Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915889351229440 |
|---|---|
| author | Ma, Li Peng, Hao Wang, Yiming Luo, Hongbin Liu, Jie Gu, Kongjing Wu, Guanlin Lin, Hui Ren, Lei |
| author_facet | Ma, Li Peng, Hao Wang, Yiming Luo, Hongbin Liu, Jie Gu, Kongjing Wu, Guanlin Lin, Hui Ren, Lei |
| contents | Large language models (LLMs) have demonstrated exceptional potential in complex reasoning,pioneering a new paradigm for autonomous agent decision making in dynamic settings. However, in Real-Time Strategy (RTS) scenarios, LLMs suffer from a critical speed-quality trade-off. Specifically expansive state spaces and time limits render inference delays prohibitive, while stochastic planning errors undermine logical consistency. To address these challenges, we present SEMA (Self-Evolving Multi-Agent), a novel framework designed for high-performance, low-latency decision-making in RTS environments. This collaborative multi-agent framework facilitates self-evolution by adaptively calibrating model bias through in-episode assessment and cross-episode analysis. We further incorporate dynamic observation pruning based on structural entropy to model game states topologically. By distilling high dimensional data into core semantic information, this approach significantly reduces inference time. We also develop a hybrid knowledge-memory mechanism that integrates micro-trajectories, macro-experience, and hierarchical domain knowledge, thereby enhancing both strategic adaptability and decision consistency. Experiments across multiple StarCraft II maps demonstrate that SEMA achieves superior win rates while reducing average decision latency by over 50%, validating its efficiency and robustness in complex RTS scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23875 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios Ma, Li Peng, Hao Wang, Yiming Luo, Hongbin Liu, Jie Gu, Kongjing Wu, Guanlin Lin, Hui Ren, Lei Multiagent Systems Large language models (LLMs) have demonstrated exceptional potential in complex reasoning,pioneering a new paradigm for autonomous agent decision making in dynamic settings. However, in Real-Time Strategy (RTS) scenarios, LLMs suffer from a critical speed-quality trade-off. Specifically expansive state spaces and time limits render inference delays prohibitive, while stochastic planning errors undermine logical consistency. To address these challenges, we present SEMA (Self-Evolving Multi-Agent), a novel framework designed for high-performance, low-latency decision-making in RTS environments. This collaborative multi-agent framework facilitates self-evolution by adaptively calibrating model bias through in-episode assessment and cross-episode analysis. We further incorporate dynamic observation pruning based on structural entropy to model game states topologically. By distilling high dimensional data into core semantic information, this approach significantly reduces inference time. We also develop a hybrid knowledge-memory mechanism that integrates micro-trajectories, macro-experience, and hierarchical domain knowledge, thereby enhancing both strategic adaptability and decision consistency. Experiments across multiple StarCraft II maps demonstrate that SEMA achieves superior win rates while reducing average decision latency by over 50%, validating its efficiency and robustness in complex RTS scenarios. |
| title | Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2603.23875 |