MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux

Graphical user interface (GUI) agents are rapidly progressing toward autonomous interaction and reliable task execution across diverse applications. However, two central challenges remain unresolved: automating the evaluation of agent trajectories and generating high-quality training data at scale to enable continual improvement. Existing approaches often depend on manual annotation or static rule-based verification, which restricts scalability and limits adaptability in dynamic environments. We present MagicGUI-RMS, a multi-agent reward model system that delivers adaptive trajectory evaluation, corrective feedback, and self-evolving learning capabilities. MagicGUI-RMS integrates a Domain-Specific Reward Model (DS-RM) with a General-Purpose Reward Model (GP-RM), enabling fine-grained action assessment and robust generalization across heterogeneous GUI tasks. To support reward learning at scale, we design a structured data construction pipeline that automatically produces balanced and diverse reward datasets, effectively reducing annotation costs while maintaining sample fidelity. During execution, the reward model system identifies erroneous actions, proposes refined alternatives, and continuously enhances agent behavior through an automated data-reflux mechanism. Extensive experiments demonstrate that MagicGUI-RMS yields substantial gains in task accuracy, behavioral robustness. These results establish MagicGUI-RMS as a principled and effective foundation for building self-improving GUI agents driven by reward-based adaptation.

NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems

Accurately assessing model confidence is essential for deploying large language models (LLMs) in mission-critical factual domains. While retrieval-augmented generation (RAG) is widely adopted to improve grounding, confidence calibration in RAG settings remains poorly understood. We conduct a systematic study across four benchmarks, revealing that LLMs exhibit poor calibration performance due to noisy retrieved contexts. Specifically, contradictory or irrelevant evidence tends to inflate the model's false certainty, leading to severe overconfidence. To address this, we propose NAACL Rules (Noise-AwAre Confidence CaLibration Rules) to provide a principled foundation for resolving overconfidence under noise. We further design NAACL, a noise-aware calibration framework that synthesizes supervision from about 2K HotpotQA examples guided by these rules. By performing supervised fine-tuning (SFT) with this data, NAACL equips models with intrinsic noise awareness without relying on stronger teacher models. Empirical results show that NAACL yields substantial gains, improving ECE scores by 10.9% in-domain and 8.0% out-of-domain. By bridging the gap between retrieval noise and verbal calibration, NAACL paves the way for both accurate and epistemically reliable LLMs.

Reward Modeling from Natural Language Human Feedback

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with critiques and preference labels, and RLVR then relies on the correctness of the preference labels as the training reward. However, in this paper, we demonstrate that such binary classification tasks make GRMs susceptible to guessing correct outcomes without sound critiques. Consequently, these spurious successes introduce substantial noise into the reward signal, thereby impairing the effectiveness of reinforcement learning. To address this issue, we propose Reward Modeling from Natural Language Human Feedback (RM-NLHF), which leverages natural language feedback to obtain process reward signals, thereby mitigating the problem of limited solution space inherent in binary tasks. Specifically, we compute the similarity between GRM-generated and human critiques as the training reward, which provides more accurate reward signals than outcome-only supervision. Additionally, considering that human critiques are difficult to scale up, we introduce Meta Reward Model (MetaRM) which learns to predict process reward from datasets with human critiques and then generalizes to data without human critiques. Experiments on multiple benchmarks demonstrate that our method consistently outperforms state-of-the-art GRMs trained with outcome-only reward, confirming the superiority of integrating natural language over binary human feedback as supervision.

Cumulative Path-Level Semantic Reasoning for Inductive Knowledge Graph Completion

Conventional Knowledge Graph Completion (KGC) methods aim to infer missing information in incomplete Knowledge Graphs (KGs) by leveraging existing information, which struggle to perform effectively in scenarios involving emerging entities. Inductive KGC methods can handle the emerging entities and relations in KGs, offering greater dynamic adaptability. While existing inductive KGC methods have achieved some success, they also face challenges, such as susceptibility to noisy structural information during reasoning and difficulty in capturing long-range dependencies in reasoning paths. To address these challenges, this paper proposes the Cumulative Path-Level Semantic Reasoning for inductive knowledge graph completion (CPSR) framework, which simultaneously captures both the structural and semantic information of KGs to enhance the inductive KGC task. Specifically, the proposed CPSR employs a query-dependent masking module to adaptively mask noisy structural information while retaining important information closely related to the targets. Additionally, CPSR introduces a global semantic scoring module that evaluates both the individual contributions and the collective impact of nodes along the reasoning path within KGs. The experimental results demonstrate that CPSR achieves state-of-the-art performance.

Decoupling Constraint from Two Direction in Evolutionary Constrained Multi-objective Optimization

Real-world Constrained Multi-objective Optimization Problems (CMOPs) often contain multiple constraints, and understanding and utilizing the coupling between these constraints is crucial for solving CMOPs. However, existing Constrained Multi-objective Evolutionary Algorithms (CMOEAs) typically ignore these couplings and treat all constraints as a single aggregate, which lacks interpretability regarding the specific geometric roles of constraints. To address this limitation, we first analyze how different constraints interact and show that the final Constrained Pareto Front (CPF) depends not only on the Pareto fronts of individual constraints but also on the boundaries of infeasible regions. This insight implies that CMOPs with different coupling types must be solved from different search directions. Accordingly, we propose a novel algorithm named Decoupling Constraint from Two Directions (DCF2D). This method periodically detects constraint couplings and spawns an auxiliary population for each relevant constraint with an appropriate search direction. Extensive experiments on seven challenging CMOP benchmark suites and on a collection of real-world CMOPs demonstrate that DCF2D outperforms five state-of-the-art CMOEAs, including existing decoupling-based methods.

See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning

Large vision-language models (VLMs) often benefit from intermediate visual cues, either injected via external tools or generated as latent visual tokens during reasoning, but these mechanisms still overlook fine-grained visual evidence (e.g., polylines in charts), generalize poorly across domains, and incur high inference-time cost. In this paper, we propose Bi-directional Perceptual Shaping (BiPS), which transforms question-conditioned masked views into bidirectional where-to-look signals that shape perception during training. BiPS first applies a KL-consistency constraint between the original image and an evidence-preserving view that keeps only question-relevant regions, encouraging coarse but complete coverage of supporting pixels. It then applies a KL-separation constraint between the original and an evidence-ablated view where critical pixels are masked so the image no longer supports the original answer, discouraging text-only shortcuts (i.e., answering from text alone) and enforcing fine-grained visual reliance. Across eight benchmarks, BiPS boosts Qwen2.5-VL-7B by 8.2% on average and shows strong out-of-domain generalization to unseen datasets and image types.

C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling

We present C2LLM - Contrastive Code Large Language Models, a family of code embedding models in both 0.5B and 7B sizes. Building upon Qwen-2.5-Coder backbones, C2LLM adopts a Pooling by Multihead Attention (PMA) module for generating sequence embedding from token embeddings, effectively 1) utilizing the LLM's causal representations acquired during pretraining, while also 2) being able to aggregate information from all tokens in the sequence, breaking the information bottleneck in EOS-based sequence embeddings, and 3) supporting flexible adaptation of embedding dimension, serving as an alternative to MRL. Trained on three million publicly available data, C2LLM models set new records on MTEB-Code among models of similar sizes, with C2LLM-7B ranking 1st on the overall leaderboard.

Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically for native, joint audio-video generation. Leveraging a dual-branch Diffusion Transformer architecture, the model integrates a cross-modal joint module with a specialized multi-stage data pipeline, achieving exceptional audio-visual synchronization and superior generation quality. To ensure practical utility, we implement meticulous post-training optimizations, including Supervised Fine-Tuning (SFT) on high-quality datasets and Reinforcement Learning from Human Feedback (RLHF) with multi-dimensional reward models. Furthermore, we introduce an acceleration framework that boosts inference speed by over 10X. Seedance 1.5 pro distinguishes itself through precise multilingual and dialect lip-syncing, dynamic cinematic camera control, and enhanced narrative coherence, positioning it as a robust engine for professional-grade content creation. Seedance 1.5 pro is now accessible on Volcano Engine at https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?type=GenVideo.

Learning-Assisted Multi-Operator Variable Neighborhood Search for Urban Cable Routing

Urban underground cable construction is essential for enhancing the reliability of city power grids, yet its high construction costs make planning a worthwhile optimization task. In urban environments, road layouts tightly constrain cable routing. This, on the one hand, renders relation-only models (i.e., those without explicit routes) used in prior work overly simplistic, and on the other hand, dramatically enlarges the combinatorial search space, thereby imposing much higher demands on algorithm design. In this study, we formulate urban cable routing as a connectivity-path co-optimization problem and propose a learning-assisted multi-operator variable neighborhood search (L-MVNS) algorithm. The framework first introduces an auxiliary task to generate high-quality feasible initial solutions. A hybrid genetic search (HGS) and A* serve as the connectivity optimizer and the route-planning optimizer, respectively. Building on these, a multi-operator variable neighborhood search (MVNS) iteratively co-optimizes inter-substation connectivity and detailed routes via three complementary destruction operators, a modified A* repair operator, and an adaptive neighborhood-sizing mechanism. A multi-agent deep reinforcement learning module is further embedded to prioritize promising neighborhoods. We also construct a standardized and scalable benchmark suite for evaluation. Across these cases, comprehensive experiments demonstrate effectiveness and stability: relative to representative approaches, MVNS and L-MVNS reduce total construction cost by approximately 30-50%, with L-MVNS delivering additional gains on larger instances and consistently higher stability.

AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning

Multi-prompt learning methods have emerged as an effective approach for facilitating the rapid adaptation of vision-language models to downstream tasks with limited resources. Existing multi-prompt learning methods primarily focus on utilizing various meticulously designed prompts within a single foundation vision-language model to achieve superior performance. However, the overlooked model-prompt matching bias hinders the development of multi-prompt learning, i.e., the same prompt can convey different semantics across distinct vision-language models, such as CLIP-ViT-B/16 and CLIP-ViT-B/32, resulting in inconsistent predictions of identical prompt. To mitigate the impact of this bias on downstream tasks, we explore an ensemble learning approach to sufficiently aggregate the benefits of diverse predictions. Additionally, we further disclose the presence of sample-prompt matching bias, which originates from the prompt-irrelevant semantics encapsulated in the input samples. Thus, directly utilizing all information from the input samples for generating weights of ensemble learning can lead to suboptimal performance. In response, we extract prompt-relevant semantics from input samples by leveraging the guidance of the information theory-based analysis, adaptively calculating debiased ensemble weights. Overall, we propose Adaptive-Debiased Ensemble MultiPrompt Learning, abbreviated as AmPLe, to mitigate the two types of bias simultaneously. Extensive experiments on three representative tasks, i.e., generalization to novel classes, new target datasets, and unseen domain shifts, show that AmPLe can widely outperform existing methods. Theoretical validation from a causal perspective further supports the effectiveness of AmPLe.