arXiv:2606. 24437v1 Announce Type: new Abstract: Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines.
By Heng Ping, Arijit Bhattacharjee, Peiyu Zhang, Shixuan Li, Wei Yang, Ali Jannesari, Nesreen Ahmed, Paul Bogdan
The paper introduces a method to improve test-time scaling (TTS) for large language models by using multi-agent systems (MAS) to split long reasoning chains into manageable contexts. A new dataset, M500, containing 500 multi-agent collaborative reasoning traces, is used to fine‑tune open‑source models, enabling them to learn collaborative patterns and outperform their base versions. An adaptive scaling strategy with a "CEO" agent is proposed to dynamically guide reasoning depth, and experiments in the AgentVerse framework confirm the effectiveness of the approach.
By Can Jin, Hongwu Peng, Qixin Zhang, Yujin Tang, Dimitris N. Metaxas, Tong Che
arXiv:2606. 17803v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process.
By Vaggelis Dorovatas, Nancy Kalaj, Rahaf Aljundi
The paper introduces Gated-Memory Routing, a method for efficient collaboration in multi‑agent large language model systems. It uses a learned execution memory with write and retrieval gates to keep only non‑redundant reasoning steps, and an adaptive halting controller to stop execution when enough evidence is gathered. Experiments on five reasoning and code‑generation benchmarks show the approach achieves higher accuracy and reduces inference cost by 31.9% compared to the strongest baseline.
By Rakibul Hasan Rajib, Mengxing Zheng, Qian Lou
arXiv:2604. 20140v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks.
By Darsh Kachroo, Arjun Prasaath Anbazhagan, Adriana Caraeni, Brennan Lagasse, Kevin Zhu
arXiv:2607. 22562v1 Announce Type: new Abstract: Managing long-context dependencies remains a primary bottleneck in LLM agents, as redundant and irrelevant information can degrade multi-step reasoning.
By Ning Yang, Siqi Li, Miaoxin Shen, Yuan Zhou, Meng Zhang, Tong Li, Haijun Zhang