arXiv AI September 17, 2026 By Jiaxuan Jiang, Liyuan He, Zhixuan Fang

CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents

CERA-MoA introduces a co-evolving router and independently learning agents for Mixture-of-Agents systems, allowing routing strategies to adapt to evolving agent capabilities. The framework uses a predictive familiarity estimator based on mid-layer hidden states to evaluate semantic competence, and a cumulative-threshold adaptive routing mechanism to activate a minimal agent subset. Experiments across multiple domains show that CERA-MoA outperforms static-agent routing and fixed-workflow fine-tuning baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Sep 16

CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents

Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate processes, limiting their ability to respond to evolving agent capabilities. This disconnect p...

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 7

Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration

arXiv:2511. 02200v2 Announce Type: replace Abstract: The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse agents to integrate unique expertise, collaborate flexibly, and address challenges unattainable for individual models.

By Jingbo Wang, Sendong Zhao, Haochun Wang, Yuzheng Fan, Ting Liu

llms agents benchmarks

arXiv AI

1d ago

EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation

arXiv:2610.35690v1 Announce Type: new Abstract: Serving web queries at scale with multi-agent systems requires jointly configuring large language models, collaboration modes, agent counts, interactio...

By Yitao Xiao, Xu Zhang, Ye Cheng, Shaoyong Guo, Yan Sun, Ziyue Zhu, Sitao Xie, Guo Tong, Haoran Luo

llms agents reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Oct 8

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

SkillRL is a framework that enhances large language model agents by automatically discovering and evolving skills from raw experience. It builds a hierarchical skill library called SkillBank, uses an adaptive retrieval strategy for heuristics, and allows the skill library to co‑evolve with the agent’s policy during reinforcement learning. These techniques reduce token usage and improve reasoning, achieving state‑of‑the‑art results on ALFWorld, WebShop, and seven search‑augmented tasks, outperforming baselines by 15.3% and remaining robust as task complexity grows.

By Peng Xia, Jianwen Chen, Hanyang Wang, Jiaqi Liu, Kaide Zeng, Yu Wang, Siwei Han, Yiyang Zhou, Xujiang Zhao, Haifeng Chen, Zeyu Zheng, Cihang Xie, Huaxiu Yao

llms agents reinforcement-learning efficiency benchmarks

arXiv AI

Sep 23

ACLArena: Agent Continue Learning in Multi-stage Post-training

arXiv:2609.23989v1 Announce Type: new Abstract: Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of tr...

By Haixin Wang, Xiaoxuan Wang, Junkai Zhang, Han Zhang, Renliang Sun, Alexander K Taylor, Yidan Shi, Haoran Deng, Chenguang Wang, Jason Cong, Yizhou Sun, Wei Wang

agents reinforcement-learning fine-tuning efficiency

arXiv AI

Jun 2

PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning

arXiv:2606. 00395v1 Announce Type: cross Abstract: Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale.

By Daize Dong, Junlin Chen, Haolong Jia, Jiawei Wu, Huanwei Di, Jiang Liu, Jialian Wu, Zhengzhong Liu, Zicheng Liu, Emad Barsoum, Dimitris N. Metaxas, Hongyi Wang

llms reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents

Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration

EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

ACLArena: Agent Continue Learning in Multi-stage Post-training

PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning