WenHao Wang, Peizhi Niu, Zhao Xu, Zhaoyu Chen, Jian Du, Yaxin Du, Xianghe Pang, Keduan Huang, Yanfeng Wang, Qiang Yan, Siheng Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the network. To extend coding capabilities beyond function-level tasks to more challenging software-level development, we further propose RSD-Bench, a requirement-oriented software development benchmark, which features complex and diverse software requirements along with automatic evaluation of requirement correctness. Our experiments show that: i) The automatic requirement-aware evaluation in RSD-Bench closely aligns with human evaluations, validating its reliability as a software-level coding benchmark. ii) EvoMAC outperforms previous SOTA methods on both the software-level RSD-Bench and the function-level HumanEval benchmarks, reflecting its superior coding capabilities.

LLM-based multi-agent systems (MAS) have shown significant potential in tackling diverse tasks. However, to design effective MAS, existing approaches heavily rely on manual configurations or multiple calls of advanced LLMs, resulting in inadaptability and high inference costs. In this paper, we simplify the process of building an MAS by reframing it as a generative language task, where the input is a user query and the output is a corresponding MAS. To address this novel task, we unify the representation of MAS as executable code and propose a consistency-oriented data construction pipeline to create a high-quality dataset comprising coherent and consistent query-MAS pairs. Using this dataset, we train MAS-GPT, an open-source medium-sized LLM that is capable of generating query-adaptive MAS within a single LLM inference. The generated MAS can be seamlessly applied to process user queries and deliver high-quality responses. Extensive experiments on 9 benchmarks and 5 LLMs show that the proposed MAS-GPT consistently outperforms 10+ baseline MAS methods on diverse settings, indicating MAS-GPT’s high effectiveness, efficiency and strong generalization ability. The codes are released at https://github.com/rui-ye/MAS-GPT.

In federated learning (FL), data heterogeneity is one key bottleneck that causes model divergence and limits performance. Addressing this, existing methods often regard data heterogeneity as an inherent property and propose to mitigate its adverse effects by correcting models. In this paper, we seek to break this inherent property by generating data to complement the original dataset to fundamentally mitigate heterogeneity level. As a novel attempt from the perspective of data, we propose federated learning with consensus-oriented generation (FedCOG). FedCOG consists of two key components at the client side: complementary data generation, which generates data extracted from the shared global model to complement the original dataset, and knowledge-distillation-based model training, which distills knowledge from global model to local model based on the generated data to mitigate over-fitting the original heterogeneous dataset. FedCOG has two critical advantages: 1) it can be a plug-and-play module to further improve the performance of most existing FL methods, and 2) it is naturally compatible with standard FL protocols such as Secure Aggregation since it makes no modification in communication process. Extensive experiments on classical and real-world FL datasets show that FedCOG consistently outperforms state-of-the-art methods. Code is available at https://github.com/rui-ye/FedCOG.

Trained on massive publicly available data, large language models (LLMs) have demonstrated tremendous success across various fields.While more data contributes to better performance, a disconcerting reality is that high-quality public data will be exhausted in a few * Siheng Chen is the corresponding author.

Federated learning has enabled multiple parties to collaboratively train large language models without directly sharing their data (FedLLM).Following this training paradigm, the community has put massive efforts from diverse aspects including framework, performance, and privacy.However, an unpleasant fact is that there are currently no realistic datasets and benchmarks for FedLLM and previous works all rely on artificially constructed datasets, failing to capture properties in real-world scenarios.Addressing this, we propose FedLLM-Bench, which involves 8 training methods, 4 training datasets, and 6 evaluation metrics, to offer a comprehensive testbed for the FedLLM community.FedLLM-Bench encompasses three datasets (e.g., user-annotated multilingual dataset) for federated instruction tuning and one dataset (e.g., user-annotated preference dataset) for federated preference alignment, whose scale of client number ranges from 38 to 747.Our datasets incorporate several representative diversities: language, quality, quantity, instruction, length, embedding, and preference, capturing properties in real-world scenarios.Based on FedLLM-Bench, we conduct experiments on all datasets to benchmark existing FL methods and provide empirical insights (e.g., multilingual collaboration).We believe that our FedLLM-Bench can benefit the FedLLM community by reducing required efforts, providing a practical testbed, and promoting fair comparisons.Code and datasets are available at https://github.com/rui-ye/FedLLM-Bench.