Recent advances, such as DeepSeek R1-Zero, highlight the effectiveness of incentive training, a reinforcement learning paradigm that computes rewards solely based on the final answer part of a language model's output, thereby encouraging the generation of intermediate reasoning steps.However, these methods fundamentally rely on external verifiers, which limits their applicability to domains like mathematics and coding, where such verifiers are readily available.Although reward models can serve as verifiers, they require high-quality annotated data and are costly to train.In this work, we propose NOVER, NO-VERifier Reinforcement Learning, a general reinforcement learning framework that requires only standard supervised fine-tuning data with no need for an external verifier.NOVER enables incentive training across a wide range of text-to-text tasks and outperforms the model of the same size distilled from large reasoning models such as DeepSeek R1 671B by 7.7%.Moreover, the flexibility of NOVER enables new possibilities for optimizing large language models, such as inverse incentive training.

Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning. Inspired by the neural scaling law—increasing neurons enhances performance, this study explores whether the continuous addition of collaborative agents can yield similar benefits. Technically, we utilize directed acyclic graphs to organize agents into a multi-agent collaboration network (MacNet), upon which their interactive reasoning is topologically orchestrated for autonomous task solving. Extensive evaluations reveal that it effectively supports collaboration among over a thousand agents, with irregular topologies outperforming regular ones. We also identify a collaborative scaling law—the overall performance follows a logistic growth pattern as agents scale, with collaborative emergence occurring earlier than traditional neural emergence. We speculate this may be because scaling agents catalyzes their multidimensional considerations during interactive reflection and refinement, thereby producing more comprehensive artifacts. The code is available at https://github.com/OpenBMB/ChatDev/tree/macnet.

Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, Maosong Sun. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Websites are a crucial medium for conveying multimedia information. However, malicious websites can lurk among them, posing a threat to the security of users’ sensitive data and personal privacy. Hence, it is significant to identify and categorize such harmful sites. Various solutions have been proposed by researchers for this task, including extracting features from URLs and analyzing web page content using classification algorithms. To tackle these challenges, we suggest the Adaptive Balanced multimodal website Classification Framework (ABCF), which is designed for web page classification tasks. The framework includes a FAModule and FEAModule for better multimodal data fusion on websites. We also employ incremental learning to continuously improve our model and adapt to the changing network environment. Experiments on three website datasets confirm the effectiveness of our modules in capturing website features and demonstrate the superiority of our model compared to past malicious website classification systems. Code will be released at github.com/lzyy2435/ABCF/.

Large Language Model Multi-Agent Systems (LLM-MAS) have greatly progressed in solving complex tasks. It communicates among agents within the system to collaboratively solve tasks, under the premise of shared information. However, when agents' collaborations are leveraged to perform multi-person tasks, a new challenge arises due to information asymmetry, since each agent can only access the information of its human user. Previous MAS struggle to complete tasks under this condition. To address this, we propose a new MAS paradigm termed iAgents, which denotes Informative Multi-Agent Systems. In iAgents, the human social network is mirrored in the agent network, where agents proactively exchange human information necessary for task resolution, thereby overcoming information asymmetry. iAgents employs a novel agent reasoning mechanism, InfoNav, to navigate agents' communication towards effective information exchange. Together with InfoNav, iAgents organizes human information in a mixed memory to provide agents with accurate and comprehensive information for exchange. Additionally, we introduce InformativeBench, the first benchmark tailored for evaluating LLM agents' task-solving ability under information asymmetry. Experimental results show that iAgents can collaborate within a social network of 140 individuals and 588 relationships, autonomously communicate over 30 turns, and retrieve information from nearly 70,000 messages to complete tasks within 3 minutes.

Generating absent keyphrases, which do not appear in the input document, is challenging in the keyphrase prediction task. Most previous works treat the problem as an autoregressive sequence-to-sequence generation task, which demonstrates promising results for generating grammatically correct and fluent absent keyphrases. However, such an end-to-end process with a complete data-driven manner is unconstrained, which is prone to generate keyphrases inconsistent with the input document. In addition, the existing autoregressive decoding method makes the generation of keyphrases must be done from left to right, leading to slow speed during inference. In this paper, we propose a constrained absent keyphrase generation method in a prompt-based learning fashion. Specifically, the prompt will be created firstly based on the keywords, which are defined as the overlapping words between absent keyphrase and document. Then, a mask-predict decoder is used to complete the absent keyphrase on the constraint of prompt. Experiments on keyphrase generation benchmarks have demonstrated the effectiveness of our approach. In addition, we evaluate the performance of constrained absent keyphrases generation from an information retrieval perspective. The result shows that our approach can generate more consistent keyphrases, which can improve document retrieval performance. What’s more, with a non-autoregressive decoding manner, our model can speed up the absent keyphrase generation by 8.67× compared with the autoregressive method.

Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently.Despite these models provide high ROUGE scores, they are limited to generate comprehensive summaries with a high level of abstraction due to its degenerated attention distribution.We introduce Diverse Convolutional Seq2Seq Model(DivCNN Seq2Seq) using Determinantal Point Processes methods(Micro DPPs and Macro DPPs) to produce attention distribution considering both quality and diversity.Without breaking the end to end architecture, Di-vCNN Seq2Seq achieves a higher level of comprehensiveness compared to vanilla models and strong baselines.All the reproducible codes and datasets are available online 1 .1 available at https://github.com/thinkwee/DPPCNN Sum marization Article: marseille , france the french prosecutor leading an investigation into the crash of germanwings flight 9525 insisted wednesday that he was not aware of any video footage from on board the plane .marseille prosecutor brice robin told cnn that so far no videos were used in the crash investigation ...... of a cell phone video showing the harrowing final seconds from on board germanwings flight 9525 as it crashed into the french alps .......paris match and bild reported that the video was recovered from a phone at the wreckage site ....... cnn 's frederik pleitgen , pamela boykoff , antonia mortensen , sandrine amiel and anna-maja rappard contributed to this report .CNN Seq2Seq: french prosecutor UNK robin says he was not aware of any video