الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in domains where task outcomes can be reliably evaluated, but long-horizon interaction remains challenging due to sparse terminal feedback and difficult credit assignment. Process rewards provide denser supervision, yet the capabilities most relevant for training can change as the policy evolves: a behavior that is easy to evaluate or frequently deficient need not be the bottleneck currently limiting task success. We introduce RewardWeaver, a self-evolving reward adaptation framework for language agents in long-horizon interaction. RewardWeaver maintains a validated capability space in which the semantics of admitted Rubrics remain fixed, and closes the loop between policy optimization, task evaluation, failure attribution, and reward adaptation. After each training stage, it performs outcome-grounded backward attribution on low-outcome trajectories, aggregates recurrent and policy-controlled capability bottlenecks, and dynamically selects the corresponding process rewards for the next stage. Recurrent failures not covered by the existing capability space trigger a separate, controlled expansion procedure. We evaluate REWARDWEAVER on SOTOPIA, Amazon?HistoryPrice, and a newly constructed Sales Benchmark. Across social interaction, bilateral bargaining, and domain-specific sales, REWARDWEAVER establishes new state-of-the-art (SOTA) results. Ablations further demonstrate the importance of dynamic reward allocation, failure-grounded attribution, and stable semantics for admitted capabilities.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Xiao, H., Zhang, B., Liu, P., Zheng, Y., Yin, H., Liu, H., & Zhang, F. (2026). RewardWeaver: تعلم تفاعلي طويل الأفق لوكلاء اللغة عبر تكيّف المكافأة المتطور ذاتياً. https://omanscience.com/ar/articles/rewardweaver-long-horizon-interactive-learning-for-language-agents-via-self-evolving-reward-adaptation
MLA 9
Xiao, Hengbo, et al. "RewardWeaver: تعلم تفاعلي طويل الأفق لوكلاء اللغة عبر تكيّف المكافأة المتطور ذاتياً." https://omanscience.com/ar/articles/rewardweaver-long-horizon-interactive-learning-for-language-agents-via-self-evolving-reward-adaptation.
شيكاغو (المؤلف–التاريخ)
Xiao, Hengbo, Boyao Zhang, Purui Liu, Yuxuan Zheng, Haoran Yin, Haibo Liu, and Fan Zhang. 2026. "RewardWeaver: تعلم تفاعلي طويل الأفق لوكلاء اللغة عبر تكيّف المكافأة المتطور ذاتياً." https://omanscience.com/ar/articles/rewardweaver-long-horizon-interactive-learning-for-language-agents-via-self-evolving-reward-adaptation.
هارفارد
Xiao, H., Zhang, B., Liu, P., Zheng, Y., Yin, H., Liu, H. and Zhang, F. (2026) 'RewardWeaver: تعلم تفاعلي طويل الأفق لوكلاء اللغة عبر تكيّف المكافأة المتطور ذاتياً', Available at: https://omanscience.com/ar/articles/rewardweaver-long-horizon-interactive-learning-for-language-agents-via-self-evolving-reward-adaptation.
فانكوفر
Xiao H, Zhang B, Liu P, Zheng Y, Yin H, Liu H, et al. RewardWeaver: تعلم تفاعلي طويل الأفق لوكلاء اللغة عبر تكيّف المكافأة المتطور ذاتياً. https://omanscience.com/ar/articles/rewardweaver-long-horizon-interactive-learning-for-language-agents-via-self-evolving-reward-adaptation
IEEE
H. Xiao, B. Zhang, P. Liu, Y. Zheng, H. Yin, H. Liu, and F. Zhang, "RewardWeaver: تعلم تفاعلي طويل الأفق لوكلاء اللغة عبر تكيّف المكافأة المتطور ذاتياً," https://omanscience.com/ar/articles/rewardweaver-long-horizon-interactive-learning-for-language-agents-via-self-evolving-reward-adaptation.