Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and reliance on ungrounded synthetic teacher supervision. To transcend these limitations, we propose , a framework that shifts the learning focus from mimicking high-level trajectories to learning interaction dynamics from executed transitions. Through a systematic investigation of self-supervised objectives, we identify that forward dynamics, defined as the generative prediction of future interface states, acts as the primary driver for scalability and outperforms inverse and backward objectives. leverages this insight by converting low-cost autonomous exploration into high-density generative supervision to learn a semantic transition world model from executed transitions. Experimental evaluations across a series of models demonstrate consistent gains from our approach: models utilizing Continual Pre-Training (CPT) on synthetic dynamics outperform non-CPT baselines with an average success rate improvement of 7% on offline benchmarks, which amplifies to a 16.8% gain in real-world online navigation. Furthermore, we observe that navigation performance scales with synthetic data volume. These results suggest that grounding agents in forward predictive modeling offers a promising pathway to scalable GUI automation with cross-domain adaptability and compositional generalization.

Multi-turn Text-to-SQL aims to translate a user’s conversational utterances into executable SQL while preserving dialogue coherence and grounding to the target schema. However, most existing systems only regard this task as a simple text translation task and follow a short-horizon paradigm, generating a query per turn without execution, explicit verification, and refinement, which leads to non-executable or incoherent outputs. We present MTSQL-R1, an agentic training framework for long-horizon multi-turn Text-to-SQL. We cast the task as a Markov Decision Process (MDP) in which an agent interacts with (i) a database for execution feedback and (ii) a persistent dialogue memory for coherence verification, performing an iterative propose->execute->verify->refine cycle until all checks pass. Experiments on CoSQL and SParC demonstrate that MTSQL-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing. Full recipes (including code, trained models, reasoning trajectories, etc.) will be released upon acceptance to contribute to community research.

Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP). However, the predominant pretraining of LLMs on extensive web-based texts remains insufficient for advanced scientific discovery, particularly in chemistry. The scarcity of specialized chemistry data, coupled with the complexity of multi-modal data such as 2D graph, 3D structure and spectrum, present distinct challenges. Although several studies have reviewed Pretrained Language Models (PLMs) in chemistry, there is a conspicuous absence of a systematic survey specifically focused on chemistry-oriented LLMs. In this paper, we outline methodologies for incorporating domain-specific chemistry knowledge and multi-modal information into LLMs, we also conceptualize chemistry LLMs as agents using chemistry tools and investigate their potential to accelerate scientific research. Additionally, we conclude the existing benchmarks to evaluate chemistry ability of LLMs. Finally, we critically examine the current challenges and identify promising directions for future research. Through this comprehensive survey, we aim to assist researchers in staying at the forefront of developments in chemistry LLMs and to inspire innovative applications in the field.

Using the pre-trained language models to understand source codes has attracted increasing attention from financial institutions owing to the great potential to uncover financial risks. However, there are several challenges in applying these language models to solve programming language related problems directly. For instance, the shift of domain knowledge between natural language (NL) and programming language (PL) requires understanding the semantic and syntactic information from the data from different perspectives. To this end, we propose the AstBERT model, a pre-trained PL model aiming to better understand the financial codes using the abstract syntax tree (AST). Specifically, we collect a sheer number of source codes (both Java and Python) from the Alipay code repository and incorporate both syntactic and semantic code knowledge into our model through the help of code parsers, in which AST information of the source codes can be interpreted and integrated. We evaluate the performance of the proposed model on three tasks, including code question answering, code clone detection and code refinement. Experiment results show that our AstBERT achieves promising performance on three different downstream tasks.

在散文阅读理解的鉴赏类问题中,对拟人句赏析考查比较频繁。目前,已有的工作仅对拟人句中的本体要素进行识别并抽取,存在要素抽取不完整的问题,尤其是当句子中出现多个本体时,需要确定拟人词与各个本体的对应关系。为解决这些问题,本文提出了基于人物特征增强的拟人句要素抽取方法。该方法利用特定领域的特征,增强句子的向量表示,再利用条件随机场模型对拟人句中的本体和拟人词要素进行识别。在此基础上,利用自注意力机制对要素之间的关系进行检测,使用要素同步机制和关系同步机制进行信息交互,用于要素识别和关系检测的输入更新。在自建的拟人数据集上进行<本体,拟人词>抽取的比较实验,结果表明本文提出的模型性能优于其他比较模型。