Dong Fang

Bowen Cao, Weibin Liao, Yushi Sun et al.

Text-to-SQL systems powered by Large Language Models have excelled on academic benchmarks but struggle in complex enterprise environments. The primary limitation lies in their reliance on static schema representations, which fails to resolve semantic ambiguity and scale effectively to large, complex databases. To address this, we propose APEX-SQL, an Agentic Text-to-SQL Framework that shifts the paradigm from passive translation to agentic exploration. Our framework employs a hypothesis-verification loop to ground model reasoning in real data. In the schema linking phase, we use logical planning to verbalize hypotheses, dual-pathway pruning to reduce the search space, and parallel data profiling to validate column roles against real data, followed by global synthesis to ensure topological connectivity. For SQL generation, we introduce a deterministic mechanism to retrieve exploration directives, allowing the agent to effectively explore data distributions, refine hypotheses, and generate semantically accurate SQLs. Experiments on BIRD (70.65% execution accuracy) and Spider 2.0-Snow (51.01% execution accuracy) demonstrate that APEX-SQL outperforms competitive baselines with reduced token consumption. Further analysis reveals that agentic exploration acts as a performance multiplier, unlocking the latent reasoning potential of foundation models in enterprise settings. Ablation studies confirm the critical contributions of each component in ensuring robust and accurate data analysis. Our code is released at https://github.com/Tencent/APEX-SQL-Project.

Zhiqin Yang, Yonggang Zhang, Wei Xue et al.

Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is conditional rather than universal, depending on an implicit assumption frequently violated in practice: the RLHF-optimal policy must prefer human-preferred responses. When this assumption fails, DPO optimizes relative advantage over the reference policy rather than absolute alignment with human preferences, leading to pathological convergence where policies decrease DPO loss while preferring dispreferred responses. We characterize when this assumption is violated, show the existence of an undesirable solution space, and prove that DPO and RLHF optimize fundamentally different objectives in such cases. To address this, we introduce Constrained Preference Optimization (CPO), augmenting RLHF with constraints for provable alignment. We further provide a geometric interpretation through soft margin ranking, revealing that DPO implements margin ranking with potentially negative targets. Our theoretical analysis establishes when DPOs' guarantees hold and provides solutions preserving simplicity with provable alignment. Comprehensive experiments on standard benchmarks demonstrate that CPO achieves state-of-the-art performance. Code is available at: https://github.com/visitworld123/CPO.

Weixin Mao, Weiheng Zhong, Zhou Jiang et al.

Existing robot policies predominantly adopt the task-centric approach, requiring end-to-end task data collection. This results in limited generalization to new tasks and difficulties in pinpointing errors within long-horizon, multi-stage tasks. To address this, we propose RoboMatrix, a skill-centric hierarchical framework designed for scalable robot task planning and execution in open-world environments. RoboMatrix extracts general meta-skills from diverse complex tasks, enabling the completion of unseen tasks through skill composition. Its architecture consists of a high-level scheduling layer that utilizes large language models (LLMs) for task decomposition, an intermediate skill layer housing meta-skill models, and a low-level hardware layer for robot control. A key innovation of our work is the introduction of the first unified vision-language-action (VLA) model capable of seamlessly integrating both movement and manipulation within one model. This is achieved by combining vision and language prompts to generate discrete actions. Experimental results demonstrate that RoboMatrix achieves a 50% higher success rate than task-centric baselines when applied to unseen objects, scenes, and tasks. To advance open-world robotics research, we will open-source code, hardware designs, model weights, and datasets at https://github.com/WayneMao/RoboMatrix.

Shuliang Liu, Songbo Yang, Dong Fang et al.

Object hallucination critically undermines the reliability of Multimodal Large Language Models, often stemming from a fundamental failure in cognitive introspection, where models blindly trust linguistic priors over specific visual evidence. Existing mitigations remain limited: contrastive decoding approaches operate superficially without rectifying internal semantic misalignments, while current latent steering methods rely on static vectors that lack instance-specific precision. We introduce Vision-Language Introspection (VLI), a training-free inference framework that simulates a metacognitive self-correction process. VLI first performs Attributive Introspection to diagnose hallucination risks via probabilistic conflict detection and localize the causal visual anchors. It then employs Interpretable Bi-Causal Steering to actively modulate the inference process, dynamically isolating visual evidence from background noise while neutralizing blind confidence through adaptive calibration. VLI achieves state-of-the-art performance on advanced models, reducing object hallucination rates by 12.67% on MMHal-Bench and improving accuracy by 5.8% on POPE.

Shuliang Liu, Xingyu Li, Hongyi Liu et al.

Reasoning Large Language Models (RLLMs) excelling in complex tasks present unique challenges for digital watermarking, as existing methods often disrupt logical coherence or incur high computational costs. Token-based watermarking techniques can corrupt the reasoning flow by applying pseudo-random biases, while semantic-aware approaches improve quality but introduce significant latency or require auxiliary models. This paper introduces ReasonMark, a novel watermarking framework specifically designed for reasoning-intensive LLMs. Our approach decouples generation into an undisturbed Thinking Phase and a watermarked Answering Phase. We propose a Criticality Score to identify semantically pivotal tokens from the reasoning trace, which are distilled into a Principal Semantic Vector (PSV). The PSV then guides a semantically-adaptive mechanism that modulates watermark strength based on token-PSV alignment, ensuring robustness without compromising logical integrity. Extensive experiments show ReasonMark surpasses state-of-the-art methods by reducing text Perplexity by 0.35, increasing translation BLEU score by 0.164, and raising mathematical accuracy by 0.67 points. These advancements are achieved alongside a 0.34% higher watermark detection AUC and stronger robustness to attacks, all with a negligible increase in latency. This work enables the traceable and trustworthy deployment of reasoning LLMs in real-world applications.

Zhuo Deng, Yuanhao Cai, Lu Chen et al.

Ophthalmologists have used fundus images to screen and diagnose eye diseases. However, different equipments and ophthalmologists pose large variations to the quality of fundus images. Low-quality (LQ) degraded fundus images easily lead to uncertainty in clinical screening and generally increase the risk of misdiagnosis. Thus, real fundus image restoration is worth studying. Unfortunately, real clinical benchmark has not been explored for this task so far. In this paper, we investigate the real clinical fundus image restoration problem. Firstly, We establish a clinical dataset, Real Fundus (RF), including 120 low- and high-quality (HQ) image pairs. Then we propose a novel Transformer-based Generative Adversarial Network (RFormer) to restore the real degradation of clinical fundus images. The key component in our network is the Window-based Self-Attention Block (WSAB) which captures non-local self-similarity and long-range dependencies. To produce more visually pleasant results, a Transformer-based discriminator is introduced. Extensive experiments on our clinical benchmark show that the proposed RFormer significantly outperforms the state-of-the-art (SOTA) methods. In addition, experiments of downstream tasks such as vessel segmentation and optic disc/cup detection demonstrate that our proposed RFormer benefits clinical fundus image analysis and applications. The dataset, code, and models are publicly available at https://github.com/dengzhuo-AI/Real-Fundus

Binyan Xu, Dong Fang, Haitao Li et al.

Multi-agent systems (MAS) tackle complex tasks by distributing expertise, though this often comes at the cost of heavy coordination overhead, context fragmentation, and brittle phase ordering. Distilling a MAS into a single-agent skill can bypass these costs, but this conversion lacks a principled answer for when and what to distill. Instead, the empirical outcome is surprisingly inconsistent: skill lift ranges from a 28% improvement to a 2% degradation across metrics of the exact same task. In this work, we reveal that skill utility is governed not by the task, but by the evaluation metric. We introduce Metric Freedom ($F$), the first a priori predictor of skill utility. $F$ measures the topological rigidity of a metric's scoring landscape by quantifying how output diversity couples with score variance via a Mantel test. Guided by $F$, we propose a two-stage adaptive distillation framework. Stage 1 acts as a selective extraction mechanism, extracting tools and knowledge while discarding restrictive structures on "free" metrics to preserve exploration. Stage 2 targets computationally intensive iterative refinement exclusively toward "rigid" metrics ($F \lesssim 0.6$) to eliminate trajectory-local overfitting. Evaluating across 4 tasks, 11 datasets, and 6 metrics, $F$ strongly predicts skill utility ($ρ= -0.62$, $p < 0.05$). Strikingly, identical agent trajectories yield diametrically opposite skill lifts under rigid versus free metrics, demonstrating that skill utility is fundamentally a metric-level property. Driven by this signal, our adaptive agent matches or exceeds the original MAS while reducing cost up to 8$\times$ and latency by up to 15$\times$.

Yushi Sun, Bowen Cao, Dong Fang et al.

Long-horizon conversational agents rely on memory systems with increasingly sophisticated retrieval mechanisms. However, retrieved fragments are typically fed to the language model as unstructured text, lacking the relational, temporal, and thematic structures essential for complex reasoning. To bridge this reasoning gap, we introduce GRAVITY (\textbf{G}eneration-time \textbf{R}elational \textbf{A}nchoring \textbf{V}ia \textbf{I}njected \textbf{T}opological Memor\textbf{Y}), a plug-and-play structured memory module. GRAVITY extracts three complementary knowledge representations from raw conversational utterances: entity profiles grounded in relational graphs, temporal event tuples linked into causal traces, and cross-session topic summaries. At generation time, it injects these representations into the host system's prompt as structured anchoring contexts. This approach effectively synthesizes scattered evidence into a coherent, query-relevant context without requiring any architectural modifications to the host model. Extensive evaluations across five diverse memory systems on the LongMemEval and LoCoMo benchmarks demonstrate the efficacy of our approach. On average, GRAVITY improves LLM-judge accuracy by 7.5--10.1%. Gains are inversely correlated with baseline strength: the weakest host improves by 12.2% while the strongest still gains 3.8--5.7%. These findings establish structured context anchoring as a broadly effective, architecture-agnostic augmentation paradigm for long-horizon conversational memory.

Ran Zhang, Kun Ouyang, Tiancheng Ma et al.

Optimizing numerical systems and mechanism design is crucial for enhancing player experience in Massively Multiplayer Online (MMO) games. Traditional optimization approaches rely on large-scale online experiments or parameter tuning over predefined statistical models, which are costly, time-consuming, and may disrupt player experience. Although simplified offline simulation systems are often adopted as alternatives, their limited fidelity prevents agents from accurately mimicking real player reasoning and reactions to interventions. To address these limitations, we propose a generative agent-based MMO simulation system empowered by Large Language Models (LLMs). By applying Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on large-scale real player behavioral data, we adapt LLMs from general priors to game-specific domains, enabling realistic and interpretable player decision-making. In parallel, a data-driven environment model trained on real gameplay logs reconstructs dynamic in-game systems. Experiments demonstrate strong consistency with real-world player behaviors and plausible causal responses under interventions, providing a reliable, interpretable, and cost-efficient framework for data-driven numerical design optimization.

Kun Ouyang, Haoyu Wang, Dong Fang

Event log data, recording fine-grained user actions and system events, represent one of the most valuable assets for modern digital services. However, the complexity and heterogeneity of industrial event logs--characterized by large scale, high dimensionality, diverse data types, and intricate temporal or relational structures--make feature engineering extremely challenging. Existing automatic feature engineering approaches, such as AutoML or genetic methods, often suffer from limited explainability, rigid predefined operations, and poor adaptability to complicated heterogeneous data. In this paper, we propose FELA (Feature Engineering LLM Agents), a multi-agent evolutionary system that autonomously extracts meaningful and high-performing features from complex industrial event log data. FELA integrates the reasoning and coding capabilities of large language models (LLMs) with an insight-guided self-evolution paradigm. Specifically, FELA employs specialized agents--Idea Agents, Code Agents, and Critic Agents--to collaboratively generate, validate, and implement novel feature ideas. An Evaluation Agent summarizes feedback and updates a hierarchical knowledge base and dual-memory system to enable continual improvement. Moreover, FELA introduces an agentic evolution algorithm, combining reinforcement learning and genetic algorithm principles to balance exploration and exploitation across the idea space. Extensive experiments on real industrial datasets demonstrate that FELA can generate explainable, domain-relevant features that significantly improve model performance while reducing manual effort. Our results highlight the potential of LLM-based multi-agent systems as a general framework for automated, interpretable, and adaptive feature engineering in complex real-world environments.

Jingyu Xiao, Zhiyao Xu, Qingsong Zou et al.

Smart homes, powered by the Internet of Things, offer great convenience but also pose security concerns due to abnormal behaviors, such as improper operations of users and potential attacks from malicious attackers. Several behavior modeling methods have been proposed to identify abnormal behaviors and mitigate potential risks. However, their performance often falls short because they do not effectively learn less frequent behaviors, consider temporal context, or account for the impact of noise in human behaviors. In this paper, we propose SmartGuard, an autoencoder-based unsupervised user behavior anomaly detection framework. First, we design a Loss-guided Dynamic Mask Strategy (LDMS) to encourage the model to learn less frequent behaviors, which are often overlooked during learning. Second, we propose a Three-level Time-aware Position Embedding (TTPE) to incorporate temporal information into positional embedding to detect temporal context anomaly. Third, we propose a Noise-aware Weighted Reconstruction Loss (NWRL) that assigns different weights for routine behaviors and noise behaviors to mitigate the interference of noise behaviors during inference. Comprehensive experiments on three datasets with ten types of anomaly behaviors demonstrates that SmartGuard consistently outperforms state-of-the-art baselines and also offers highly interpretable results.