arXiv：cs.AI· Mengdi Liu, Chenghao Jia, Hong Chang, Mingjie He, Shiguang Shan, Xilin Chen·· 13 小时前
JANUS：用协同演化世界模型增强长时程自主研究
JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models
AI 导读
JANUS 是一个通过协同演化世界模型驱动的 Predict-Verify-Evolve 循环，统一未来结果预测与过往经验反思的研究框架，在执行前先对候选分支打分并选择、精炼或剪枝。它把真实反馈蒸馏为分层研究技能、探索策略技能及协调协议，实现研究智能体与世界模型的持续协同演化。在 MLS-Bench-Lite 和真实研究任务上，JANUS 显著优于当前最优基线，演化效率与上限均有提升。
正文
Abstract:Long-horizon autonomous research has shown promise in accelerating scientific progress through sustained cycles of hypothesis generation, implementation, and validation. However, this Generate-Execute-Feedback paradigm relies on reactive trial-and-error, where costly and time-consuming executions introduce severe feedback delays, throttling evolutionary progress under explosively expanding search space. To address this challenge, we propose JANUS, a framework that unifies future outcomes forecasting and past experience reflection through a Predict-Verify-Evolve loop driven by a co-evolving world model. Within an evolving graph, the research agent proposes candidates while world model scores them by forecasting value improvement, information gain, and exploration utility, then accordingly selects, refines, or prunes branches prior to execution. After receiving ground-truth feedback, JANUS distills experience into evolving skills: hierarchical skills for research agent, exploration-strategy skills for world model, and their coordination protocols. This mechanism enables continual co-evolution: the research agent sharpens candidate generation while the world model refines its predictive judgment over extended horizons. Extensive evaluations on MLS-Bench-Lite and real research tasks demonstrate that JANUS significantly outperforms state-of-the-art baselines, achieving both higher evolving efficiency and ceiling.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.13194 [cs.AI] |
| (or arXiv:2610.13194v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13194 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chenghao Jia [view email]
[v1]
Fri, 9 Oct 2026 08:13:28 UTC (5,389 KB)
来源：arXiv：cs.AI · arxiv.org