DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training

Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM post-training. Recent distributional RL methods improve robustness by modeling values with multiple quantile points, but they still learn each quantile independently as a scalar. This results in rough-grained value representations that lack fine-grained conditioning on state information, struggling under complex and OOD conditions. We propose DFPO (Distributional Value Flow Policy Optimization with Conditional Risk and Consistency Control), a robust distributional RL framework that models values as continuous flows across time steps. By scaling value modeling through learning of a value flow field instead of isolated quantile predictions, DFPO captures richer state information for more accurate advantage estimation. To stabilize training under noisy feedback, DFPO further integrates conditional risk control and consistency constraints along value flow trajectories. Experiments on dialogue, math reasoning, and scientific tasks show that DFPO outperforms PPO, FlowRL, and other robust baselines under noisy supervision, achieving improved training stability and generalization.

Human-AI Collaboration Mechanism Study on AIGC Assisted Image Production for Special Coverage

Artificial Intelligence Generated Content (AIGC) assisting image production triggers controversy in journalism while attracting attention from media agencies. Key issues involve misinformation, authenticity, semantic fidelity, and interpretability. Most AIGC tools are opaque "black boxes," hindering the dual demands of content accuracy and semantic alignment and creating ethical, sociotechnical, and trust dilemmas. This paper explores pathways for controllable image production in journalism's special coverage and conducts two experiments with projects from China's media agency: (1) Experiment 1 tests cross-platform adaptability via standardized prompts across three scenes, revealing disparities in semantic alignment, cultural specificity, and visual realism driven by training-corpus bias and platform-level filtering. (2) Experiment 2 builds a human-in-the-loop modular pipeline combining high-precision segmentation (SAM, GroundingDINO), semantic alignment (BrushNet), and style regulating (Style-LoRA, Prompt-to-Prompt), ensuring editorial fidelity through CLIP-based semantic scoring, NSFW/OCR/YOLO filtering, and verifiable content credentials. Traceable deployment preserves semantic representation. Consequently, we propose a human-AI collaboration mechanism for AIGC assisted image production in special coverage and recommend evaluating Character Identity Stability (CIS), Cultural Expression Accuracy (CEA), and User-Public Appropriateness (U-PA).

AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress

Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation, which require making a sequence of intelligent decisions based on environmental feedback. Previous work for LLM agents typically relies on elaborate prompt engineering or fine-tuning with expert trajectories to improve performance. In this work, we take a different perspective: we explore constructing process reward models (PRMs) to evaluate each decision and guide the agent's decision-making process. Unlike LLM reasoning, where each step is scored based on correctness, actions in agent tasks do not have a clear-cut correctness. Instead, they should be evaluated based on their proximity to the goal and the progress they have made. Building on this insight, we propose a re-defined PRM for agent tasks, named AgentPRM, to capture both the interdependence between sequential decisions and their contribution to the final goal. This enables better progress tracking and exploration-exploitation balance. To scalably obtain labeled data for training AgentPRM, we employ a Temporal Difference-based (TD-based) estimation method combined with Generalized Advantage Estimation (GAE), which proves more sample-efficient than prior methods. Extensive experiments across different agentic tasks show that AgentPRM is over $8\times$ more compute-efficient than baselines, and it demonstrates robust improvement when scaling up test-time compute. Moreover, we perform detailed analyses to show how our method works and offer more insights, e.g., applying AgentPRM to the reinforcement learning of LLM agents.

Data Proportion Detection for Optimized Data Management for Large Language Models

Large language models (LLMs) have demonstrated exceptional performance across a wide range of tasks and domains, with data preparation playing a critical role in achieving these results. Pre-training data typically combines information from multiple domains. To maximize performance when integrating data from various domains, determining the optimal data proportion is essential. However, state-of-the-art (SOTA) LLMs rarely disclose details about their pre-training data, making it difficult for researchers to identify ideal data proportions. In this paper, we introduce a new topic, \textit{data proportion detection}, which enables the automatic estimation of pre-training data proportions by analyzing the generated outputs of LLMs. We provide rigorous theoretical proofs, practical algorithms, and preliminary experimental results for data proportion detection. Based on these findings, we offer valuable insights into the challenges and future directions for effective data proportion detection and data management.

Channel-Spatial-Based Few-Shot Bird Sound Event Detection

In this paper, we propose a model for bird sound event detection that focuses on a small number of training samples within the everyday long-tail distribution. As a result, we investigate bird sound detection using the few-shot learning paradigm. By integrating channel and spatial attention mechanisms, improved feature representations can be learned from few-shot training datasets. We develop a Metric Channel-Spatial Network model by incorporating a Channel Spatial Squeeze-Excitation block into the prototype network, combining it with these attention mechanisms. We evaluate the Metric Channel Spatial Network model on the DCASE 2022 Take5 dataset benchmark, achieving an F-measure of 66.84% and a PSDS of 58.98%. Our experiment demonstrates that the combination of channel and spatial attention mechanisms effectively enhances the performance of bird sound classification and detection.