Effective memory management is essential for large language model agents to navigate long-horizon tasks. Recent research has explored using Reinforcement Learning to develop specialized memory manager agents. However, existing approaches rely on final task performance as the primary reward, which results in severe reward sparsity and ineffective credit assignment, providing insufficient guidance for individual memory operations. To this end, we propose Fine-Mem, a unified framework designed for fine-grained feedback alignment. First, we introduce a Chunk-level Step Reward to provide immediate step-level supervision via auxiliary chunk-specific question answering tasks. Second, we devise Evidence-Anchored Reward Attribution to redistribute global rewards by anchoring credit to key memory operations, based on the specific memory items utilized as evidence in reasoning. Together, these components enable stable policy optimization and align local memory operations with the long-term utility of memory. Experiments on Memalpha and MemoryAgentBench demonstrate that Fine-Mem consistently outperforms strong baselines, achieving superior success rates across various sub-tasks. Further analysis reveals its adaptability and strong generalization capabilities across diverse model configurations and backbones

High-quality chain-of-thought has demonstrated strong potential for unlocking the reasoning capabilities of large language models. However, current paradigms typically treat the reasoning process as an indivisible sequence, lacking an intrinsic mechanism to quantify step-wise information gain. This granularity gap manifests in two limitations: inference inefficiency from redundant exploration without explicit guidance, and optimization difficulty due to sparse outcome supervision or costly external verifiers. In this work, we propose CoT-Flow, a framework that reconceptualizes discrete reasoning steps as a continuous probabilistic flow, quantifying the contribution of each step toward the ground-truth answer. Built on this formulation, CoT-Flow enables two complementary methodologies: flow-guided decoding, which employs a greedy flow-based decoding strategy to extract information-efficient reasoning paths, and flow-based reinforcement learning, which constructs a verifier-free dense reward function. Experiments on challenging benchmarks demonstrate that CoT-Flow achieves a superior balance between inference efficiency and reasoning performance.

Multilingual document-grounded dialogue, where the system is required to generate responses based on both the conversation Multilingual context and external knowledge sources. Traditional pipeline methods for knowledge identification and response generation, while effective in certain scenarios, suffer from error propagation issues and fail to capture the interdependence between these two sub-tasks. To overcome these challenges, we propose the application of the SLDT method, which treats passage-knowledge selection as a sequential decision process rather than a single-step decision process. We achieved winner 3rd in dialdoc 2023 and we also validated the effectiveness of our method on other datasets. The ablation experiment also shows that our method significantly improves the basic model compared to other methods.

Recently, many task-oriented dialogue systems need to serve users in different languages. However, it is time-consuming to collect enough data of each language for training. Thus, zero-shot adaptation of cross-lingual task-oriented dialog systems has been studied. Most of existing methods consider the word-level alignments to conduct two main tasks for task-oriented dialogue system, i.e., intent detection and slot filling, and they rarely explore the dependency relations among these two tasks. In this paper, we propose a hierarchical framework to classify the pre-defined intents in the high-level and fulfill slot filling under the guidance of intent in the low-level. Particularly, we incorporate sentence-level alignment among different languages to enhance the performance of intent detection. The extensive experiments report that our proposed method achieves the SOTA performance on a public task-oriented dialog dataset.

Aspect-based sentiment analysis is a fine-grained sentiment classification task. Recently, graph neural networks over dependency trees have been explored to explicitly model connections between aspects and opinion words. However, the improvement is limited due to the inaccuracy of the dependency parsing results and the informal expressions and complexity of online reviews. To overcome these challenges, in this paper, we propose a dual graph convolutional networks (DualGCN) model that considers the complementarity of syntax structures and semantic correlations simultaneously. Particularly, to alleviate dependency parsing errors, we design a SynGCN module with rich syntactic knowledge. To capture semantic correlations, we design a SemGCN module with self-attention mechanism. Furthermore, we propose orthogonal and differential regularizers to capture semantic correlations between words precisely by constraining attention scores in the SemGCN module. The orthogonal regularizer encourages the SemGCN to learn semantically correlated words with less overlap for each word. The differential regularizer encourages the SemGCN to learn semantic features that the SynGCN fails to capture. Experimental results on three public datasets show that our DualGCN model outperforms state-of-the-art methods and verify the effectiveness of our model.