Robust Regularized Policy Iteration under Transition Uncertainty

Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs where value estimates and learned dynamics are unreliable. To address policy-induced extrapolation and transition uncertainty in a unified framework, we formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set and optimizing the policy against the worst-case dynamics. We propose Robust Regularized Policy Iteration (RRPI), which replaces the intractable max-min bilevel objective with a tractable KL-regularized surrogate and derives an efficient policy iteration procedure based on a robust regularized Bellman operator. We provide theoretical guarantees by showing that the proposed operator is a $γ$-contraction and that iteratively updating the surrogate yields monotonic improvement of the original robust objective with convergence. Experiments on D4RL benchmarks demonstrate that RRPI achieves strong average performance, outperforming recent baselines including percentile-based methods such as PMDB on the majority of environments while remaining competitive on the rest. Moreover, RRPI exhibits robust behavior. The learned $Q$-values decrease in regions with higher epistemic uncertainty, suggesting that the resulting policy avoids unreliable out-of-distribution actions under transition uncertainty.

Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement

Scaling test-time computation enhances LLM reasoning ability but faces a uniform computation paradox. Allocating identical resources leads to over-correction on simple tasks and insufficient refinement on complex ones. To address this, we propose CoFiCot, a coarse-to-fine adaptive framework that dynamically tailors inference strategies to problem difficulty. Specifically, we implement a multi-metric classifier that triages queries by synthesizing semantic entropy, consensus reliability, and predicted reasoning depth . This enables a differentiated refinement stage that applies efficient aggregation for simple queries while routing complex ones to a context-aware correction loop . We formalize correction as a stateful sequential propagation process , where each repair is strictly conditioned on the verified history of prior rectifications. By integrating Process Reward Models (PRMs) within this state-dependent trajectory, CoFiCot effectively bridges the gap between granular error localization and global logical coherence, preventing the context fragmentation typical of stateless refinement methods.

PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning

While Multimodal Large Language Models (MLLMs) demonstrate proficiency in 2D scenes, extending their perceptual intelligence to 3D point cloud understanding remains a significant challenge. Current approaches focus primarily on aligning 3D features with pre-trained models. However, they typically treat geometric reasoning as an implicit mapping process. These methods bypass intermediate logical steps and consequently suffer from geometric hallucinations. They confidently generate plausible responses that fail to ground in precise structural details. To bridge this gap, we present PointCoT, a novel framework that empowers MLLMs with explicit Chain-of-Thought (CoT) reasoning for 3D data. We advocate for a \textit{Look, Think, then Answer} paradigm. In this approach, the model is supervised to generate geometry-grounded rationales before predicting final answers. To facilitate this, we construct Point-Reason-Instruct, a large-scale benchmark comprising $\sim$86k instruction-tuning samples with hierarchical CoT annotations. By leveraging a dual-stream multi-modal architecture, our method synergizes semantic appearance with geometric truth. Extensive experiments demonstrate that PointCoT achieves state-of-the-art performance on complex reasoning tasks.

Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, yet traditional single-round retrieval struggles with complex multi-step reasoning. Agentic RAG addresses this by enabling LLMs to dynamically decide when and what to retrieve, but current RL-based training methods suffer from sparse outcome rewards that discard intermediate signals and low sample efficiency where failed samples contribute nothing. We propose Search-P1, a framework that introduces path-centric reward shaping for agentic RAG training, comprising two key components: (1) Path-Centric Reward, which evaluates the structural quality of reasoning trajectories through order-agnostic step coverage and soft scoring that extracts learning signals even from failed samples, and (2) Dual-Track Path Scoring with offline-generated reference planners that assesses paths from both self-consistency and reference-alignment perspectives. Experiments on multiple QA benchmarks demonstrate that Search-P1 achieves significant improvements over Search-R1 and other strong baselines, with an average accuracy gain of 7.7 points.

Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception

Point cloud video understanding is critical for robotics as it accurately encodes motion and scene interaction. We recognize that 4D datasets are far scarcer than 3D ones, which hampers the scalability of self-supervised 4D models. A promising alternative is to transfer 3D pre-trained models to 4D perception tasks. However, rigorous empirical analysis reveals two critical limitations that impede transfer capability: overfitting and the modality gap. To overcome these challenges, we develop a novel "Align then Adapt" (PointATA) paradigm that decomposes parameter-efficient transfer learning into two sequential stages. Optimal-transport theory is employed to quantify the distributional discrepancy between 3D and 4D datasets, enabling our proposed point align embedder to be trained in Stage 1 to alleviate the underlying modality gap. To mitigate overfitting, an efficient point-video adapter and a spatial-context encoder are integrated into the frozen 3D backbone to enhance temporal modeling capacity in Stage 2. Notably, with the above engineering-oriented designs, PointATA enables a pre-trained 3D model without temporal knowledge to reason about dynamic video content at a smaller parameter cost compared to previous work. Extensive experiments show that PointATA can match or even outperform strong full fine-tuning models, whilst enjoying the advantage of parameter efficiency, e.g. 97.21 \% accuracy on 3D action recognition, $+8.7 \%$ on 4 D action segmentation, and 84.06\% on 4D semantic segmentation.

Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA

Industrial advertising question answering (QA) is a high-stakes task in which hallucinated content, particularly fabricated URLs, can lead to financial loss, compliance violations, and legal risk. Although Retrieval-Augmented Generation (RAG) is widely adopted, deploying it in production remains challenging because industrial knowledge is inherently relational, frequently updated, and insufficiently aligned with generation objectives. We propose a reinforced co-adaptation framework that jointly optimizes retrieval and generation through two components: (1) Graph-aware Retrieval (GraphRAG), which models entity-relation structure over a high-citation knowledge subgraph for multi-hop, domain-specific evidence selection; and (2) evidence-constrained reinforcement learning via Group Relative Policy Optimization (GRPO) with multi-dimensional rewards covering faithfulness, style compliance, safety, and URL validity. Experiments on an internal advertising QA dataset show consistent gains across expert-judged dimensions including accuracy, completeness, and safety, while reducing the hallucination rate by 72\%. A two-week online A/B test demonstrates a 28.6\% increase in like rate, a 46.2\% decrease in dislike rate, and a 92.7\% reduction in URL hallucination. The system has been running in production for over half a year and has served millions of QA interactions.

AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents

While Large Language Model (LLM) agents have achieved remarkable progress in complex reasoning tasks, evaluating their performance in real-world environments has become a critical problem. Current benchmarks, however, are largely restricted to idealized simulations, failing to address the practical demands of specialized domains like advertising and marketing analytics. In these fields, tasks are inherently more complex, often requiring multi-round interaction with professional marketing tools. To address this gap, we propose AD-Bench, a benchmark designed based on real-world business requirements of advertising and marketing platforms. AD-Bench is constructed from real user marketing analysis requests, with domain experts providing verifiable reference answers and corresponding reference tool-call trajectories. The benchmark categorizes requests into three difficulty levels (L1-L3) to evaluate agents' capabilities under multi-round, multi-tool collaboration. Experiments show that on AD-Bench, Gemini-3-Pro achieves Pass@1 = 68.0% and Pass@3 = 83.0%, but performance drops significantly on L3 to Pass@1 = 49.4% and Pass@3 = 62.1%, with a trajectory coverage of 70.1%, indicating that even state-of-the-art models still exhibit substantial capability gaps in complex advertising and marketing analysis scenarios. AD-Bench provides a realistic benchmark for evaluating and improving advertising marketing agents, the leaderboard and code can be found at https://github.com/Emanual20/adbench-leaderboard.

Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring

While Chain-of-Thought (CoT) reasoning significantly enhances the performance of Multimodal Large Language Models (MLLMs), its autoregressive nature incurs prohibitive latency constraints. Current efforts to mitigate this via token compression often fail by blindly applying text-centric metrics to multimodal contexts. We identify a critical failure mode termed Visual Amnesia, where linguistically redundant tokens are erroneously pruned, leading to hallucinations. To address this, we introduce V-Skip that reformulates token pruning as a Visual-Anchored Information Bottleneck (VA-IB) optimization problem. V-Skip employs a dual-path gating mechanism that weighs token importance through both linguistic surprisal and cross-modal attention flow, effectively rescuing visually salient anchors. Extensive experiments on Qwen2-VL and Llama-3.2 families demonstrate that V-Skip achieves a $2.9\times$ speedup with negligible accuracy loss. Specifically, it preserves fine-grained visual details, outperforming other baselines over 30\% on the DocVQA.

PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models

Self-supervised representation learning has shown significant improvement in Natural Language Processing and 2D Computer Vision. However, existing methods face difficulties in representing 3D data because of its unordered and uneven density. Through an in-depth analysis of mainstream contrastive and generative approaches, we find that contrastive models tend to suffer from overfitting, while 3D Mask Autoencoders struggle to handle unordered point clouds. This motivates us to learn 3D representations by sharing the merits of diffusion and contrast models, which is non-trivial due to the pattern difference between the two paradigms. In this paper, we propose \textit{PointDico}, a novel model that seamlessly integrates these methods. \textit{PointDico} learns from both denoising generative modeling and cross-modal contrastive learning through knowledge distillation, where the diffusion model serves as a guide for the contrastive model. We introduce a hierarchical pyramid conditional generator for multi-scale geometric feature extraction and employ a dual-channel design to effectively integrate local and global contextual information. \textit{PointDico} achieves a new state-of-the-art in 3D representation learning, \textit{e.g.}, \textbf{94.32\%} accuracy on ScanObjectNN, \textbf{86.5\%} Inst. mIoU on ShapeNetPart.

AFBS:Buffer Gradient Selection in Semi-asynchronous Federated Learning

Asynchronous federated learning (AFL) accelerates training by eliminating the need to wait for stragglers, but its asynchronous nature introduces gradient staleness, where outdated gradients degrade performance. Existing solutions address this issue with gradient buffers, forming a semi-asynchronous framework. However, this approach struggles when buffers accumulate numerous stale gradients, as blindly aggregating all gradients can harm training. To address this, we propose AFBS (Asynchronous FL Buffer Selection), the first algorithm to perform gradient selection within buffers while ensuring privacy protection. Specifically, the client sends the random projection encrypted label distribution matrix before training, and the server performs client clustering based on it. During training, server scores and selects gradients within each cluster based on their informational value, discarding low-value gradients to enhance semi-asynchronous federated learning. Extensive experiments in highly heterogeneous system and data environments demonstrate AFBS's superior performance compared to state-of-the-art methods. Notably, on the most challenging task, CIFAR-100, AFBS improves accuracy by up to 4.8% over the previous best algorithm and reduces the time to reach target accuracy by 75%.