LLM Review: Enhancing Creative Writing via Blind Peer Review Feedback

Large Language Models (LLMs) often struggle with creative generation, and multi-agent frameworks that improve reasoning through interaction can paradoxically hinder creativity by inducing content homogenization. We introduce LLM Review, a peer-review-inspired framework implementing Blind Peer Review: agents exchange targeted feedback while revising independently, preserving divergent creative trajectories. To enable rigorous evaluation, we propose SciFi-100, a science fiction writing dataset with a unified framework combining LLM-as-a-judge scoring, human annotation, and rule-based novelty metrics. Experiments demonstrate that LLM Review consistently outperforms multi-agent baselines, and smaller models with our framework can surpass larger single-agent models, suggesting interaction structure may substitute for model scale.

Grading Scale Impact on LLM-as-a-Judge: Human-LLM Alignment Is Highest on 0-5 Grading Scale

Large language models (LLMs) are increasingly used as automated evaluators, yet prior works demonstrate that these LLM judges often lack consistency in scoring when the prompt is altered. However, the effect of the grading scale itself remains underexplored. We study the LLM-as-a-judge problem by comparing two kinds of raters: humans and LLMs. We collect ratings from both groups on three scales and across six benchmarks that include objective, open-ended subjective, and mixed tasks. Using intraclass correlation coefficients (ICC) to measure absolute agreement, we find that LLM judgments are not perfectly consistent across scales on subjective benchmarks, and that the choice of scale substantially shifts human-LLM agreement, even when within-group panel reliability is high. Aggregated over tasks, the grading scale of 0-5 yields the strongest human-LLM alignment. We further demonstrate that pooled reliability can mask benchmark heterogeneity and reveal systematic subgroup differences in alignment across gender groups, strengthening the importance of scale design and sub-level diagnostics as essential components of LLM-as-a-judge protocols.

MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents

Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal, and entity information. This design limits interpretability and alignment between query intent and retrieved evidence, leading to suboptimal reasoning accuracy. In this paper, we propose MAGMA, a multi-graph agentic memory architecture that represents each memory item across orthogonal semantic, temporal, causal, and entity graphs. MAGMA formulates retrieval as policy-guided traversal over these relational views, enabling query-adaptive selection and structured context construction. By decoupling memory representation from retrieval logic, MAGMA provides transparent reasoning paths and fine-grained control over retrieval. Experiments on LoCoMo and LongMemEval demonstrate that MAGMA consistently outperforms state-of-the-art agentic memory systems in long-horizon reasoning tasks.

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.

Robust and Efficient Communication in Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments. This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints, including message perturbations, transmission delays, and limited bandwidth. Furthermore, because the challenges of low-latency reliability, bandwidth-intensive data sharing, and communication-privacy trade-offs are central to practical MARL systems, we focus on three applications involving cooperative autonomous driving, distributed simultaneous localization and mapping, and federated learning. Finally, we identify key open challenges and future research directions, advocating a unified approach that co-designs communication, learning, and robustness to bridge the gap between theoretical MARL models and practical implementations.

GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation

As an intelligent infrastructure connecting users with commercial content, advertising recommendation systems play a central role in information flow and value creation within the digital economy. However, existing multi-stage advertising recommendation systems suffer from objective misalignment and error propagation, making it difficult to achieve global optimality, while unified generative recommendation models still struggle to meet the demands of practical industrial applications. To address these issues, we propose GPR (Generative Pre-trained Recommender), the first one-model framework that redefines advertising recommendation as an end-to-end generative task, replacing the traditional cascading paradigm with a unified generative approach. To realize GPR, we introduce three key innovations spanning unified representation, network architecture, and training strategy. First, we design a unified input schema and tokenization method tailored to advertising scenarios, mapping both ads and organic content into a shared multi-level semantic ID space, thereby enhancing semantic alignment and modeling consistency across heterogeneous data. Second, we develop the Heterogeneous Hierarchical Decoder (HHD), a dual-decoder architecture that decouples user intent modeling from ad generation, achieving a balance between training efficiency and inference flexibility while maintaining strong modeling capacity. Finally, we propose a multi-stage joint training strategy that integrates Multi-Token Prediction (MTP), Value-Aware Fine-Tuning and the Hierarchy Enhanced Policy Optimization (HEPO) algorithm, forming a complete generative recommendation pipeline that unifies interest modeling, value alignment, and policy optimization. GPR has been fully deployed in the Tencent Weixin Channels advertising system, delivering significant improvements in key business metrics including GMV and CTCVR.

Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models

Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization bias, ultimately leading to suboptimal performance on downstream tasks. In this work, we analyze the underlying causes of prompt optimization bias from both the model and data perspectives. In terms of the model, the entropy minimization objective typically focuses on reducing the entropy of model predictions while overlooking their correctness. This can result in overconfident yet incorrect outputs, thereby compromising the quality of prompt optimization. On the data side, prompts affected by optimization bias can introduce misalignment between visual and textual modalities, which further aggravates the prompt optimization bias. To this end, we propose a Doubly Debiased Test-Time Prompt Tuning method. Specifically, we first introduce a dynamic retrieval-augmented modulation module that retrieves high-confidence knowledge from a dynamic knowledge base using the test image feature as a query, and uses the retrieved knowledge to modulate the predictions. Guided by the refined predictions, we further develop a reliability-aware prompt optimization module that incorporates a confidence-based weighted ensemble and cross-modal consistency distillation to impose regularization constraints during prompt tuning. Extensive experiments across 15 benchmark datasets involving both natural distribution shifts and cross-datasets generalization demonstrate that our method outperforms baselines, validating its effectiveness in mitigating prompt optimization bias.

MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classification

Recent advances in histopathology vision-language foundation models (VLFMs) have shown promise in addressing data scarcity for whole slide image (WSI) classification via zero-shot adaptation. However, these methods remain outperformed by conventional multiple instance learning (MIL) approaches trained on large datasets, motivating recent efforts to enhance VLFM-based WSI classification through fewshot learning paradigms. While existing few-shot methods improve diagnostic accuracy with limited annotations, their reliance on conventional classifier designs introduces critical vulnerabilities to data scarcity. To address this problem, we propose a Meta-Optimized Classifier (MOC) comprising two core components: (1) a meta-learner that automatically optimizes a classifier configuration from a mixture of candidate classifiers and (2) a classifier bank housing diverse candidate classifiers to enable a holistic pathological interpretation. Extensive experiments demonstrate that MOC outperforms prior arts in multiple few-shot benchmarks. Notably, on the TCGA-NSCLC benchmark, MOC improves AUC by 10.4% over the state-of-the-art few-shot VLFM-based methods, with gains up to 26.25% under 1-shot conditions, offering a critical advancement for clinical deployments where diagnostic training data is severely limited. Code is available at https://github.com/xmed-lab/MOC.

Targeted Deep Architectures: A TMLE-Based Framework for Robust Causal Inference in Neural Networks

Modern deep neural networks are powerful predictive tools yet often lack valid inference for causal parameters, such as treatment effects or entire survival curves. While frameworks like Double Machine Learning (DML) and Targeted Maximum Likelihood Estimation (TMLE) can debias machine-learning fits, existing neural implementations either rely on "targeted losses" that do not guarantee solving the efficient influence function equation or computationally expensive post-hoc "fluctuations" for multi-parameter settings. We propose Targeted Deep Architectures (TDA), a new framework that embeds TMLE directly into the network's parameter space with no restrictions on the backbone architecture. Specifically, TDA partitions model parameters - freezing all but a small "targeting" subset - and iteratively updates them along a targeting gradient, derived from projecting the influence functions onto the span of the gradients of the loss with respect to weights. This procedure yields plug-in estimates that remove first-order bias and produce asymptotically valid confidence intervals. Crucially, TDA easily extends to multi-dimensional causal estimands (e.g., entire survival curves) by merging separate targeting gradients into a single universal targeting update. Theoretically, TDA inherits classical TMLE properties, including double robustness and semiparametric efficiency. Empirically, on the benchmark IHDP dataset (average treatment effects) and simulated survival data with informative censoring, TDA reduces bias and improves coverage relative to both standard neural-network estimators and prior post-hoc approaches. In doing so, TDA establishes a direct, scalable pathway toward rigorous causal inference within modern deep architectures for complex multi-parameter targets.

RaGNNarok: A Light-Weight Graph Neural Network for Enhancing Radar Point Clouds on Unmanned Ground Vehicles

Low-cost indoor mobile robots have gained popularity with the increasing adoption of automation in homes and commercial spaces. However, existing lidar and camera-based solutions have limitations such as poor performance in visually obscured environments, high computational overhead for data processing, and high costs for lidars. In contrast, mmWave radar sensors offer a cost-effective and lightweight alternative, providing accurate ranging regardless of visibility. However, existing radar-based localization suffers from sparse point cloud generation, noise, and false detections. Thus, in this work, we introduce RaGNNarok, a real-time, lightweight, and generalizable graph neural network (GNN)-based framework to enhance radar point clouds, even in complex and dynamic environments. With an inference time of just 7.3 ms on the low-cost Raspberry Pi 5, RaGNNarok runs efficiently even on such resource-constrained devices, requiring no additional computational resources. We evaluate its performance across key tasks, including localization, SLAM, and autonomous navigation, in three different environments. Our results demonstrate strong reliability and generalizability, making RaGNNarok a robust solution for low-cost indoor mobile robots.