mlsanityData to 14 Oct 2026

Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents

arXiv 2505.03947 ↗First posted 6 May 2025cs.AIcited by 1

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

One of the primary aspirations in reinforcement learning research is developing general-purpose agents capable of rapidly adapting to and mastering novel tasks. While RL gaming agents have mastered many Atari games, they remain slow and costly to train for each game. In this work, we demonstrate that latest reasoning LLMs with out-of-domain RL post-training can play a challenging Atari game called Frogger under a zero-shot setting. We then investigate the effect of in-context learning and the amount of reasoning effort on LLM performance. Lastly, we demonstrate a way to bootstrap traditional RL method with LLM demonstrations, which significantly improves their performance and sample efficiency. Our implementation is open sourced at https://github.com/AlienKevin/frogger.

Key facts. Cited by 1 paper 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 3 of its 7 references that are in the map. First posted on arXiv 6 May 2025.

Builds on

3 of 7 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learning20 Mar

Other references · 2

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  2. 2017Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agentscited by 269

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Leveraging LLM Agents for Automated Video Game Testingcited by 5

Similar, not cited

Close in wording, no citation either way

  1. 2025Demystifying Reinforcement Learning in Agentic Reasoning
  2. 2025Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
  3. 2026Understanding Reasoning from Pretraining to Post-Training
  4. 2024Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
  5. 2024BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
  6. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
  7. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
  8. 2026Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory