. **The outcome:** A short, sorted list of relevant papers with links to the paper, project, and code where the README provides them. ### Steps 1. Open the README and jump to the Choose a research role section. 2. Select the Play and Act role to go to its papers. 3. Scan the 2026 and 2025 entries for NPC, persona, or social-interaction topics, such as the PUBG Ally and FAIRGAMER entries. 4. Open the paper and code links for the three to five most relevant entries and save them to your reading list. ### Prompt to paste into your agent ```text Using the Eurekaleo/awesome-ai-for-games README, list the Play and Act papers that involve game NPCs or persona-driven characters, with their paper and code links. Verify that each entry you return appears under the Play and Act heading. ``` ### Caveat The list links to external papers and code, and the README does not say which of them are maintained or reproducible, so check each source before relying on it. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/eurekaleo-awesome-ai-for-games/build-reading-list-for-game-npc-agents/ ## How to find benchmarks for evaluating LLM agents on games with Awesome AI for Games Repo: [Eurekaleo/awesome-ai-for-games](https://github.com/Eurekaleo/awesome-ai-for-games) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Locate benchmark papers such as Orak and VideoGameBench to compare agent evaluations. **Who it is for:** A QA lead or AI evaluation engineer who needs a benchmark to measure how well an LLM agent plays real video games. **The problem:** Choosing a benchmark means comparing many papers that each define their own games, tasks, and metrics. **The outcome:** A shortlist of game-agent benchmarks with their source links, ready for a side-by-side review. ### Steps 1. Open the README and go to the Play and Act section. 2. Look for entries whose titles name a benchmark, such as Orak, VideoGameBench, FlashAdventure, and EMemBench. 3. Open each benchmark's paper link and note the games it covers and how it evaluates agents. 4. Use the Literature search link to find newer benchmark papers that are not yet in the list. ### Prompt to paste into your agent ```text Using the Eurekaleo/awesome-ai-for-games README, list every benchmark paper in the Play and Act section that evaluates LLM or VLM agents on video games. For each one, give the title and paper link, and state whether the README links code for it. ``` ### Caveat The README describes these entries only by title and link, so the games and metrics in each benchmark must be confirmed from the linked paper. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/eurekaleo-awesome-ai-for-games/find-benchmarks-for-testing-game-agents/ ## How to map AI-for-games research across six lifecycle roles with Awesome AI for Games Repo: [Eurekaleo/awesome-ai-for-games](https://github.com/Eurekaleo/awesome-ai-for-games) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Use the six-role structure and survey map to plan a research or product review. **Who it is for:** A product lead or research manager who needs an overview of where AI fits across the game lifecycle before choosing a focus area. **The problem:** AI-for-games work covers many stages of development, and it is hard to see which stage a given paper addresses. **The outcome:** A short map of the six roles, with the papers in each role that match the team's focus area. ### Steps 1. Read the About the survey section to see how the six roles are defined. 2. Open the Visual survey map link to see how the roles relate to each other. 3. Choose one or two roles that match your team's focus and open them from the Choose a research role section. 4. Write a one-page summary of the papers in those roles, using the three guiding questions on boundary, transfer and reuse, and evidence. ### Prompt to paste into your agent ```text Using the Eurekaleo/awesome-ai-for-games README, summarize the six research roles described in the About the survey section and name the role that covers game testing or support. Verify that your summary uses only the role names and descriptions given in the README. ``` ### Caveat The README gives the six-role structure but the roles are only partly named in the visible text, so confirm the full list on the live page before building a plan on it. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/eurekaleo-awesome-ai-for-games/map-ai-game-research-by-lifecycle-role/ ## How to review bias evaluation methods for game NPC LLMs with Awesome AI for Games Repo: [Eurekaleo/awesome-ai-for-games](https://github.com/Eurekaleo/awesome-ai-for-games) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Find the FAIRGAMER paper and related work on social bias in game characters. **Who it is for:** A trust and safety reviewer or game writer who must check whether an LLM-driven NPC behaves fairly across player groups. **The problem:** Teams deploying LLM characters need evidence on bias, but the relevant evaluation papers are not grouped together. **The outcome:** A short list of papers that evaluate bias or social behavior in game agents, with links to read the methods. ### Steps 1. Open the README and go to the Play and Act section. 2. Find the FAIRGAMER entry on social biases in LLM-based video game NPCs and open its link. 3. Look for other entries in the same section that evaluate social or persona behavior, such as the social deduction and social agent papers. 4. Record the evaluation method and the claims each paper supports, then compare them against your own NPC use case. ### Prompt to paste into your agent ```text Using the Eurekaleo/awesome-ai-for-games README, list the papers in the Play and Act section that evaluate bias, social behavior, or persona consistency in game agents, with their links. Verify that FAIRGAMER appears in your list. ``` ### Caveat The README lists FAIRGAMER by title only, so the bias categories it tests must be read from the linked paper rather than assumed. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/eurekaleo-awesome-ai-for-games/review-bias-in-game-npc-llms/