SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning

Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy advantages from multiple rollouts, avoiding the substantial memory overhead of conventional proximal policy optimization (PPO) and achieving strong performance on long-horizon interactive tasks. Despite their success, recent studies revealed three limitations: (1) Lack explicit value generalization and effective temporal credit assignment; (2) Suffer from potential advantage collapse in long-horizon complex tasks; (3) Require a costly trade-off between sampling budget and policy performance. In this work, we propose Single-rollout Autoregressive Policy Optimization (SAPO), a low-memory and compute-efficient framework in which the policy and value functions share a single autoregressive backbone. SAPO exploits the autoregressive structure of LLMs to produce policy and value predictions at distinct causal boundaries with shared parameters, while independently optimizing the PPO objectives and auxiliary on-policy SARSA objectives. To robustly estimate the contribution of each turn, we further introduce a trajectory-level generalized advantage estimator that combines lambda-returns with batch normalization. Experiments across ALFWorld and WebShop with Qwen2.5-1.5B/7B show that SAPO trains stably and outperforms PPO and GRPO by mean +15.1 and +12.1 percentage points, respectively, while eliminating the memory cost of a separate critic model and reducing per-iteration runtime by 33.2% over PPO.

PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs

Group-relative policy optimization has emerged as a key paradigm for training agentic large language models (LLMs) on multi-turn interactive tasks. However, most existing variants fail to distinguish advantages among successful trajectories even when these trajectories differ substantially in their interaction efficiency. For instance, circuitous successes are often assigned the identical outcome reward, causing advantage collapse and severe performance bottlenecks. To this end, we propose Group Planning-aware Policy Optimization (PlanPO), a simple yet effective RL method for learning generalizable planning abilities beyond task-specific high-quality behavior patterns. Specifically, PlanPO introduces coarse-to-fine advantage signals, which capture the relative differences in trajectory-level lengths and turn-level response lengths conditioned on successful trajectories sampled for the same task. Within the group-relative optimization structure, this enables agents to actively learn generalizable and deliberate behaviors spanning interaction planning and textual generation from high-quality rollouts, without degenerating into vanilla length minimization. Experimentally, PlanPO improves over GRPO by 27.2\% on average across the challenging multi-turn benchmarks ALFWorld, WebShop, and SciWorld, outperforming recent powerful baselines while incurring negligible additional training cost.

Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence

Apollo did not reach the Moon merely because its engineers could solve difficult equations. It succeeded by turning a distant ambition into a mission architecture of explicit objectives, simulation, verification, and repeated correction. AI now faces a similar transition: frontier models can solve difficult tasks once the problem, tools, and success criteria are specified, yet consequential real-world challenges rarely arrive in an executable or verifiable form. We introduce Apodex Discovery, a framework for building and evaluating discoverative AI through the heavy-duty solver, a system comprising a foundation model, harness, tools, and control policies that pursues extended, stateful, verifiable investigations. It has three core components. First, a problem-scouting process surveyed 561 industries across 16 sectors, assembled 423 high-value real-world problems, and selected 20 for the initial release. Second, a common environment-task-episode abstraction provides data, tools, constraints, feedback, trajectory recording, and verification of intermediate artifacts and final submissions. Third, HDS6 evaluates Tools, Repair, Alternatives, Coherence, Evidence, and Scope independently of final-task success. In AAV capsid design, Apodex surpassed the published state of the art by 7% across viability, tropism, structure prediction, and generative design. In drug repurposing and reformulation, a task-specific biomedical environment improved the mean normalized prediction score of GPT-5.5 and GPT-5.6-sol by 2.5 and 7.6 points over the same closed-book backbone. Controlled ablations show that the fixed TRACES episode interface enables attribution of performance differences to specific solver components. Apodex Discovery moves AI evaluation beyond predefined benchmarks toward verifiable investigations aimed at genuine discovery.

StreamFlow: Dynamic Memory Flows for Streaming Video Understanding

Streaming video understanding requires multimodal large language models (MLLMs) to preserve relevant evidence from continuously evolving streams under strict causality and bounded memory. Yet existing paradigms remain limited: model-based methods require intrusive backbone updates, while memory-based methods expend substantial visual-encoding computation on temporally redundant content and rely on rigid access to visual history. To address these limitations, we introduce StreamFlow, an efficient visual memory framework that enables dynamic, on-demand access to historical visual information. StreamFlow combines a lightweight, dynamics-aware mid-term memory that filters temporal redundancy before visual encoding with a latent long-term memory that consolidates historical video content into visual latents accessible to subsequent reasoning. During generation, an attention-guided retrieval mechanism injects relevant visual latents when the model's reliance on visual evidence weakens. StreamFlow achieves state-of-the-art streaming video understanding performance, reaching 67.73% overall accuracy on StreamingBench, while also delivering strong performance on offline long-video benchmarks. Relative to the vanilla setting, it improves the visual attention score (VAS) by 59.1% while reducing end-to-end latency and peak memory by 50.4% and 21.1%, respectively, enabling more visually grounded and efficient reasoning.

VeinCast: Physics-Guided Dynamic Field Graphs with Graph-Conditioned Fusion for Global Medium-Range Weather Forecasting

Global medium-range weather forecasting requires modeling structured yet state-dependent interactions among heterogeneous atmospheric fields. Existing data-driven models largely learn these interactions implicitly, whereas equation-level physical constraints may inherit approximation and model-form biases. We present VeinCast, a physics-guided dynamic field graph and graph-conditioned fusion framework that jointly forecasts 69 surface and upper-air fields. Within each local window, its Physics-Guided Dynamic Field Graph combines predefined atmospheric relations with state-dependent Top-K residual edges and adapts Earth-window attention using the resulting graph context. Graph-Conditioned Latent Fusion further employs graph context and source-node centrality to guide field-to-latent aggregation, while bounded feedback preserves field-specific information. On the $1.5^\circ$ ERA5 benchmark, VeinCast demonstrates competitive forecasting performance across all 69 meteorological fields at lead times of up to 14 days, compared with representative global weather forecasting models including FuXi, Pangu-Weather, GraphCast, FengWu, and ARROW. Ablations confirm that the two modules provide complementary gains, demonstrating the effectiveness of relational-level physical guidance for data-driven weather forecasting.

AppDeltaWorld: Transition-Grounded Delta Code World Model for Mobile GUI Agents

Mobile GUI agents can operate apps through pixel perception and touch actions, making them a promising interface for collecting and improving long-horizon mobile interaction policies. However, real trajectories are difficult to obtain for sensitive apps and privacy-critical operations. At the same time, existing simulated environments are costly to scale up, and GUI world models still suffer from unstable generation, limited modality coverage, and inconsistent action-transition logic. To address these limitations, we propose AppDeltaWorld, a transition-grounded delta code world model that predicts the next GUI as a reachable code update rather than as an unconstrained image or text description. AppDeltaWorld retrieves app-specific Level-1 HTML references under an action-transition constraint, generates Level-2 executable HTML conditioned on the current screen, action, predicted next-screen text, and retrieved structure, and inserts generated visual assets into image slots before browser rendering. As a world model, AppDeltaWorld achieves the highest fidelity on CMGUIBench-500 under Code2World evaluation, with clear gains in structural layout and UI element reconstruction over image-only and code-only baselines. As a training environment, AppDeltaWorld supports filtered closed-loop SFT data construction that, when combined with public supervision, enables AppDeltaAgent to achieve state-of-the-art performance on AndroidLens and consistent gains on MobileGym and MobileWorld. Moreover, world-model-based test-time reinforcement learning enables policy adaptation and shows further improvements without additional interaction with real apps.

Where Detectors Fail: Closing the Tail-Domain Gap with Expert-Guided Mutual Distillation

Multimodal fake news detectors often generalize poorly across domains because they learn to trust unreliable evidence: domain-specific shortcuts amplified by imbalanced data and semantically inconsistent text-image pairs that make cross-modal evidence unreliable. We propose Expert-Guided Mutual Distillation (EGMD), which learns what evidence to trust across the prediction pipeline. At the input level, input-level calibration encodes pair-level coherence as a shared gain before fusion. At the representation level, an expert-guided teacher aligns domain statistics and encourages domain-specific patterns to concentrate in specialized experts. At the decision level, prototype-anchored domain-specific students use mutual learning and dual-channel distillation to inherit the teacher's feature geometry and calibrated predictions while discouraging local domain priors. We further construct Weibo_Balanced, a domain-balanced benchmark that isolates the effect of imbalance on generalization. Across four datasets in two languages, EGMD achieves state-of-the-art accuracy while reducing domain bias by up to 57.3%.

PlatformBid: An Auto-Bidding Benchmark from a Unified Advertising Platform's Perspective

Real-time bidding is central to computational advertising, comprising three elements: Supply Side Platform (SSP) selling ad impressions, Demand Side Platform (DSP) bidding for advertisers, and Ad Exchange conducting auctions between them. Traditional auto-bidding algorithms focus solely on the DSP side, maximizing advertiser conversions by adjusting bids against competitors. However, current big ad platforms, such as social media and e-commerce companies, now integrate SSP, DSP, and Ad Exchange functions internally. From such ad platforms' perspective, the goal of the auto-bidding algorithms is not only to maximize the advertisers' conversions, but also the total revenue of the platform. Given the lack of platform-centric evaluation frameworks and the pressing need to advance auto-bidding research, we propose PlatformBid - the first comprehensive benchmark designed from a unified ad platform's perspective. To accurately reflect the real-world auto-bidding scenarios, we define three representative settings: (1) homogeneous competition with identical algorithms across advertisers, (2) heterogeneous competition with diverse algorithmic strategies, and (3) promotional competition where some advertisers surge budgets for boosting sales during promotional events like Black Friday. We systematically evaluate a broad spectrum of existing auto-bidding methods across these settings, encompassing classical control methods, RL-based methods, and recent generative methods. Besides these methods, we further propose a novel auto-bidding method based on flow-matching, termed BidFlow, which leverages the flow-matching method's expressive policy representation to effectively handle dynamic competitive environments. Online experiments on Kuaishou further show a +0.68\% improvement in target cost, providing deployment evidence for the offline-online consistency of PlatformBid.

DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation

Existing autoregressive video distillation methods commonly adopt a Distribution Matching Distillation (DMD)-based multi-stage pipeline. However, they typically decouple the initialization and DMD stages -- which then pursue different target distributions -- and judge the intermediate student mainly by visual scores such as VBench. In this paper, we revisit this design from a distributional perspective. Given the mode-seeking nature of the distribution matching loss, a good initialization should match the mode coverage of the target DMD teacher, rather than merely pursuing high quality. To analyze this, we introduce a distributional evaluation protocol that measures precision and coverage between student and teacher distributions in a shared latent space. It exposes differences hidden by visual scores: some initializations reach high precision but low coverage, leading to suboptimal refinement, while mode-covering ones preserve broader support. Furthermore, even when the target distributions are aligned, DMD's reverse-KL objective can still drive the student toward high-probability teacher regions in late training, reducing coverage and diversity. To address this, we propose joint distillation, which combines DMD's mode-seeking objective with a Consistency Distillation-based mode-covering constraint. Experiments show that our method improves generation quality, coverage, and diversity; notably, even with a Wan-1.3B DMD teacher, it outperforms baselines refined with Wan-14B, underscoring the importance of distributional alignment in autoregressive video distillation.

ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation

Establishing interpretable decision-making processes in long-horizon robotic manipulation is critical for enabling reliable human oversight and intervention. However, existing approaches to robotic manipulation largely treat skill selection as opaque mappings from observations to actions, offering limited transparency into how decisions are formed. In this work, we propose ConceptTree, a framework that reframes high-level manipulation skill selection as reasoning over human-interpretable concepts, representing high-level policies as a sequence of concept-level predicates over visual observations. Rather than relying on implicit latent representations, our method learns a normalized concept space grounded in visual inputs, over which a decision tree is trained to predict high-level skills. This formulation yields a transparent decision process that is both traceable and intervenable, enabling direct inspection and modification of policy behavior. We evaluate our approach on a set of real-world robotic manipulation tasks with increasing complexity. Experimental results show that ConceptTree consistently outperforms existing concept-based baselines, particularly in complex, long-horizon scenarios. Furthermore, we provide qualitative case studies showing that our model supports fine-grained intervention by modifying individual concepts, enabling targeted correction of decision errors without retraining.