REVIEW 5 cited by
CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The generalization of decision-making agents encompasses two fundamental elements: learning from past experiences and reasoning in novel contexts. However, the predominant emphasis in most interactive environments is on learning, often at the expense of complexity in reasoning. In this paper, we introduce CivRealm, an environment inspired by the Civilization game. Civilization's profound alignment with human history and society necessitates sophisticated learning, while its ever-changing situations demand strong reasoning to generalize. Particularly, CivRealm sets up an imperfect-information general-sum game with a changing number of players; it presents a plethora of complex features, challenging the agent to deal with open-ended stochastic environments that require diplomacy and negotiation skills. Within CivRealm, we provide interfaces for two typical agent types: tensor-based agents that focus on learning, and language-based agents that emphasize reasoning. To catalyze further research, we present initial results for both paradigms. The canonical RL-based agents exhibit reasonable performance in mini-games, whereas both RL- and LLM-based agents struggle to make substantial progress in the full game. Overall, CivRealm stands as a unique learning and reasoning challenge for decision-making agents. The code is available at https://github.com/bigai-ai/civrealm.
Forward citations
Cited by 5 Pith papers
-
Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning
A hierarchical framework of specialized imitation agents plus a strategic planner improves win rates and cuts LLM calls in text-based StarCraft II across all race matchups.
-
StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production-Living Simulations with Stardew Valley
StarDojo is a 1,000-task benchmark in Stardew Valley combining production and social activities, and the best tested MLLM (GPT-4.1) achieves only 12.7% success on its 100-task subset.
-
Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling
LLM-driven agents in a simulated MMO economy reproduce role specialization and price responses to supply and demand, though the price result is partly shaped by what the AI is told.
-
InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow
InstantEdit combines RectifiedFlow inversion, latent injection, disentangled prompt guidance, and Canny ControlNet to do fast few-step text-guided image editing with content preservation.
-
Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games
A group, fuse, and retrain recipe for multi-game reinforcement learning lets a 32B model reach near-Claude3.5 performance on several TextArena games, though the headline score is internally inconsistent.
Discussion (0). Continue with ORCID to comment.