Debate Dialogue Generation requires multi-turn responses that are both high quality and directly engage with the opponent’s arguments. Existing methods often emphasize intrinsic quality but overlook argument-level engagement, leading to superficial or irrelevant rebuttals. We propose a Dual-dIM ensional rEflection and Refinement (DIMER) framework that explicitly models argument engagements and iteratively improves responses. DIMER combines: (1) retrieval-augmented generation for factual grounding, (2) dual-dimensional reflection evaluating both argument coverage/rebuttal and intrinsic quality, and (3) unified refinement that leverages reflection feedback to enhance responses. We also introduce a high-quality debate dataset synthesized with DIMER, enabling supervised fine-tuning and direct preference optimization. Experiments on Debate Arena show that DIMER significantly improves the coherence, persuasiveness, and engagement-awareness of generated debate dialogues.

Event Causality Extraction (ECE) aims to extract causal event pairs from text. Existing methods overlook the interplay between causal event pairs and their corresponding textual evidence (e.g., causal event mention pairs), and fail to effectively leverage global causal dependency information. To address these issues, we propose a Mention-Level Causal Evidence and Global Causal Graph Reasoning (MLCE-GCGR) framework to enhance ECE. First, we introduce an auxiliary Event Mention Causality Extraction (EMCE) task, which extracts causal event mention pairs, to provide evidence for the main ECE task, and design a Dual-Level Interaction Enhancement (DLIE) strategy to enhance the bidirectional interplay between event-level and mention-level causality. Second, we develop a Global Causal Graph Reasoning (GCGR) module that simulates human-like multi-turn reasoning, aiming to progressively refine the causal graph by capturing global dependencies among event mentions, types, and arguments. Experiments on four benchmark datasets show that our method outperforms state-of-the-art approaches. Moreover, by extracting causal event mention pairs as supporting evidence, our approach improves the interpretability of structured causality extraction.

Large language models (LLMs) can call tools effectively, yet they remain brittle in multi-turn execution: after a tool-call error, smaller models often fall into repetitive invalid re-invocations instead of interpreting the feedback and recovering. This failure mode persists because current training paradigms do not explicitly teach models how to recover from execution errors. In particular, standard reinforcement learning (RL) collapses rich failure experience into sparse negative rewards, while pre-collected error-correction datasets become mismatched to the policy’s evolving failure modes. To bridge this gap, we propose Fission-GRPO, a framework that converts execution errors into on-policy corrective supervision within the RL training loop. Our core mechanism fissions each failed trajectory into a new training instance by augmenting it with diagnostic feedback from a fine-tuned Error Simulator, then resampling multiple recovery rollouts on-policy. This enables the model to learn from the precise errors it makes during exploration, rather than from static, pre-collected error cases. On BFCL v4 Multi-Turn, Fission-GRPO improves the error recovery rate of Qwen3-8B by 5.7% absolute and overall accuracy by 4.0% (from 42.75% to 46.75%), outperforming both RL baselines and specialized tool-use agents. The method further generalizes to TAU-Bench and TAU2-Bench, achieving leading results across most settings with gains up to +17.4%.

Reinforcement learning for user-centric agents is limited by the cost, latency, and risk of collecting online feedback, as well as by the lack of counterfactual comparisons under the same user state. In this paper, we propose World Model-Guided Reinforcement Learning via counterfactual user engagement simulation (WMG-RL), a framework in which a frozen user simulator provides reward supervision before real user exposure. Motivated by language world models, we instantiate the simulator as a User Engagement World Model (UEWM), which treats a recommended item as the agent action and the user's heterogeneous feedback as the environment observation. Rather than learning one fixed environment transition, UEWM learns to infer user-specific dynamics from engagement history and apply them to candidate items. In WMG-RL, a downstream policy proposes multiple candidate items for the same history; UEWM predicts the corresponding engagement feedback in parallel; and the simulated feedback is converted into dense rewards for policy optimization. Experiments show that UEWM provides reliable and transferable reward signals across domains, and that WMG-RL enables a compact 1.7B student policy to match or surpass much larger LLMs on downstream recommendation tasks.

Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations. Existing evaluation approaches, relying on model heuristics, expert rubrics, or user simulation, fail to capture the diversity and subtlety of real human expectations, causing models to appear competent while misaligning with what users actually seek. we present the first systematic study of user expectations in real-world LLM interactions, proposing a principled procedure to extract semantically rich expectations and introducing ExpectBench, a benchmark grounded in real user expectations. Analyses reveal that current LLMs struggle to satisfy and anticipate what users hope to obtain, highlighting a fundamental source of misalignment. Building on these observations, we propose LENS, a lightweight latent expectation–aware response generation framework. LENS enables models to internalize user expectations and generate better-aligned responses, consistently improving expectation satisfaction and underscoring the importance of explicitly modeling user expectations for realistic human–AI alignment.

Processing long-context information remains a major challenge for large language models (LLMs). Retrieval-Augmented Generation (RAG) alleviates this issue by fetching relevant passages, yet it often wastes retrieval budget on near-duplicates and disperses mutually relevant evidence across an oversizes prompt. Cognitive studies suggest that human readers instead maintain only a few topical chunks in working memory and selectively reactivate details when needed. Inspired by this principle, we propose Topic-Graph-based RAG (TGRAG) for long document question answering (LDQA). Specifically, TGRAG (1) segments a document into sentence-level units and assigns each a high-level topic label; (2) connects sentences via lightweight topic-and similarity-based edges to construct a sparse topic graph that approximates coarser topical clusters; and (3) activates the k most relevant sentences together with their strongest neighbors at query time. This graph-guided retrieval preserves cross-sectional context while reducing redundancy, thereby improving the activation of relevant information for long-term reasoning. Experiments on three LDQA benchmarks demonstrate that TGRAG outperforms competitive RAG and GraphRAG baselines, improving over the strongest baseline by 0.8, 1.0, and 2.8 absolute accuracy points on NarrativeQA, HotpotQA, and MuSiQue, respectively (averaged over strict and lenient LLM-based rating criteria), which validates its effectiveness.

Long Document Question Answering (LDQA) remains a critical challenge for LLMs, as lengthy contexts often exceed context window and contain irrelevant distractors. We propose Topic-Chain Compression, a novel prompt compression framework that organizes documents into topic chains. The method first splits the document into sentences, each labeled with a topic derived by a Large Language Model (LLM). Sentences sharing the same topic are linked sequentially, forming coherent topic chains. Relevance of a chain to a given query is assessed via a Cross-Encoder at the sentence level, with chain scores obtained by aggregation. The most relevant chains are retained to form a compressed prompt for final inference. TCC balances structural coherence with query sensitivity, enabling more accurate and efficient long-document reasoning in LLMs. Empirical results demonstrate the effectiveness of the framework compared with baseline methods.

Integrating memory components into large language models (LLMs) can improve the generation quality for long-term conversations. However, existing memory management methods largely overlook the cognition and regulation of the memory process, lacking the capability to dynamically manage and utilize memory on demand. To address this challenge, this paper approaches Meta-Memory for Memory Management (M$^{4}$), a novel paradigm that equips LLMs with the ability for self-monitoring and self-reflective memory management. In long-term conversations, where dialogue history accumulates continuously, the meta-memory capability of M$^{4}$ enables LLMs to autonomously 1) identify what knowledge needs to be memorized; 2) determine how to construct and store memory; 3) monitor the correctness and validity of the acquired information; and 4) decide when to learn more and how to retrieve information to refine their responses. Experimental results on two long-term conversation datasets and two long-term question-answering datasets demonstrate that our M$^{4}$ significantly enhances the memory management capacity of LLMs in long-term information learning, achieving more efficient storage and higher-quality response generation.

Large language models have improved dialogue systems, but often process conversational turns in isolation, overlooking the event structures that guide natural interactions. Hence we introduce EventWeave, a framework that explicitly models relationships between conversational events to generate more contextually appropriate dialogue responses. EventWeave constructs a dynamic event graph that distinguishes between core events (main goals) and supporting events (interconnected details), employing a multi-head attention mechanism to selectively determine which events are most relevant to the current turn. Unlike summarization or standard graph-based approaches, our method captures three distinct relationship types between events, allowing for more nuanced context modeling. Experiments on three dialogue datasets demonstrate that EventWeave produces more natural and contextually appropriate responses while requiring less computational overhead than models processing the entire dialogue history. Ablation studies confirm improvements stem from better event relationship modeling rather than increased information density. Our approach effectively balances comprehensive context understanding with generating concise responses, maintaining strong performance across various dialogue lengths through targeted optimization techniques.

Recent advances in video editing have been largely driven by large-scale instruction-based datasets. However, existing datasets still suffer from two critical limitations. First, target videos are commonly produced by automatic editing models, which may introduce visible artifacts and unreliable supervision signals. Second, most public datasets rely primarily on textual instructions, while lacking visual references that are crucial for precise, identity-preserving, and controllable editing. To address these limitations, we introduce RefVideo-6M, a large-scale reference-guided editing dataset containing 5 million video editing samples and 1 million image editing samples. To ensure reliable supervision, our dataset uses a construction pipeline that treats artifact-free real videos as editing targets and generates quality-filtered input conditions with multiple editing experts. In addition, it provides approximately 6 million visual references, covering diverse reference types and editing scenarios, thereby enabling models to learn fine-grained visual correspondence beyond text-only instructions. Based on RefVideo-6M, we further train a reference-guided video editing model, Ref-MoT, to evaluate the effectiveness and scalability of the proposed dataset. Extensive experiments demonstrate that RefVideo-6M provides substantially more reliable supervision than existing datasets and enables the training of powerful editing models with improved visual quality, controllability, and reference consistency. The open-source dataset is available at https://huggingface.co/datasets/RefVideo6M/RefVideo6M.

Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. As dialogue histories grow in length and accumulate noise, existing long-context models struggle to accurately identify temporally pertinent information, significantly impairing reasoning performance. To address this, we introduce **Memory-T1**, a framework that learns a time-aware memory selection policy using reinforcement learning (RL). It employs a coarse-to-fine strategy, first pruning the dialogue history into a candidate set with temporal and retriever filters, followed by an RL agent that selects the precise evidence. The RL training is guided by a multi-level reward function optimizing (i) accuracy, (ii) evidence grounding, and (iii) temporal consistency. This temporal consistency reward provides a dense signal by evaluating alignment at both the session-level (range proximity) and the utterance-level (evidence density), enabling the agent to resolve subtle chronological ambiguities. On the Time-Dialog benchmark, Memory-T1 boosts a 7B model to an overall score of 67.0\%, establishing a new state-of-the-art performance for open-source models and outperforming a 14B baseline by 10.2\%. Ablation studies show temporal consistency and evidence grounding rewards jointly contributing to a 15.0\% performance gain.Moreover, Memory-T1 maintains robustness up to 128k tokens, where baseline models collapse, proving effectiveness against noise in extensive dialogue histories.

Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill. This gap suggests that following procedural guidance and improving it from execution evidence are distinct capabilities. Inference time loops can repair skills but do not improve the model that writes the next one. We study how to organize execution experience from intermediate skills into training states for an optimizer. We introduce WER (Write, Execute, and Refine), a multi-phase framework that trains a Skill Optimizer outside a frozen executor. The optimizer proposes skills, a frozen agent executes each repeatedly, and a programmatic verifier scores the outcomes. The scores provide relative credit and select mixed-outcome records. Matched successful and failed trajectories from these records form the next phase's refinement states, so the optimizer learns from the consequences of its earlier outputs. On BFCL v4 multi-turn and tau2-bench, WER improves average Pass@1 over the no-skill baseline by 7.80 and 3.85 points, respectively. Under an identical refinement workflow, it outperforms the same backbone without optimizer training by 9.35 and 10.29 points. The trained 4B optimizer reaches 76.63 percent on BFCL v4, outperforming all evaluated off-the-shelf general-purpose models used as skill optimizers on average.

Multimodal Emotion-Cause Pair Extraction (ECPE) in Conversations (MC-ECPE) aims to simultaneously identify emotions and their causes within conversations across different modalities. Early paradigms of ECPE involved a two-step framework for emotion and cause extraction and pairing, resulting in error accumulation. Thus, there is a growing interest in end-to-end ECPE. Despite the progress, emotion, and cause extraction are essentially mutually dependent, yet existing efforts fail to model it deeply. Additionally, Baselines for the MC-ECPE task primarily use traditional fusion methods like concatenation, limiting context understanding between modalities. Based on this, we propose the Multi-Task Mutual Learning (MTML) framework, which utilizes implicit and explicit modeling strategies to model the mutual dependency between emotion and cause extraction. Specifically, we introduce a Multimodal Interactive Graph Attention Network (MIGAT) with three types of connections: intra-modal for conversational context, cross-modal for multimodal fusion, and cross-task for capturing dependencies between emotion and cause extraction tasks. Implicit modeling leverages cross-task connections within MIGAT and information from shared components in progressive multi-task learning (PMTL), while explicit modeling iteratively extracts emotional and causal probability distributions to enhance subsequent reasoning. Experimental results demonstrate the superiority of our MTML over state-of-the-art methods.

Multimodal stance detection leverages multimodal information to identify an author’s stance towards a specific target. Existing approaches typically focus on coarse alignment between image and text representations, overlooking fine-grained modality alignment oriented by the target. Therefore, we propose a novel Target-oriented Consistent Cross-modal Alignment (TCCA) method. Our approach first designs a Target-oriented Prompt as Visual-Language Query module, which leverages the target to activate visual and textual representations, guiding the model to focus on stance-relevant visual regions and text spans. This enables more efficient and precise cross-modal semantic fusion. Furthermore, we devise a Target-oriented Cross-modal Alignment module to align the target-activated image and text representations. This facilitates tighter target-oriented cross-modal information and enhances the model’s ability to capture stance-specific information. By orienting both modalities towards the target, TCCA effectively simplifies the alignment process and improves the model’s capacity to capture fine-grained stance cues. Finally, we construct the Multiview Decoding module that enables more effective extraction of rich stance cues from diverse perspectives. The experimental results demonstrate that TCCA outperforms existing approaches in most metrics, validating its effectiveness for multimodal stance detection.

Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming and low in coverage, while large language models (LLMs) often produce hallucinated or logically inconsistent outputs. We present SymbolicThought, a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning. The system constructs editable character relationship graphs, refines them using seven types of logical constraints, and enables real-time validation and conflict resolution through an interactive interface. To support logical supervision and explainable social analysis, we release a dataset of 160 interpersonal relationships with corresponding logical structures. Experiments show that SymbolicThought improves annotation accuracy and consistency while significantly reducing time cost, offering a practical tool for narrative understanding, explainable AI, and LLM evaluation.

Multimodal Stance Detection (MSD) is a crucial task for understanding public opinion on social media. Existing methods predominantly operate by learning to fuse modalities. They lack an explicit reasoning process to discern how inter-modal dynamics, such as irony or conflict, collectively shape the user's final stance, leading to frequent misjudgments. To address this, we advocate for a paradigm shift from *learning to fuse* to *learning to reason*. We introduce **MIND**, a **M**eta-cognitive **I**ntuitive-reflective **N**etwork for **D**ual-reasoning. Inspired by the dual-process theory of human cognition, MIND operationalizes a self-improving loop. It first generates a rapid, intuitive hypothesis by querying evolving Modality and Semantic Experience Pools. Subsequently, a meta-cognitive reflective stage uses Modality-CoT and Semantic-CoT to scrutinize this initial judgment, distill superior adaptive strategies, and evolve the experience pools themselves. These dual experience structures are continuously refined during training and recalled at inference to guide robust and context-aware stance decisions. Extensive experiments on the MMSD benchmark demonstrate that our MIND significantly outperforms most baseline models and exhibits strong generalization.

Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods prioritise semantic similarity over task intent, degrading multi-session coherence. We propose MemGuide, a two-stage intent-driven memory selection framework: (1) Intent‑Aligned Retrieval retrieves goal-consistent QA‑formatted memory units; (2) Missing‑Slot Guided Filtering reranks units by slot-completion gain via a chain‑of‑thought reasoner and fine‑tuned LLaMA‑8B filter. We also introduce the MS-TOD, the first multi-session TOD benchmark with 132 diverse personas, 956 task goals, and annotated intent-aligned memory targets. Evaluations on MS-TOD show that MemGuide boosts task success rate by 11% (88%→99%) and reduces dialogue length by 2.84 turns, and matches single‑session performance.

Stance detection is crucial for understanding the underlying attitude of an expression towards a target. Conversational stance detection is a more challenging stance detection task in real-world social media scenarios, as it involves detecting the user's stance by leveraging the target-related historical statements across conversational sessions. In this paper, we propose target-aware Memory Graph TamGraph, a novel method that dynamically leverages target-related statements for conversational stance detection. Instead of considering all preceding historical conversations or using no prior conversation information for stance detection, our TamGraph employs a stepwise, entropy-guided backtracking mechanism to selectively activate memory from historical conversations and dynamically constructs a target-aware graph to model the stance relations among utterances. This allows the exploitation of target-related information from the conversation history for stance detection while preventing the introduction of noise. Experimental results on both English and Chinese benchmarks demonstrate that our TamGraph substantially improves LLM performance on conversational stance detection.

Self-supervised learning (SSL) has shown great potential in learning generalizable representations for graph-structured data. However, existing SSL-based graph pre-training methods largely focus on improving graph representations by learning the structure information based on disturbing or reconstructing graphs, which ignores an important issue: the importance of different nodes in the graph structure may vary. To fill this gap, we propose a Centrality-guided Graph Pre-training (CenPre) framework to integrate the distinct importance of nodes in graph structure into the corresponding representations of nodes based on the centrality in graph theory. In this way, the different roles played by different nodes can be effectively leveraged when learning graph structure. The proposed CenPre contains three modules for node representation pre-training and alignment. The node-level importance learning module fuses the fine-grained node importance into node representation based on degree centrality, allowing the aggregation of node representations with equal/similar importance. The graph-level importance learning module characterizes the importance between all nodes in the graph based on eigenvector centrality, enabling the exploitation of graph-level structure similarities/differences when learning node representation. Finally, a representation alignment module aligns the pre-trained node representation using the original one, essentially allowing graph representations to learn structural information without losing their original semantic information, thereby leading to better graph representations. Extensive experiments on a series of real-world datasets demonstrate that the proposed CenPre outperforms the state-of-the-art baselines in the tasks of node classification, link prediction, and graph classification.