We introduce SeamlessFlow, a server based reinforcement learning (RL) framework that addresses two core challenges in industrial scale RL: (1) decoupling RL training from the complex execution flow of agents; (2) maximizing GPU utilization with minimal idle time while preserving the stability and scalability required for large-scale deployments. First, SeamlessFlow introduces a data plane that decouples the RL trainer from diverse, complex agent implementations while sustaining high throughput. A central trajectory manager maintains complete interaction histories and supports partial rollout, allowing rollout to pause for weight updates and resume seamlessly, keeping agents unaware of service interruptions. Second, we propose a tag driven scheduling paradigm that abstracts hardware into capability tagged resources, unifying colocated and disaggregated architectures. Based on this, SeamlessFlow introduces a spatiotemporal multiplexing pipeline that dynamically reassigns idle training nodes to rollout in a train rollout separated setup, eliminating pipeline bubbles and fully exploiting heterogeneous cluster resources. By combining these innovations, SeamlessFlow delivers both stability and high performance, making it well suited for multi agent, long horizon, and other complex RL tasks.

The growing deployment of decision-making agents in dynamic environments increases the demand for safety verification. While critical testing scenario generation has emerged as an appealing verification methodology, effectively balancing diversity and criticality remains a key challenge for existing methods, particularly due to local optima entrapment in high-dimensional scenario spaces. To address this limitation, we propose a dual-space guided testing framework that coordinates scenario parameter space and agent behavior space, aiming to generate testing scenarios considering diversity and criticality. Specifically, in the scenario parameter space, a hierarchical representation framework combines dimensionality reduction and multi-dimensional subspace evaluation to efficiently localize diverse and critical subspaces. This guides dynamic coordination between two generation modes: local perturbation and global exploration, optimizing critical scenario quantity and diversity. Complementarily, in the agent behavior space, agent-environment interaction data are leveraged to quantify behavioral criticality/diversity and adaptively support generation mode switching, forming a closed feedback loop that continuously enhances scenario characterization and exploration within the parameter space. Experiments show our framework improves critical scenario generation by an average of 56.23\% and demonstrates greater diversity under novel parameter-behavior co-driven metrics when tested on five decision-making agents, outperforming state-of-the-art baselines.

Trajectory prediction and planning in autonomous driving are highly challenging due to the complexity of predicting surrounding agents' movements and planning the ego agent's actions in dynamic environments. Existing methods encode map and agent positions and decode future trajectories in Cartesian coordinates. However, modeling the relationships between the ego vehicle and surrounding traffic elements in Cartesian space can be suboptimal, as it does not naturally capture the varying influence of different elements based on their relative distances and directions. To address this limitation, we adopt the Polar coordinate system, where positions are represented by radius and angle. This representation provides a more intuitive and effective way to model spatial changes and relative relationships, especially in terms of distance and directional influence. Based on this insight, we propose Polaris, a novel method that operates entirely in Polar coordinates, distinguishing itself from conventional Cartesian-based approaches. By leveraging the Polar representation, this method explicitly models distance and direction variations and captures relative relationships through dedicated encoding and refinement modules, enabling more structured and spatially aware trajectory prediction and planning. Extensive experiments on the challenging prediction (Argoverse 2) and planning benchmarks (nuPlan) demonstrate that Polaris achieves state-of-the-art performance.

Open-vocabulary Object Goal Navigation requires an embodied agent to reach objects described by free-form language, including categories never seen during training. Existing end-to-end policies overfit small simulator datasets, achieving high success on training scenes but failing to generalize and exhibiting unsafe behaviour (frequent collisions). We introduce OVSegDT, a lightweight transformer policy that tackles these issues with two synergistic components. The first component is the semantic branch, which includes an encoder for the target binary mask and an auxiliary segmentation loss function, grounding the textual goal and providing precise spatial cues. The second component consists of a proposed Entropy-Adaptive Loss Modulation that is a per-sample scheduler that continuously balances imitation and reinforcement signals according to the policy entropy, eliminating brittle manual phase switches. These additions cut the sample complexity of training by 33%, and reduce collision count in two times while keeping inference cost low (130M parameters, RGB-only input). On HM3D-OVON, our model matches the performance on unseen categories to that on seen ones and establishes state-of-the-art results (40.1% SR, 20.9% SPL on val unseen) without depth, odom-etry, or large vision-language models.

As autonomous agents become adept at understanding and interacting with graphical user interface (GUI) environments, a new era of automated task execution is emerging. Recent studies have demonstrated that Reinforcement Learning (RL) can effectively enhance agents' performance in dynamic interactive GUI environments. However, these methods face two key limitations: (1) they overlook the significant variation in difficulty across different GUI tasks by treating the entire training data as a uniform set, which hampers the agent's ability to adapt its learning process; and (2) most approaches collapse task-specific nuances into a single, coarse reward, leaving the agent with a uniform signal that yields inefficient policy updates. To address these limitations, we propose CRAFT-GUI, a curriculum learning framework based on Group Relative Policy Optimization (GRPO) that explicitly accounts for the varying difficulty across trajectories. To enable more fine-grained policy optimization, we design a reward function that combines simple rule-based signals with model-judged evaluation, providing richer and more nuanced feedback during training. Experimental results demonstrate that our method achieves significant improvements over previous state-of-the-art approaches, outperforming them by 5.6% on public benchmarks Android Control and 10.3% on our internal online benchmarks, respectively. These findings empirically validate the effectiveness of integrating reinforcement learning with curriculum learning in GUI interaction tasks.

The growing interest in automatic survey generation (ASG), a task that traditionally required considerable time and effort, has been spurred by recent advances in large language models (LLMs). With advancements in retrieval-augmented generation (RAG) and the rising popularity of multi-agent systems (MASs), synthesizing academic surveys using LLMs has become a viable approach, thereby elevating the need for robust evaluation methods in this domain. However, existing evaluation methods suffer from several limitations, including biased metrics, a lack of human preference, and an over-reliance on LLMs-as-judges. To address these challenges, we propose SGSimEval, a comprehensive benchmark for Survey Generation with Similarity-Enhanced Evaluation that evaluates automatic survey generation systems by integrating assessments of the outline, content, and references, and also combines LLM-based scoring with quantitative metrics to provide a multifaceted evaluation framework. In SGSimEval, we also introduce human preference metrics that emphasize both inherent quality and similarity to humans. Extensive experiments reveal that current ASG systems demonstrate human-comparable superiority in outline generation, while showing significant room for improvement in content and reference generation, and our evaluation metrics maintain strong consistency with human assessments.

We introduce a new Multi-Agent System (MAS) - Allen, designed to address two core challenges in current MAS design: (1) improve system's policy autonomy, empowering agents to dynamically adapt their behavioral strategies, and (2) achieving the trade-off between collaborative efficiency, task supervision, and human oversight in complex network topologies. Our core insight is to redefine the basic execution unit in the MAS, allowing agents to autonomously form different patterns by combining these units. We have constructed a four-tier state architecture (Task, Stage, Agent, Step) to constrain system behavior from both task-oriented and execution-oriented perspectives. This achieves a unification of topological optimization and controllable progress. Allen grants unprecedented Policy Autonomy, while making a trade-off for the controllability of the collaborative structure. The project code has been open source at: https://github.com/motern88/Allen

When humans perform everyday tasks, we naturally adjust our actions based on the current state of the environment. For instance, if we intend to put something into a drawer but notice it is closed, we open it first. However, many autonomous robots lack this adaptive awareness. They often follow pre-planned actions that may overlook subtle yet critical changes in the scene, which can result in actions being executed under outdated assumptions and eventual failure. While replanning is critical for robust autonomy, most existing methods respond only after failures occur, when recovery may be inefficient or infeasible. While proactive replanning holds promise for preventing failures in advance, current solutions often rely on manually designed rules and extensive supervision. In this work, we present a proactive replanning framework that detects and corrects failures at subtask boundaries by comparing scene graphs constructed from current RGB-D observations against reference graphs extracted from successful demonstrations. When the current scene fails to align with reference trajectories, a lightweight reasoning module is activated to diagnose the mismatch and adjust the plan. Experiments in the AI2-THOR simulator demonstrate that our approach detects semantic and spatial mismatches before execution failures occur, significantly improving task success and robustness.

The field of artificial intelligence (AI) agents is evolving rapidly, driven by the capabilities of Large Language Models (LLMs) to autonomously perform and refine tasks with human-like efficiency and adaptability. In this context, multi-agent collaboration has emerged as a promising approach, enabling multiple AI agents to work together to solve complex challenges. This study investigates the application of role-based multi-agent systems to support stock selection in equity research and portfolio management. We present a comprehensive analysis performed by a team of specialized agents and evaluate their stock-picking performance against established benchmarks under varying levels of risk tolerance. Furthermore, we examine the advantages and limitations of employing multi-agent frameworks in equity analysis, offering critical insights into their practical efficacy and implementation challenges.

Generating high-quality and temporally synchronized audio from video content is essential for video editing and post-production tasks, enabling the creation of semantically aligned audio for silent videos. However, most existing approaches focus on short-form audio generation for video segments under 10 seconds or rely on noisy datasets for long-form video-to-audio zsynthesis. To address these limitations, we introduce LD-LAudio-V1, an extension of state-of-the-art video-to-audio models and it incorporates dual lightweight adapters to enable long-form audio generation. In addition, we release a clean and human-annotated video-to-audio dataset that contains pure sound effects without noise or artifacts. Our method significantly reduces splicing artifacts and temporal inconsistencies while maintaining computational efficiency. Compared to direct fine-tuning with short training videos, LD-LAudio-V1 achieves significant improvements across multiple metrics: $FD_{\text{passt}}$ 450.00 $\rightarrow$ 327.29 (+27.27%), $FD_{\text{panns}}$ 34.88 $\rightarrow$ 22.68 (+34.98%), $FD_{\text{vgg}}$ 3.75 $\rightarrow$ 1.28 (+65.87%), $KL_{\text{panns}}$ 2.49 $\rightarrow$ 2.07 (+16.87%), $KL_{\text{passt}}$ 1.78 $\rightarrow$ 1.53 (+14.04%), $IS_{\text{panns}}$ 4.17 $\rightarrow$ 4.30 (+3.12%), $IB_{\text{score}}$ 0.25 $\rightarrow$ 0.28 (+12.00%), $Energy\Delta10\text{ms}$ 0.3013 $\rightarrow$ 0.1349 (+55.23%), $Energy\Delta10\text{ms(vs.GT)}$ 0.0531 $\rightarrow$ 0.0288 (+45.76%), and $Sem.\,Rel.$ 2.73 $\rightarrow$ 3.28 (+20.15%). Our dataset aims to facilitate further research in long-form video-to-audio generation and is available at https://github.com/deepreasonings/long-form-video2audio.