# OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation

arXiv: https://arxiv.org/abs/2609.39727 · HTML: https://mlsanity.com/paper/2609.39727/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 31)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://mlsanity.com/paper/2011.09533/) (2020)
- [ADaPT: As-Needed Decomposition and Planning with Language Models](https://mlsanity.com/paper/2311.05772/) (2023)
- [Hierarchical Reasoning Model](https://mlsanity.com/paper/2506.21734/) (2025)
- [Theory of Mind for Multi-Agent Collaboration via Large Language Models](https://mlsanity.com/paper/2310.10701/) (2023)
- [Gemini Robotics: Bringing AI into the Physical World](https://mlsanity.com/paper/2503.20020/) (2025)
- [PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks](https://mlsanity.com/paper/2411.00081/) (2024)
- [ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2503.09501/) (2025)
- [VL-JEPA: Joint Embedding Predictive Architecture for Vision-language](https://mlsanity.com/paper/2512.10942/) (2025)
- [LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination](https://mlsanity.com/paper/2312.15224/) (2023)
- [Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration](https://mlsanity.com/paper/2405.14314/) (2024)
- [Less is More: Recursive Reasoning with Tiny Networks](https://mlsanity.com/paper/2510.04871/) (2025)
- [Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents](https://mlsanity.com/paper/2502.20073/) (2025)
- [Agents Thinking Fast and Slow: A Talker-Reasoner Architecture](https://mlsanity.com/paper/2410.08328/) (2024)
- [Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy](https://mlsanity.com/paper/2502.19902/) (2025)
- [AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling](https://mlsanity.com/paper/2502.15676/) (2025)
- [AdaJEPA: An Adaptive Latent World Model](https://mlsanity.com/paper/2606.32026/) (2026)
- [Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interaction](https://mlsanity.com/paper/2508.05294/) (2025)
- [OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination](https://mlsanity.com/paper/2503.17821/) (2025)
- [Social World Models](https://mlsanity.com/paper/2509.00559/) (2025)
- [V1: Unifying Generation and Self-Verification for Parallel Reasoners](https://mlsanity.com/paper/2603.04304/) (2026)
- [Scaling Discovery through Test-Time Communication](https://mlsanity.com/paper/2609.21032/) (2026)
- [MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning](https://mlsanity.com/paper/2411.12977/) (2024)
- [Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning](https://mlsanity.com/paper/2511.23262/) (2025)
- [Theory of Mind Using Active Inference: A Framework for Multi-Agent Cooperation](https://mlsanity.com/paper/2508.00401/) (2025)
- [CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning](https://mlsanity.com/paper/2508.13721/) (2025)

## Abstract (arXiv)

Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet existing agents map observations to actions without separating persistent coordination strategies from their tactical execution. We introduce OverForge, a training-free hierarchical architecture that separates strategic reasoning over roles and divisions of labour from tactical reasoning over actions within each agent's private, partner-conditioned world model. A metacognitive Prefrontal Cortex Module couples the two levels by forming strategy-action branches, imagining their consequences with a forward model, and committing when confident. In OvercookedV2, OverForge delivers 7 soups in a connected kitchen versus 3 for each flat LLM baseline, retains agreed roles, and adopts roles proposed by unfamiliar partners. Ablations and a fixed-strategy probe show that persistent strategies guide tactical adaptation while each reasoning level contributes to coordination. Memory restarts show that cross-episode partner knowledge supports task performance and partner prediction, linking the hierarchy to continual adaptation.