OracleAgent: A Multimodal Reasoning Agent for Oracle Bone Script Research

As one of the earliest writing systems, Oracle Bone Script (OBS) preserves the cultural and intellectual heritage of ancient civilizations. However, current OBS research faces two major challenges: (1) the interpretation of OBS involves a complex workflow comprising multiple serial and parallel sub-tasks, and (2) the efficiency of OBS information organization and retrieval remains a critical bottleneck, as scholars often spend substantial effort searching for, compiling, and managing relevant resources. To address these challenges, we present OracleAgent, the first agent system designed for the structured management and retrieval of OBS-related information. OracleAgent seamlessly integrates multiple OBS analysis tools, empowered by large language models (LLMs), and can flexibly orchestrate these components. Additionally, we construct a comprehensive domain-specific multimodal knowledge base for OBS, which is built through a rigorous multi-year process of data collection, cleaning, and expert annotation. The knowledge base comprises over 1.4M single-character rubbing images and 80K interpretation texts. OracleAgent leverages this resource through its multimodal tools to assist experts in retrieval tasks of character, document, interpretation text, and rubbing image. Extensive experiments demonstrate that OracleAgent achieves superior performance across a range of multimodal reasoning and generation tasks, surpassing leading mainstream multimodal large language models (MLLMs) (e.g., GPT-4o). Furthermore, our case study illustrates that OracleAgent can effectively assist domain experts, significantly reducing the time cost of OBS research. These results highlight OracleAgent as a significant step toward the practical deployment of OBS-assisted research and automated interpretation systems.

Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization

To combat the prohibitive communication costs of ``free-for-all" multi-agent systems (MAS), we introduce \textbf{Agent-GSPO}, a framework that directly optimizes for token economy using sequence-level reinforcement learning. Agent-GSPO leverages the stable and memory-efficient Group Sequence Policy Optimization (GSPO) algorithm to train agents on a communication-aware reward that explicitly penalizes verbosity. Across seven reasoning benchmarks, Agent-GSPO not only achieves new state-of-the-art performance but does so with a fraction of the token consumption of existing methods. By fostering emergent strategies like ``strategic silence," our approach provides a practical blueprint for developing scalable and economically viable multi-agent systems.

DynaPose4D: High-Quality 4D Dynamic Content Generation via Pose Alignment Loss

Recent advancements in 2D and 3D generative models have expanded the capabilities of computer vision. However, generating high-quality 4D dynamic content from a single static image remains a significant challenge. Traditional methods have limitations in modeling temporal dependencies and accurately capturing dynamic geometry changes, especially when considering variations in camera perspective. To address this issue, we propose DynaPose4D, an innovative solution that integrates 4D Gaussian Splatting (4DGS) techniques with Category-Agnostic Pose Estimation (CAPE) technology. This framework uses 3D Gaussian Splatting to construct a 3D model from single images, then predicts multi-view pose keypoints based on one-shot support from a chosen view, leveraging supervisory signals to enhance motion consistency. Experimental results show that DynaPose4D achieves excellent coherence, consistency, and fluidity in dynamic motion generation. These findings not only validate the efficacy of the DynaPose4D framework but also indicate its potential applications in the domains of computer vision and animation production.

Guardian: Decoupling Exploration from Safety in Reinforcement Learning

Hybrid offline--online reinforcement learning (O2O RL) promises both sample efficiency and robust exploration, but suffers from instability due to distribution shift between offline and online data. We introduce RLPD-GX, a framework that decouples policy optimization from safety enforcement: a reward-seeking learner explores freely, while a projection-based guardian guarantees rule-consistent execution and safe value backups. This design preserves the exploratory value of online interactions without collapsing to conservative policies. To further stabilize training, we propose dynamic curricula that gradually extend temporal horizons and anneal offline--online data mixing. We prove convergence via a contraction property of the guarded Bellman operator, and empirically show state-of-the-art performance on Atari-100k, achieving a normalized mean score of 3.02 (+45\% over prior hybrid methods) with stronger safety and stability. Beyond Atari, ablations demonstrate consistent gains across safety-critical and long-horizon tasks, underscoring the generality of our design. Extensive and comprehensive results highlight decoupled safety enforcement as a simple yet principled route to robust O2O RL, suggesting a broader paradigm for reconciling exploration and safety in reinforcement learning.

Backward-Friendly Optimization: Training Large Language Models with Approximate Gradients under Memory Constraints

Full fine-tuning of Large Language Models (LLMs) is notoriously memory-intensive, primarily because conventional optimizers such as SGD or Adam assume access to exact gradients derived from cached activations. Existing solutions either alter the model architecture (e.g., reversible networks) or trade memory for computation (e.g., activation checkpointing), but the optimizer itself remains untouched. In this work, we introduce GradLite, a backward-friendly optimizer that relaxes the requirement of exact gradients, enabling efficient training even when intermediate activations are aggressively discarded or approximated. GradLite leverages two key techniques: (i) low-rank Jacobian approximation, which reduces the dimensionality of backpropagated error signals, and (ii) error-feedback correction, which accumulates and compensates approximation errors across iterations to preserve convergence guarantees. We provide a theoretical analysis showing that GradLite maintains unbiased gradient estimates with bounded variance, ensuring convergence rates comparable to Adam. Empirically, GradLite reduces optimizer-state and activation memory consumption by up to 50\% without architectural changes, and achieves on-par or superior downstream performance on reasoning (MMLU, GSM8K), multilingual, and dialogue benchmarks compared to checkpointing and optimizer-centric baselines (LoMo, GaLore).

RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability

Retrieval-Augmented Generation (RAG) faces a core bottleneck with knowledge-sparse and semantically ambiguous long-tail queries, where retrieval noise distorts reasoning and necessitates costly post-processing. To tackle this, we propose RaCoT (Retrieval-aware Contrastive-of-Thought), a novel framework that shifts contrastive thinking to the pre-retrieval stage. By automatically generating a semantically adjacent yet differently answered contrastive question and extracting a $\Delta$-Prompt to capture their key differences, RaCoT guides the model to proactively focus on the ``critical details that determine answer divergence." This approach allows it to suppress semantic interference within a single retrieval pass, overcoming the theoretical bottleneck of single-vector queries that struggle to simultaneously encode signals for what to attend to and what to ignore. On six authoritative benchmarks, including PopQA and TriviaQA-unfiltered, RaCoT outperforms strong baselines like RankRAG and Self-RAG by 0.9-2.4 percentage points. It exhibits superior robustness, with a performance drop of only 8.6\% in adversarial tests, far surpassing the over 15\% degradation in other methods. Furthermore, its low latency (3.12s) and token overhead (11.54) place it on the accuracy-efficiency Pareto frontier, while ablation studies validate the necessity of each component. Ultimately, RaCoT reframes the RAG paradigm from ``post-hoc context cleaning" to ``a priori shaping of discriminative reasoning", offering an efficient and robust path toward reliable AI systems for real-time, resource-constrained deployments.

Top-Down Semantic Refinement for Image Captioning

Large Vision-Language Models (VLMs) face an inherent contradiction in image captioning: their powerful single-step generation capabilities often lead to a myopic decision-making process. This makes it difficult to maintain global narrative coherence while capturing rich details, a limitation that is particularly pronounced in tasks that require multi-step and complex scene description. To overcome this fundamental challenge, we redefine image captioning as a goal-oriented hierarchical refinement planning problem, and further propose a novel framework, named Top-Down Semantic Refinement (TDSR), which models the generation process as a Markov Decision Process (MDP). However, planning within the vast state space of a VLM presents a significant computational hurdle. Our core contribution, therefore, is the design of a highly efficient Monte Carlo Tree Search (MCTS) algorithm tailored for VLMs. By incorporating a visual-guided parallel expansion and a lightweight value network, our TDSR reduces the call frequency to the expensive VLM by an order of magnitude without sacrificing planning quality. Furthermore, an adaptive early stopping mechanism dynamically matches computational overhead to the image's complexity. Extensive experiments on multiple benchmarks, including DetailCaps, COMPOSITIONCAP, and POPE, demonstrate that our TDSR, as a plug-and-play module, can significantly enhance the performance of existing VLMs (e.g., LLaVA-1.5, Qwen2.5-VL) by achieving state-of-the-art or highly competitive results in fine-grained description, compositional generalization, and hallucination suppression.

Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media

Digital social media platforms frequently contribute to cognitive-behavioral fixation, a phenomenon in which users exhibit sustained and repetitive engagement with narrow content domains. While cognitive-behavioral fixation has been extensively studied in psychology, methods for computationally detecting and evaluating such fixation remain underexplored. To address this gap, we propose a novel framework for assessing cognitive-behavioral fixation by analyzing users' multimodal social media engagement patterns. Specifically, we introduce a multimodal topic extraction module and a cognitive-behavioral fixation quantification module that collaboratively enable adaptive, hierarchical, and interpretable assessment of user behavior. Experiments on existing benchmarks and a newly curated multimodal dataset demonstrate the effectiveness of our approach, laying the groundwork for scalable computational analysis of cognitive fixation. All code in this project is publicly available for research purposes at https://github.com/Liskie/cognitive-fixation-evaluation.

EMPOWER: Evolutionary Medical Prompt Optimization With Reinforcement Learning

Prompt engineering significantly influences the reliability and clinical utility of Large Language Models (LLMs) in medical applications. Current optimization approaches inadequately address domain-specific medical knowledge and safety requirements. This paper introduces EMPOWER, a novel evolutionary framework that enhances medical prompt quality through specialized representation learning, multi-dimensional evaluation, and structure-preserving algorithms. Our methodology incorporates: (1) a medical terminology attention mechanism, (2) a comprehensive assessment architecture evaluating clarity, specificity, clinical relevance, and factual accuracy, (3) a component-level evolutionary algorithm preserving clinical reasoning integrity, and (4) a semantic verification module ensuring adherence to medical knowledge. Evaluation across diagnostic, therapeutic, and educational tasks demonstrates significant improvements: 24.7% reduction in factually incorrect content, 19.6% enhancement in domain specificity, and 15.3% higher clinician preference in blinded evaluations. The framework addresses critical challenges in developing clinically appropriate prompts, facilitating more responsible integration of LLMs into healthcare settings.

Multi-Metric Preference Alignment for Generative Speech Restoration

Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven effective in other generative domains like text and image generation, its application to generative speech restoration remains largely under-explored. This work investigates the challenges of applying preference-based post-training to this task, focusing on how to define a robust preference signal and curate high-quality data to avoid reward hacking. To address these challenges, we propose a multi-metric preference alignment strategy. We construct a new dataset, GenSR-Pref, comprising 80K preference pairs, where each chosen sample is unanimously favored by a complementary suite of metrics covering perceptual quality, signal fidelity, content consistency, and timbre preservation. This principled approach ensures a holistic preference signal. Applying Direct Preference Optimization (DPO) with our dataset, we observe consistent and significant performance gains across three diverse generative paradigms: autoregressive models (AR), masked generative models (MGM), and flow-matching models (FM) on various restoration benchmarks, in both objective and subjective evaluations. Ablation studies confirm the superiority of our multi-metric strategy over single-metric approaches in mitigating reward hacking. Furthermore, we demonstrate that our aligned models can serve as powerful ''data annotators'', generating high-quality pseudo-labels to serve as a supervision signal for traditional discriminative models in data-scarce scenarios like singing voice restoration. Demo Page:https://gensr-pref.github.io