Searcharxiv⌕ Search

arXiv subjects

Jiaxuan Gao

Publications and source records attributed to Jiaxuan Gao.

At least 19 recordsLinked to original sources
arXiv2026

Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning

Scaling test-time reasoning has substantially improved the problem-solving ability of large language models (LLMs), but standard autoregressive decoding still executes long reasoning traces sequentially, creating severe latency for difficult tasks (up to days and weeks). Parallel reasoning offers a natural remedy. However, prior systems primarily focus on Subtask Parallelism, where the model learns to decompose a high-level task into smaller chunks that can be solved independently. This approach overlooks another pervasive form of parallelism: Trial Parallelism, where multiple speculative attempts explore, verify, and aggregate competing hypotheses in parallel. In this paper, we introduce Parason, which reveals and learns both forms of parallelism in LLM reasoning. Our analysis identifies Trial Parallelism as the majority of parallelizable reasoning computation (65.5% in DeepSeek-V4's reasoning steps in HLE), and it becomes increasingly dominant on hard problems. Guided by this taxonomy, Parason converts sequential reasoning traces into structured parallel trajectories with a context-free grammar, then trains models with Parallelism-Aware Group Relative Policy Optimization (PA-GRPO), whose reward jointly balances accuracy, latency, and the two parallelism ratios. At inference time, Parason executes the learned parallel structure through tool calls, translating theoretical savings to real-world wall-clock acceleration. Experiments on mathematical reasoning benchmarks including AIME24 and AIME25 show that Parason achieves an average acceleration about 1.7$\times$ while maintaining competitive accuracy.

cs.AI↗
arXiv2026

Embodied Operators and Benchmarking: Toward Reusable and Deployable Embodied Intelligence Systems

Embodied intelligence systems require not only end-to-end policy models, but also reusable functional modules that transform multimodal observations, robot states, human demonstrations, and task contexts into structured representations, decisions, trajectories, control references, and system services. This work defines these modules as embodied operators and studies them as independent yet composable units in embodied intelligence pipelines. We clarify their definition boundary, emphasizing task semantics, standardized input-output contracts, deployability, reusability, and multi-layer optimizability. We further construct a taxonomy covering five categories: detection and segmentation, spatial localization and 3D understanding, hand motion recovery, embodied foundation models and task-decision operators, and planning, control, and system support operators. For each category, we summarize representative functions, technical paradigms, application roles, and practical limitations. Beyond taxonomy, we propose a multi-dimensional benchmark framework that evaluates embodied operators in terms of correctness, end-to-end efficiency, resource usage, temporal stability, portability, interface compatibility, deployment reliability, and downstream task utility. We also discuss workflow-level operator acceleration and open challenges in operator composition, data standardization, world models, VLA safety, edge deployment, and real-world application value. Overall, this work argues that embodied operators should be optimized and evaluated as holistic deployable components, providing a foundation for reusable, scalable, and verifiable embodied intelligence systems.

cs.AI↗
arXiv2026

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents

LLM agents are rapidly being deployed in production, including coding assistants, customer-support chatbots, and scientific research assistants, yet they remain fundamentally static in enterprise deployment. The LLM weights, system prompts, tool repertoires, and in-context harnesses are frozen at deployment time, and any improvement requires a manual loop of human-curated data collection, offline fine-tuning, modification of the agentic paradigm, and re-deployment. Recent work on self-evolving agents, such as OpenClaw for individual users, indicates that the next leap in agent capability will come from agents that continually learn from their own experience. In this paper, we argue that this vision for self-evolving agent deployment is being held back for enterprise-level large-scale agentic service not by reinforcement learning (RL) algorithms but by agentic online RL systems. Specifically, current agentic RL systems and the surrounding observability software stack are inadequate along three essential aspects: (i) there is no standardized agent trajectory data protocol capable of carrying RL learning signals at step granularity across heterogeneous agent paradigms; (ii) there is no enterprise-grade comprehensive data proxy that converts real workloads into governed learning substrates; and (iii) there is no unified agent evolution control plane that automatically decides, based on trajectory statistics, when to update policy weights or evolve the in-context harness. The next generation of agentic RL systems must be co-designed around these three pillars, and we sketch concrete architectures, case studies, and counter-arguments. We instantiate one branch through AReaL2.0, reorganizing existing RL infrastructure into an agent-oriented online RL loop for policy weight updates from deployed workloads.

cs.DC↗
arXiv2026

Building a Scalable, Reproducible, Evaluatable, and Closed-Loop Simulation Environment Foundation for Embodied Intelligence

This paper presents a cloud-native simulation infrastructure framework for embodied intelligence that supports large-scale training, standardized evaluation, and simulation-based data collection. The framework unifies simulation environment generation, task execution, trajectory collection, model evaluation, data management, and cloud services into a scalable and reproducible platform. To address the high cost, limited scalability, and poor reproducibility of real-world robotic data collection, the framework adopts cloud-native technologies including elastic resource scheduling, containerized simulation, unified data management, and service-oriented system design, enabling efficient large-scale simulation for multi-model and multi-task workloads. Built on a four-layer architecture, the framework provides standardized environment assets, automated task generation, trajectory collection, benchmark evaluation, and closed-loop data optimization. It further integrates representative systems including D-VLA, RL-VLA3, Sword, and Pre-VLA to support scalable simulation, dynamic scheduling, visual augmentation, and real-time data filtering. We argue that cloud-native simulation infrastructure provides a unified foundation for data generation, model training, standardized evaluation, and real-world deployment, and will play a key role in the future development of embodied intelligence.

cs.RO↗
arXiv2026

AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models

Reinforcement learning (RL)-based post-training for large language models (LLMs) is computationally expensive, as it generates many rollout sequences that frequently share long token prefixes. Existing RL frameworks usually process these sequences independently during policy training, i.e., repeatedly recomputing identical prefixes in both the forward and backward passes of policy gradient computation, leading to substantial inefficiencies in computation resources and memory usage. Although prefix sharing naturally induces a tree structure over rollouts, packed tree-mask approaches scale poorly in RL settings. In this paper, we introduce AReaL-DTA, which efficiently exploits prefix sharing in RL training. AReaL-DTA employs a depth-first search (DFS)-based execution strategy that dynamically traverses the rollout prefix tree during both forward and backward computation, materializing only a single root-to-leaf path at a time. To further improve scalability, AReaL-DTA incorporates a load-balanced distributed batching mechanism that dynamically constructs and processes prefix trees across multiple GPUs. On $τ^2$-bench, AReaL-DTA improves training throughput by up to $8.31\times$ over dense training and up to $1.70\times$ over sparse training. Our code is available at https://github.com/areal-project/AReaL/tree/feat/dta.

cs.LG↗
arXiv2026

Verifiable Process Rewards for Agentic Reasoning

Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of large language models (LLMs), but most existing approaches rely on sparse outcome-level feedback. This sparsity creates a credit assignment challenge in long-horizon agentic reasoning: a trajectory may fail despite containing many correct intermediate decisions, or succeed despite containing flawed ones. In this work, we study a class of densely-verifiable agentic reasoning problems, where intermediate actions can be objectively checked by symbolic or algorithmic oracles. We propose Verifiable Process Rewards (VPR), a framework that converts such oracles into dense turn-level supervision for reinforcement learning, and instantiate it in three representative settings: search-based verification for dynamic deduction, constraint-based verification for logical reasoning, and posterior-based verification for probabilistic inference. We further provide a theoretical analysis showing that dense verifier-grounded rewards can improve long-horizon credit assignment by providing more localized learning signals, with the benefit depending on the reliability of the verifier. Empirically, VPR outperforms outcome-level reward and rollout-based process reward baselines across controlled environments, and more importantly, transfers to both general and agentic reasoning benchmarks, suggesting that verifiable process supervision can foster general reasoning skills applicable beyond the training environments. Our results indicate that VPR is a promising approach for enhancing LLM agents whenever reliable intermediate verification is available, while also highlighting its dependence on oracle quality and the open challenge of extending VPR to less structured, open-ended environments.

cs.AI↗
arXiv2026

Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training

The integration of Vision-Language-Action (VLA) models with World Models has gained increasing attention. One representative approach treats learned World Models as generative simulators, enabling policy optimization entirely within "imagination." However, when deployed as simulators for specific environments such as the LIBERO benchmark, existing World Models often suffer from poor generalization and long-horizon error accumulation. During closed-loop rollouts, these models are highly sensitive to initial-state perturbations; minor changes in color, illumination, and other visual factors can trigger cascading hallucinations, leading to severe blurriness or overexposure. Moreover, long-horizon error accumulation further degrades the quality and fidelity of predicted future states. These issues limit the reliability of World Models as simulators. To mitigate these problems, we propose Sword, a robust World Model framework. Our method introduces Structure-Guided Style Augmentation to disentangle the visual textures of interactive environments from task-relevant dynamics, thereby improving generalization. We further propose Dynamic Latent Bootstrapping, which maintains consistency between training and inference while keeping memory consumption low. Extensive experiments on the LIBERO benchmark show that our method significantly outperforms the baseline WoVR in terms of generalization, generation quality, robustness, fidelity, and the success rate of reinforcement-learning post-training for VLA models.

cs.CV↗
arXiv2026

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation

Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL's ability to incentivize reasoning capacity beyond the base model. This raises a key challenge: how can RL be adapted to solve harder reasoning problems more effectively? To address this challenge, we propose a simple yet effective strategy via Question Augmentation: introduce partial solutions during training to reduce problem difficulty and provide more informative learning signals. Our method, QuestA, when applied during RL training on math reasoning tasks, not only improves pass@1 but also pass@k-particularly on problems where standard RL struggles to make progress. This enables continual improvement over strong open-source models such as DeepScaleR and OpenMath Nemotron, further enhancing their reasoning capabilities. We achieve new state-of-the-art results on math benchmarks using 1.5B-parameter models: 72.50% (+10.73%) on AIME24, 62.29% (+12.79%) on AIME25, and 41.67% (+10.11%) on HMMT25. Code, data and model are available at https://github.com/foreverlasting1202/QuestA.

cs.CL↗
arXiv2026

From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents

Interactive tool-using agents must solve real-world tasks via multi-turn interaction with both humans and external environments, requiring dialogue state tracking, multi-step tool execution, while following complex instructions. Post-training such agents is challenging because synthesis for high-quality multi-turn tool-use data is difficult to scale, and reinforcement learning (RL) could face noisy signals caused by user simulation, leading to degraded training efficiency. We propose a unified framework that combines a self-evolving data agent with verifier-based RL. Our system, EigenData, is a hierarchical multi-agent engine that synthesizes tool-grounded dialogues together with executable per-instance checkers, and improves generation reliability via closed-loop self-evolving process that updates prompts and workflow. Building on the synthetic data, we develop an RL recipe that first fine-tunes the user model and then applies GRPO-style training with trajectory-level group-relative advantages and dynamic filtering, yielding consistent improvements beyond SFT. Evaluated on tau^2-bench, our best model reaches 73.0% pass^1 on Airline and 98.3% pass^1 on Telecom, matching or exceeding frontier models. Overall, our results suggest a scalable pathway for bootstrapping complex tool-using behaviors without expensive human annotation.

cs.AI↗
arXiv2026

MAGE: Meta-Reinforcement Learning for Language Agents toward Strategic Exploration and Exploitation

Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some flexibility, they fail to internalize the adaptive ability required for long-term improvement. Meta-Reinforcement Learning (meta-RL) provides an alternative by embedding the learning process directly within the model. However, existing meta-RL approaches for LLMs focus primarily on exploration in single-agent settings, neglecting the strategic exploitation necessary for multi-agent environments. We propose MAGE, a meta-RL framework that empowers LLM agents for strategic exploration and exploitation. MAGE utilizes a multi-episode training regime where interaction histories and reflections are integrated into the context window. By using the final episode reward as the objective, MAGE incentivizes the agent to refine its strategy based on past experiences. We further combine population-based training with an agent-specific advantage normalization technique to enrich agent diversity and ensure stable learning. Experiment results show that MAGE outperforms existing baselines in both exploration and exploitation tasks. Furthermore, MAGE exhibits strong generalization to unseen opponents, suggesting it has internalized the ability for strategic exploration and exploitation. Code is available at https://github.com/Lu-Yang666/MAGE.

cs.AI↗
arXiv2026

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reinforcement learning (RL) has become a dominant paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training systems. Most existing large-scale RL systems for LLMs are synchronous, alternating generation and training in a batch setting where rollouts in each training batch are generated by the same model. This approach stabilizes RL training but suffers from severe system-level inefficiency: generation must wait until the longest output in the batch is completed before model updates, resulting in GPU underutilization. We present AReaL, a fully asynchronous RL system that completely decouples generation from training. Rollout workers in AReaL continuously generate new outputs without waiting, while training workers update the model whenever a batch of data is collected. AReaL also incorporates a collection of system-level optimizations, leading to substantially higher GPU utilization. To stabilize RL training, AReaL balances the workload of rollout and training workers to control data staleness, and adopts a staleness-enhanced PPO variant to better handle outdated training samples. Extensive experiments on math and code reasoning benchmarks show that AReaL achieves up to 2.77$\times$ training speedup compared to synchronous systems with the same number of GPUs and matched or improved final performance. The code of AReaL is available at https://github.com/inclusionAI/AReaL/.

cs.LG↗
arXiv2025

Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn

Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time as the length of the reasoning context increases. However, compared with training-time scaling, test-time scaling is fundamentally limited by the limited context length of base models, which remains orders of magnitude smaller than the amount of tokens consumed during training. We revisit test-time enhancement techniques through the lens of scaling effect and introduce a unified framework of multi-dimensional test-time scaling to extend the capacity of test-time reasoning. Beyond conventional context-length scaling, we consider two additional dimensions: batch scaling, where accuracy improves with parallel sampling, and turn scaling, where iterative self-refinement enhances reasoning quality. Building on this perspective, we propose 3D test-time scaling, which integrates context, batch, and turn scaling. We show that: (1) each dimension demonstrates a test-time scaling effect, but with a bounded capacity; (2) combining all three dimensions substantially improves the reasoning performance of challenging testbeds, including IOI, IMO, and CPHO, and further benefits from human preference feedback; and (3) the human-in-the-loop framework naturally extends to a more open-ended domain, i.e., embodied learning, which enables the design of humanoid control behaviors.

cs.LG↗
arXiv2025

AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs

Maximizing training throughput and cost-efficiency of RL for LLMs is essential to democratize this advanced technique. One promising but challenging approach is to deploy such a computational workflow over heterogeneous GPUs. Unlike conventional large-scale LLM pretraining, RL training generally decomposes into three coupled stages, i.e., rollout generation, reward computation, and policy/value updates, which exhibit markedly different compute intensities, memory footprints, and communication patterns. Recent research shows that fully asynchronous RL training can disaggregate these stages across disjoint hardware pools without sacrificing training stability, creating a great opportunity for real-world heterogeneous deployment. To this end, we present AReaL-Hex, a heterogeneity-aware asynchronous RL training system that effectively schedules how to execute rollout generation and policy model training over heterogeneous GPUs while enforcing data staleness bounds. Concretely, we use a two-phase scheduler: (i) a constrained search with MILP to select per-stage parallelization strategies and workload assignments given a resource budget, and (ii) a graph-partitioning step that allocates heterogeneous GPUs and interconnects to maximize end-to-end throughput. Built atop a fully asynchronous RL architecture, AReaL-Hex maps HBM-I/O-bound generation and compute-bound optimization to more cost-efficient resources and balances their producer-consumer interactions to avoid both idleness and stale rollout trajectories. On the mathematical reasoning task with various model scales (1.5B, 7B, and 14B), compared to homogeneous deployments of state-of-the-art asynchronous RL systems: (i) When maintaining the same total budgets, AReaL-Hex delivers up to 1.50x higher training throughput; (ii) When achieving the same training throughput, AReaL-Hex results in up to 1.46x reduction in training cost.

cs.DC↗
arXiv2025

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

Recent advancements in LLM-based agents have demonstrated remarkable capabilities in handling complex, knowledge-intensive tasks by integrating external tools. Among diverse choices of tools, search tools play a pivotal role in accessing vast external knowledge. However, open-source agents still fall short of achieving expert-level Search Intelligence, the ability to resolve ambiguous queries, generate precise searches, analyze results, and conduct thorough exploration. Existing approaches fall short in scalability, efficiency, and data quality. For example, small turn limits in existing online RL methods, e.g. <=10, restrict complex strategy learning. This paper introduces ASearcher, an open-source project for large-scale RL training of search agents. Our key contributions include: (1) Scalable fully asynchronous RL training that enables long-horizon search while maintaining high training efficiency. (2) A prompt-based LLM agent that autonomously synthesizes high-quality and challenging QAs, creating a large-scale QA dataset. Through RL training, our prompt-based QwQ-32B agent achieves substantial improvements, with 78.0% and 34.3% Avg@4 gains on xBench and GAIA, respectively. Notably, our agent exhibits extreme long-horizon search, with tool calls exceeding 100 turns and output tokens exceeding 400k during training time. With a simple agent design and no external LLMs, ASearcher-Web-QwQ achieves Avg@4 scores of 51.1 on xBench and 58.7 on GAIA, surpassing existing open-source 32B agents. Finally, we also show that ASearcher-Web-QwQ could achieve performance of commercial systems using external summary tool in a zero-shot transfer manner and test-time search. We open-source our models, training data, and codes in https://github.com/inclusionAI/ASearcher.

cs.CL↗
arXiv2025

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps

Diffusion policies, widely adopted in decision-making scenarios such as robotics, gaming and autonomous driving, are capable of learning diverse skills from demonstration data due to their high representation power. However, the sub-optimal and limited coverage of demonstration data could lead to diffusion policies that generate sub-optimal trajectories and even catastrophic failures. While reinforcement learning (RL)-based fine-tuning has emerged as a promising solution to address these limitations, existing approaches struggle to effectively adapt Proximal Policy Optimization (PPO) to diffusion models. This challenge stems from the computational intractability of action likelihood estimation during the denoising process, which leads to complicated optimization objectives. In our experiments starting from randomly initialized policies, we find that online tuning of Diffusion Policies demonstrates much lower sample efficiency compared to directly applying PPO on MLP policies (MLP+PPO). To address these challenges, we introduce NCDPO, a novel framework that reformulates Diffusion Policy as a noise-conditioned deterministic policy. By treating each denoising step as a differentiable transformation conditioned on pre-sampled noise, NCDPO enables tractable likelihood evaluation and gradient backpropagation through all diffusion timesteps. Our experiments demonstrate that NCDPO achieves sample efficiency comparable to MLP+PPO when training from scratch, outperforming existing methods in both sample efficiency and final performance across diverse benchmarks, including continuous robot control and multi-agent game scenarios. Furthermore, our experimental results show that our method is robust to the number denoising timesteps in the Diffusion Policy.

cs.LG↗
arXiv2025

How Far Are We from Optimal Reasoning Efficiency?

Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redundant reasoning traces. This inefficiency incurs high inference costs and limits practical deployment. While existing fine-tuning methods aim to improve reasoning efficiency, assessing their efficiency gains remains challenging due to inconsistent evaluations. In this work, we introduce the reasoning efficiency frontiers, empirical upper bounds derived from fine-tuning base LRMs across diverse approaches and training configurations. Based on these frontiers, we propose the Reasoning Efficiency Gap (REG), a unified metric quantifying deviations of any fine-tuned LRMs from these frontiers. Systematic evaluation on challenging mathematical benchmarks reveals significant gaps in current methods: they either sacrifice accuracy for short length or still remain inefficient under tight token budgets. To reduce the efficiency gap, we propose REO-RL, a class of Reinforcement Learning algorithms that minimizes REG by targeting a sparse set of token budgets. Leveraging numerical integration over strategically selected budgets, REO-RL approximates the full efficiency objective with low error using a small set of token budgets. Through systematic benchmarking, we demonstrate that our efficiency metric, REG, effectively captures the accuracy-length trade-off, with low-REG methods reducing length while maintaining accuracy. Our approach, REO-RL, consistently reduces REG by >=50 across all evaluated LRMs and matching Qwen3-4B/8B efficiency frontiers under a 16K token budget with minimal accuracy loss. Ablation studies confirm the effectiveness of our exponential token budget strategy. Finally, our findings highlight that fine-tuning LRMs to perfectly align with the efficiency frontiers remains an open challenge.

cs.CL↗
arXiv2025

ICPL: Few-shot In-context Preference Learning via LLMs

Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tabula rasa. We demonstrate that Large Language Models (LLMs) have native preference-learning capabilities that allow them to achieve sample-efficient preference learning, addressing this challenge. We propose In-Context Preference Learning (ICPL), which uses in-context learning capabilities of LLMs to reduce human query inefficiency. ICPL uses the task description and basic environment code to create sets of reward functions which are iteratively refined by placing human feedback over videos of the resultant policies into the context of an LLM and then requesting better rewards. We first demonstrate ICPL's effectiveness through a synthetic preference study, providing quantitative evidence that it significantly outperforms baseline preference-based methods with much higher performance and orders of magnitude greater efficiency. We observe that these improvements are not solely coming from LLM grounding in the task but that the quality of the rewards improves over time, indicating preference learning capabilities. Additionally, we perform a series of real human preference-learning trials and observe that ICPL extends beyond synthetic settings and can work effectively with humans-in-the-loop.

cs.AI↗
arXiv2025

Industrial-Grade Sensor Simulation via Gaussian Splatting: A Modular Framework for Scalable Editing and Full-Stack Validation

Sensor simulation is pivotal for scalable validation of autonomous driving systems, yet existing Neural Radiance Fields (NeRF) based methods face applicability and efficiency challenges in industrial workflows. This paper introduces a Gaussian Splatting (GS) based system to address these challenges: We first break down sensor simulator components and analyze the possible advantages of GS over NeRF. Then in practice, we refactor three crucial components through GS, to leverage its explicit scene representation and real-time rendering: (1) choosing the 2D neural Gaussian representation for physics-compliant scene and sensor modeling, (2) proposing a scene editing pipeline to leverage Gaussian primitives library for data augmentation, and (3) coupling a controllable diffusion model for scene expansion and harmonization. We implement this framework on a proprietary autonomous driving dataset supporting cameras and LiDAR sensors. We demonstrate through ablation studies that our approach reduces frame-wise simulation latency, achieves better geometric and photometric consistency, and enables interpretable explicit scene editing and expansion. Furthermore, we showcase how integrating such a GS-based sensor simulator with traffic and dynamic simulators enables full-stack testing of end-to-end autonomy algorithms. Our work provides both algorithmic insights and practical validation, establishing GS as a cornerstone for industrial-grade sensor simulation.

cs.CV↗