Characterizing, Evaluating, and Optimizing Complex Reasoning

Large Reasoning Models (LRMs) increasingly rely on reasoning traces with complex internal structures. However, existing work lacks a unified answer to three fundamental questions: (1) what defines high-quality reasoning, (2) how to reliably evaluate long, implicitly structured reasoning traces, and (3) how to use such evaluation signals for reasoning optimization. To address these challenges, we provide a unified perspective. (1) We introduce the ME$^2$ principle to characterize reasoning quality along macro- and micro-level concerning efficiency and effectiveness. (2) Built on this principle, we model reasoning traces as directed acyclic graphs (DAGs) and develop a DAG-based pairwise evaluation method, capturing complex reasoning structures. (3) Based on this method, we construct the TRM-Preference dataset and train a Thinking Reward Model (TRM) to evaluate reasoning quality at scale. Experiments show that thinking rewards serve as an effective optimization signal. At test time, selecting better reasoning leads to better outcomes (up to 19.3% gain), and during RL training, thinking rewards enhance reasoning and performance (up to 3.9% gain) across diverse tasks.

New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR

Whether Reinforcement Learning with Verifiable Rewards (RLVR) endows Large Language Models (LLMs) with new capabilities or merely elicits latent traces remains a central debate. In this work, we align with the former view, proposing a probabilistic framework where capability is defined by instance-level solvability. We hypothesize that the emergence of complex reasoning can be driven by sharpening atomic step probabilities, which enables models to overcome the exponential decay of success rates inherent in multi-step reasoning chains. Utilizing the Algebrarium framework, we train models exclusively on single-step operations and evaluate their performance on unseen multi-step tasks. Our empirical results confirm that: (1) RLVR incentivizes the exploration of previously inaccessible solution paths by amplifying the model's existing skills; (2) composite performance is strictly governed by the joint probability of atomic steps, evidenced by high Pearson correlation coefficients ($ρ\in [0.69, 0.96]$); and (3) RLVR, acting as a global optimizer, can cause specific skills to be sacrificed to maximize aggregate reward. Our work offers a novel explanation for emergent abilities in RLVR, suggesting that the iterative optimization of solvable problems enables models to develop the capabilities to tackle previously unsolvable scenarios.

DAWN: Dependency-Aware Fast Inference for Diffusion LLMs

Diffusion large language models (dLLMs) have shown advantages in text generation, particularly due to their inherent ability for parallel decoding. However, constrained by the quality--speed trade-off, existing inference solutions adopt conservative parallel strategies, leaving substantial efficiency potential underexplored. A core challenge is that parallel decoding assumes each position can be filled independently, but tokens are often semantically coupled. Thus, the correct choice at one position constrains valid choices at others. Without modeling these inter-token dependencies, parallel strategies produce deteriorated outputs. Motivated by this insight, we propose DAWN, a training-free, dependency-aware decoding method for fast dLLM inference. DAWN extracts token dependencies and leverages two key motivations: (1) positions dependent on unmasked certain positions become more reliable, (2) simultaneously unmasking strongly coupled uncertain positions induces errors. Given those findings, DAWN leverages a dependency graph to select more reliable unmasking positions at each iteration, achieving high parallelism with negligible loss in generation quality. Extensive experiments across multiple models and datasets demonstrate that DAWN speedups the inference by 1.80-8.06x over baselines while preserving the generation quality. Code is released at https://github.com/lizhuo-luo/DAWN.

Tail-Aware Post-Training Quantization for 3D Geometry Models

The burgeoning complexity and scale of 3D geometry models pose significant challenges for deployment on resource-constrained platforms. While Post-Training Quantization (PTQ) enables efficient inference without retraining, conventional methods, primarily optimized for 2D Vision Transformers, fail to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead. To address these challenges, we propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline specifically engineered for 3D geometric learning. Our contribution is threefold: (1) To overcome the data-scale bottleneck in 3D datasets, we develop a progressive coarse-to-fine calibration construction strategy that constructs a highly compact subset to achieve both statistical purity and geometric representativeness. (2) We reformulate the quantization interval search as an optimization problem and introduce a ternary-search-based solver, reducing the computational complexity from $\mathcal{O}(N)$ to $\mathcal{O}(\log N)$ for accelerated deployment. (3) To mitigate quantization error accumulation, we propose TRE-Guided Module-wise Compensation, which utilizes a Tail Relative Error (TRE) metric to adaptively identify and rectify distortions in modules sensitive to long-tailed activation outliers. Extensive experiments on the VGGT and Pi3 benchmarks demonstrate that TAPTQ consistently outperforms state-of-the-art PTQ methods in accuracy while significantly reducing calibration time. The code will be released soon.

Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent Training

Large-scale, high-quality interaction trajectories are essential for advancing mobile Graphical User Interface (GUI) agents. While existing methods typically rely on labor-intensive human demonstrations or automated model exploration to generate GUI trajectories, they lack fine-grained control over task difficulty. This fundamentally restricts learning effectiveness due to the mismatch between the training difficulty and the agent's capabilities. Inspired by how humans acquire skills through progressively challenging tasks, we propose MobileGen, a novel data generation framework that adaptively aligns training difficulty with the GUI agent's capability frontier. Specifically, MobileGen explicitly decouples task difficulty into structural (e.g., trajectory length) and semantic (e.g., task goal) dimensions. It then iteratively evaluates the agent on a curated prior dataset to construct a systematic profile of its capability frontier across these two dimensions. With this profile, the probability distribution of task difficulty is adaptively computed, from which the target difficulty for the next round of training can be sampled. Guided by the sampled difficulty, a multi-agent controllable generator is finally used to synthesize high-quality interaction trajectories along with corresponding task instructions. Extensive experiments show that MobileGen consistently outperforms existing data generation methods by improving the average performance of GUI agents by 1.57 times across multiple challenging benchmarks. This highlights the importance of capability-aligned data generation for effective mobile GUI agent training.

Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning

Diffusion Policy has dominated action generation due to its strong capabilities for modeling multi-modal action distributions, but its multi-step denoising processes make it impractical for real-time visuomotor control. Existing caching-based acceleration methods typically rely on $\textit{static}$ schedules that fail to adapt to the $\textit{dynamics}$ of robot-environment interactions, thereby leading to suboptimal performance. In this paper, we propose $\underline{\textbf{S}}$parse $\underline{\textbf{A}}$ction$\underline{\textbf{G}}$en ($\textbf{SAG}$) for extremely sparse action generation. To accommodate the iterative interactions, SAG customizes a rollout-adaptive prune-then-reuse mechanism that first identifies prunable computations globally and then reuses cached activations to substitute them during action diffusion. To capture the rollout dynamics, SAG parameterizes an observation-conditioned diffusion pruner for environment-aware adaptation and instantiates it with a highly parameter- and inference-efficient design for real-time prediction. Furthermore, SAG introduces a one-for-all reusing strategy that reuses activations across both timesteps and blocks in a zig-zag manner, minimizing the global redundancy. Extensive experiments on multiple robotic benchmarks demonstrate that SAG achieves up to 4$\times$ generation speedup without sacrificing performance. Project Page: https://sparse-actiongen.github.io/.

Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation

Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks. A fundamental limitation remains \textit{the curse of diversity collapse}, where the objective formulation and optimization landscape inherently collapse the policy to a Dirac delta distribution. To address this challenge, we propose \textbf{DRIFT} (\textbf{D}ive\textbf{R}sity-\textbf{I}ncentivized Reinforcement \textbf{F}ine-\textbf{T}uning for Versatile Image Generation), an innovative framework that systematically incentivizes output diversity throughout the on-policy fine-tuning process, reconciling strong task alignment with high generation diversity to enhance versatility essential for applications that demand diverse candidate generations. We approach the problem across three representative perspectives: i) \textbf{sampling} a reward-concentrated subset that filters out reward outliers to prevent premature collapse; ii) \textbf{prompting} with stochastic variations to expand the conditioning space, and iii) \textbf{optimization} of the intra-group diversity with a potential-based reward shaping mechanism. Experimental results show that DRIFT achieves superior Pareto dominance regarding task alignment and generation diversity, yielding a $ 9.08\%\!\sim\! 43.46\%$ increase in diversity at equivalent alignment levels and a $ 59.65\% \!\sim\! 65.86\%$ increase in alignment at equivalent levels of diversity.

Continual Learning of Achieving Forgetting-free and Positive Knowledge Transfer

Existing research on continual learning (CL) of a sequence of tasks focuses mainly on dealing with catastrophic forgetting (CF) to balance the learning plasticity of new tasks and the memory stability of old tasks. However, an ideal CL agent should not only be able to overcome CF, but also encourage positive forward and backward knowledge transfer (KT), i.e., using the learned knowledge from previous tasks for the new task learning (namely FKT), and improving the previous tasks' performance with the knowledge of the new task (namely BKT). To this end, this paper first models CL as an optimization problem in which each sequential learning task aims to achieve its optimal performance under the constraint that both FKT and BKT should be positive. It then proposes a novel Enhanced Task Continual Learning (ETCL) method, which achieves forgetting-free and positive KT. Furthermore, the bounds that can lead to negative FKT and BKT are estimated theoretically. Based on the bounds, a new strategy for online task similarity detection is also proposed to facilitate positive KT. To overcome CF, ETCL learns a set of task-specific binary masks to isolate a sparse sub-network for each task while preserving the performance of a dense network for the task. At the beginning of a new task learning, ETCL tries to align the new task's gradient with that of the sub-network of the previous most similar task to ensure positive FKT. By using a new bi-objective optimization strategy and an orthogonal gradient projection method, ETCL updates only the weights of previous similar tasks at the classification layer to achieve positive BKT. Extensive evaluations demonstrate that the proposed ETCL markedly outperforms strong baselines on dissimilar, similar, and mixed task sequences.

DeepHalo: A Neural Choice Model with Controllable Context Effects

Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows that preferences are often influenced by the composition of the choice set itself -- a phenomenon known as the context effect or Halo effect. These effects can manifest as pairwise (first-order) or even higher-order interactions among the available alternatives. Recent models that attempt to capture such effects either focus on the featureless setting or, in the feature-based setting, rely on restrictive interaction structures or entangle interactions across all orders, which limits interpretability. In this work, we propose DeepHalo, a neural modeling framework that incorporates features while enabling explicit control over interaction order and principled interpretation of context effects. Our model enables systematic identification of interaction effects by order and serves as a universal approximator of context-dependent choice functions when specialized to a featureless setting. Experiments on synthetic and real-world datasets demonstrate strong predictive performance while providing greater transparency into the drivers of choice.

Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation

Generative recommendation with large language models (LLMs) reframes prediction as sequence generation, yet existing LLM-based recommenders remain limited in leveraging geographic signals that are crucial in mobility and local-services scenarios. Here, we present Reasoning Over Space (ROS), a framework that utilizes geography as a vital decision variable within the reasoning process. ROS introduces a Hierarchical Spatial Semantic ID (SID) that discretizes coarse-to-fine locality and POI semantics into compositional tokens, and endows LLM with a three-stage Mobility Chain-of-Thought (CoT) paradigm that models user personality, constructs an intent-aligned candidate space, and performs locality informed pruning. We further align the model with real world geography via spatial-guided Reinforcement Learning (RL). Experiments on three widely used location-based social network (LBSN) datasets show that ROS achieves over 10% relative gains in hit rate over strongest LLM-based baselines and improves cross-city transfer, despite using a smaller backbone model.