AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games

Dongmin Park, Minkyu Kim, Beongjun Choi, Junhyuck Kim, Keon Lee, Jonghyun Lee, Inkyu Park, Byeong-Uk Lee, Jaeyoung Hwang, Jaewoo Ahn, Ameya Sunil Mahabaleshwarkar, Bilal Kartal and 4 more

ICLR 2026 · Large language models › Instruction and fine-tuning · approach: Fine-tuning generalization and delta compression · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add reflection and planning modules to zero-shot agent (ablation)GPT-4o · Orak avg across 12 gamesaverage rank: 3.3 -> 2.2Improved
add reflection and planning modules to zero-shot agent (ablation)Llama-3.2-3B · Orak avg across 12 gamesaverage rank: 5.6 -> 6.1Hurt
add planning to reflection agent (ablation)Llama-3.2-3B · Orak avg across 12 gamesaverage rank: 5.6 -> 6.1Hurt
add image input alongside text (ablation)GPT-4o · Orak Group 1 gamesaverage rank: 1.7 -> 3.0Hurt
use image-only input instead of text (ablation)GPT-4o · Orak Group 1 gamesaverage rank: 1.7 -> 5.3Hurt
add image input alongside text (ablation)GPT-4o · Ace Attorneynormalized game score: 85.3 -> 53.5Hurt
add image input alongside text (ablation)Claude-3.7 · Street Fighter IIInormalized game score: 16.7 -> 33.3Improved
fine-tune on Orak expert trajectoriesLlama-3.2-3B · Street Fighter IIInormalized game score: 12.0 -> 40.0Improved
fine-tune on Orak expert trajectoriesLlama-3.2-3B · WebShop-Hscore: 0.0 -> 12.6Improved
fine-tune on Orak expert trajectoriesLlama-3.2-1B · WebShop-Hscore: 1.9 -> 0.0No clear effect
fine-tune on Orak trajectories (OOD game)Llama-3.2-3B · 2048normalized game score: 0.1 -> 3.1Improved
fine-tune on low-score instead of high-score data (ablation)Llama-3.2-3B · Darkest Dungeonnormalized game score: 92.0 -> 40.0Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy