论文检索

Reinforcement Learning · Deep RL

Alfredo Reichlin, Adriano Pacciarelli, Danica Kragic, Miguel Vasco

Estimating the state of an environment from high-dimensional, multimodal, and noisy observations is a fundamental challenge in reinforcement learning (RL). Traditional approaches rely on probabilistic models to account for the uncertainty, but often require explicit noise assumptions, in turn limiting generalization. In this work, we contribute a novel method to learn a structured latent representation, in which distances between states directly correlate with the minimum number of actions required to transition between them. The proposed metric space formulation provides a geometric interpretation of uncertainty without the need for explicit probabilistic modeling. To achieve this, we introduce a multimodal latent transition model and a sensor fusion mechanism based on inverse distance weighting, allowing for the adaptive integration of multiple sensor modalities without prior knowledge of noise distributions. We empirically validate the approach on a range of multimodal RL tasks, demonstrating improved robustness to sensor noise and superior state estimation compared to baseline methods. Our experiments show enhanced performance of an RL agent via the learned representation, eliminating the need of explicit noise augmentation. The presented results suggest that leveraging transition-aware metric spaces provides a principled and scalable solution for robust state estimation in sequential decision-making.

Reinforcement Learning · Deep RL

Utsav Singh, Souradip Chakraborty, Wesley Suttle, Brian Sadler, Derrik Asher, Anit Kumar Sahu, Mubarak Shah, Vinay Purushothaman Namboodiri, Amrit Bedi

Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However, HRL methods face two fundamental challenges: (i) non-stationarity caused by the evolving lower-level policy during training, which destabilizes higher-level learning, and (ii) the generation of infeasible subgoals that lower-level policies cannot achieve. To address these challenges, we introduce DIPPER, a novel HRL framework that formulates goal-conditioned HRL as a bi-level optimization problem and leverages direct preference optimization (DPO) to train the higher-level policy. By learning from preference comparisons over subgoal sequences rather than rewards that depend on the evolving lower-level policy, DIPPER mitigates the impact of non-stationarity on higher-level learning. To address infeasible subgoals, DIPPER incorporates lower-level value function regularization that encourages the higher-level policy to propose achievable subgoals. We introduce two novel metrics to quantitatively verify that DIPPER mitigates non-stationarity and infeasible subgoal generation issues in HRL. Empirical evaluation on challenging robotic navigation and manipulation benchmarks shows that DIPPER achieves upto 40% improvements over state-of-the-art baselines on challenging sparse-reward scenarios, highlighting the potential of preference-based learning for addressing longstanding HRL limitations.

Deep Learning · Generative Models and Autoencoders

Amrith Setlur, Matthew Yang, Charlie Snell, Jeremiah Greer, Ian Wu, Virginia Smith, Max Simchowitz, Aviral Kumar

Test-time scaling offers a promising path to improve LLM reasoning by utilizing more compute at inference time; however, the true promise of this paradigm lies in extrapolation (i.e., improvement in performance on hard problems as LLMs keep "thinking" for longer, beyond the maximum token budget they were trained on). Surprisingly, we find that most existing reasoning models do not extrapolate well. We show that one way to enable extrapolation is by training the LLM to perform in-context exploration: training the LLM to effectively spend its test time budget by chaining operations (such as generation, verification, refinement, etc.), or testing multiple hypotheses before it commits to an answer. To enable in-context exploration, we identify three key ingredients as part of our recipe e3: (1) chaining skills that the base LLM has asymmetric competence in, e.g., chaining verification (easy) with generation (hard), as a way to implement in-context search; (2) leveraging "negative" gradients from incorrect traces to amplify exploration during RL, resulting in longer search traces that chains additional asymmetries; and (3) coupling task difficulty with training token budget during training via a specifically-designed curriculum to structure in-context exploration. Our recipe e3 produces the best known 1.7B model according to AIME'25 and HMMT'25 scores, and extrapolates to 2x the training token budget. Our e3-1.7B model not only attains high pass@1 scores, but also improves pass@k over the base model.

Deep Learning · Algorithms

Xiangxiang Chu, Hailang Huang, Xiao Zhang, Fei Wei, Yong Wang

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and propose a minimalist RL approach termed Group Policy Gradient (GPG). Unlike conventional methods, GPG directly optimizes the original RL objective, thus obviating the need for surrogate loss functions. By eliminating the critic and reference models, avoiding KL divergence constraints, and addressing the advantage and gradient estimation bias, our approach significantly simplifies the training process compared to Group Relative Policy Optimization (GRPO). Our approach achieves superior performance without relying on auxiliary techniques or adjustments. As illustrated in Figure 1, extensive experiments demonstrate that our method not only reduces computational costs but also consistently outperforms GRPO across various unimodal and multimodal tasks.

Deep Learning · Everything Else

Yunfei Xie, Yinsong Ma, Shiyi Lan, Alan Yuille, Junfei Xiao, Chen Wei

Developing reasoning capabilities in multimodal large language models (MLLMs) remains challenging. Motivated by literature suggesting that gameplay promotes transferable reasoning skills, we propose a novel post-training method, Visual Game Learning (ViGaL), where MLLMs develop generalizable reasoning skills through playing arcade-like games. Specifically, we show that training a 7B-parameter MLLM via reinforcement learning (RL) on simple games like Snake significantly enhances the downstream performance on multimodal math benchmarks like MathVista, and on multi-discipline questions like MMMU, without seeing any worked solutions, equations, or diagrams during RL. Remarkably, our model outperforms specialist models post-trained on benchmark-oriented multimodal reasoning data, while preserving the model’s performance on general visual benchmarks, a challenge where specialist models often fall short. Our findings suggest that multimodal reasoning can emerge from gameplay, pointing to a promising strategy of designing surrogate tasks for RL post-training. The code is available at https://yunfeixie233.github.io/ViGaL.

Dingdong WANG, Shujie LIU, Tianhua Zhang, Youjun Chen, Jinyu Li, Helen Meng

Emotional information in speech plays a unique role in multimodal perception. However, current Speech Large Language Models (SpeechLLMs), similar to conventional speech emotion recognition (SER) systems, still treat emotion understanding as a simple classification problem. This provides limited interpretability of predictions, while leaving the LLMs’ expressive and reasoning capabilities underutilized. In this work, we take the first step to reformulate SER as a deep reasoning problem through reinforcement learning (RL). We propose EmotionThinker, which is designed to generate accurate emotion predictions with interpretable explanations grounded in fine-grained acoustic cues. To achieve this, we first construct EmotionCoT-35K, an emotional reasoning dataset with Chain-of-Thought annotations and detailed captions. Second, we observe that current SpeechLLMs exhibit weak prosody perception, whereas prosodic cues constitute fundamental signals for interpreting emotions. To address this, we develop the prosody-enhanced foundation model EmotionThinker-Base, and demonstrate that prosody enhancement improves emotion understanding. Third, we introduce Group-Relative-Policy-Optimization with Progressive-Trust-aware-Reasoning-Reward (GRPO-PTR}) for RL. Different from standard GRPO, which relies only on rule-based outcome rewards, GRPO-PTR progressively introduces reasoning reward, dynamically adjusts it with a trustworthiness weight reflecting the alignment between reasoning and outcome, and evaluates the overall reasoning quality with a reward model based on multi-dimensional criteria. EmotionThinker outperforms previous state-of-the-art evaluation models both in emotion accuracy and explanation quality, advancing SER toward interpretable multimodal reasoning.

Reinforcement Learning · Deep RL

yueheng li, Guangming Xie, Zongqing Lu

Reinforcement Learning (RL) in partially observable environments poses significant challenges due to the complexity of learning under uncertainty. While additional information, such as that available in simulations, can enhance training, effectively leveraging it remains an open problem. To address this, we introduce Guided Policy Optimization (GPO), a framework that co-trains a guider and a learner. The guider takes advantage of privileged information while ensuring alignment with the learner's policy that is primarily trained via imitation learning. We theoretically demonstrate that this learning scheme achieves optimality comparable to direct RL, thereby overcoming key limitations inherent in existing approaches. Empirical evaluations show strong performance of GPO across various tasks, including continuous control with partial observability and noise, and memory-based challenges, significantly outperforming existing methods.

Reinforcement Learning · Deep RL

He Zhang, Ying Sun, Hui Xiong

Flow-matching policies hold great promise for reinforcement learning (RL) by capturing complex, multi-modal action distributions. However, their practical application is often hindered by prohibitive inference latency and ineffective online exploration. Although recent works have employed one-step distillation for fast inference, the structure of the initial noise distribution remains an overlooked factor that presents significant untapped potential. This overlooked factor, along with the challenge of controlling policy stochasticity, constitutes two critical areas for advancing distilled flow-matching policies. To overcome these limitations, we propose GoldenStart (GS-flow), a policy distillation method with Q-guided priors and explicit entropy control. Instead of initializing generation from uninformed noise, we introduce a Q-guided prior modeled by a conditional VAE. This state-conditioned prior repositions the starting points of the one-step generation process into high-Q regions, effectively providing a ``golden start'' that shortcuts the policy to promising actions. Furthermore, for effective online exploration, we enable our distilled actor to output a stochastic distribution instead of a deterministic point. This is governed by entropy regularization, allowing the policy to shift from pure exploitation to principled exploration. Our integrated framework demonstrates that by designing the generative startpoint and explicitly controlling policy entropy, it is possible to achieve efficient and exploratory policies, bridging the generative models and the practical actor-critic methods. We conduct extensive experiments on offline and online continuous control benchmarks, where our method significantly outperforms prior state-of-the-art approaches.

Reinforcement Learning · Deep RL

Zhuoxu Huang, Mengxi Jia, Hao Sun, Xuelong Li, Jungong Han

Reinforcement Learning with verifiable rewards (RLVR) has emerged as a primary learning paradigm for enhancing the reasoning capabilities of multi-modal large language models (MLLMs). However, during RL training, the enormous state space of MLLM and sparse rewards often leads to entropy collapse, policy degradation, or over-exploitation of suboptimal behaviors. This necessitates an exploration strategy that maintains productive stochasticity while avoiding the drawbacks of uncontrolled random sampling, yielding inefficient exploration. In this paper, we propose CalibRL, a hybrid-policy RLVR framework that supports controllable exploration with expert guidance, enabled by two key mechanisms. First, a distribution-aware advantage weighting scales updates by group rareness to calibrate the distribution, therefore preserving exploration. Meanwhile, the asymmetric activation function (LeakyReLU) leverages the expert knowledge as a calibration baseline to moderate overconfident updates while preserving their corrective direction. CalibRL increases policy entropy in a guided manner and clarifies the target distribution by estimating the on-policy distribution through online sampling. Updates are driven by these informative behaviors, avoiding convergence to erroneous patterns. Importantly, these designs help alleviate the distributional mismatch between the model’s policy and expert trajectories, thereby achieving a more stable balance between exploration and exploitation. Extensive experiments across eight benchmarks, including both in-domain and out-of-domain settings, demonstrate consistent improvements, validating the effectiveness of our controllable hybrid-policy RLVR training. Code is available at https://github.com/zhh6425/CalibRL.

Reinforcement Learning · Deep RL

Zhiping Xiao, Yusheng Zhao, Qixin ZHANG, Jiaye Xie, Wanjia Zhao, Weizhi Zhang, Xiao Luo, Philip Yu, Ming Zhang

Reinforcement Learning with Verifiable Reward (RLVR) has equipped large language models (LLMs) with the capability of reasoning over complicated logical problems through policy optimization. However, conventional methods require complete annotation of the entire dataset and allocate computation uniformly over all samples. We articulate the lottery sample hypothesis in policy optimization of LLMs: a large training set contains a small subset that, when trained alone, yields performance comparable to that of the full dataset. This paper therefore explores the following question: How can we identify these lottery-winning samples from the original dataset without access to answers? Unlike prior efforts that analyze the effect of different samples in the training set with complete annotation, this paper focuses on the unsupervised discovery of critical instances for LLM reasoning and proposes a novel framework termed Complementary Conformal Selection (CONST). Specifically, CONST evaluates the importance of samples by considering two complementary components: procedural volatility and outcome volatility. Procedural volatility measures the potential variations during the LLM’s reasoning process, while outcome volatility captures inconsistencies in the final answer. Subsequently, conformal prediction is used to obtain a prediction set whose cardinality serves as the criterion for selecting the lottery-winning samples for annotation. We also provide a theoretical analysis, showing that CONST can effectively approximate the optimal policy. Extensive experiments on various LLMs across different datasets demonstrate the effectiveness of CONST.

Reinforcement Learning · Deep RL

Peixuan Han, ADIT KRISHNAN, Gerald Friedland, Jiaxuan You, Luyang Kong

Reinforcement learning with verifiable rewards has significantly advanced reasoning with large language models (LLMs) in domains such as mathematics and logic. However, verifiable signals provide only coarse-grained or binary correctness feedback. This limitation results in inefficiencies like overly verbose or repetitive reasoning. Existing length-based solutions (e.g., length penalty) compromise accuracy. To address this deficiency, we introduce **self-aligned reward (SAR)**, a generic, universally applicable self-guided signal that complements verifiable rewards to enhance both reasoning accuracy and efficiency in RL. Specifically, SAR is defined as the relative perplexity difference between an answer conditioned on the query and the standalone answer, thereby favoring responses that are concise and query-specific. Quantitative analysis reveals that SAR reliably judges answer quality: concise, correct answers score higher than redundant ones, and partially correct answers score higher than entirely incorrect ones. Evaluation on 4 different models across 7 benchmarks shows that integrating SAR with prevalent RL algorithms like PPO and GRPO reduces answer length by 30%, while improving accuracy by 4%. Our analysis also shows that SAR generalizes well to out-of-domain tasks and achieves a Pareto-optimal frontier between correctness and efficiency compared to state-of-the-art baselines. We also show that SAR shortens unnecessary elaboration while preserving advanced reasoning behaviors. These results highlight the promise of self-aligned reward as a fine-grained complement to verifiable rewards, paving the way for efficient and effective LLM training. All of our code implementations and data are publicly available at GitHub.

Reinforcement Learning · Deep RL

Zhengkang Guo, Wenhao Liu, Mingchen Xie, Jingwen Xu, Zisu Huang, Muzhao Tian, Jianhan Xu, Yuanzhe Shen, Qi Qian, Muling Wu 等

Large language models (LLMs) are increasingly expected to tackle complex tasks, driven by their expanding applications and users' growing proficiency in crafting sophisticated prompts. However, as the number of explicitly stated requirements increases (particularly more than $10$ constraints), LLMs often struggle to accurately follow such complex instructions, which limits their applicability in complex real-world scenarios. To the best of our knowledge, existing datasets do not exceed 10 constraints per instance. To address this challenge, we propose RECAST, an efficient and scalable framework for synthesizing datasets where each example incorporates far more constraints than those in existing benchmarks, aiming to challenge and extend the boundaries of models’ ability to follow complex instructions. These constraints are extracted from real-world prompt-response pairs to ensure practical relevance. Using this framework, we construct RECAST-$30$K, a large-scale, high-quality dataset comprising $30$k instances spanning $19$ constraint types. Experimental results demonstrate that models fine-tuned on RECAST-30K substantially improve in following complex instructions while maintaining their general capabilities without degradation. Moreover, RECAST enables automatic verification of constraint satisfaction via rule-based validators for quantitative constraints and LLM-based validators for qualitative ones, the verifiability provided by RECAST enables the design of reward functions for reinforcement learning, which further boosts model performance on complex and challenging tasks.

Reinforcement Learning · Deep RL

Liang CHEN, Xueting Han, Qizhou Wang, Bo Han, Jing Bai, Hinrich Schuetze, Kam-Fai Wong

Balancing exploration and exploitation remains a central challenge in reinforcement learning with verifiable rewards (RLVR) for large language models (LLMs). Current RLVR methods often overemphasize exploitation, leading to entropy collapse, diminished exploratory capacity, and ultimately limited performance gains. Although techniques that increase policy stochasticity can promote exploration, they frequently fail to escape dominant behavioral modes. This creates a self-reinforcing loop—repeatedly sampling and rewarding dominant modes—that further erodes exploration. We introduce **E**xploration-**E**nhanced **P**olicy **O**ptimization (**EEPO**), a framework that promotes exploration via two-stage rollouts with adaptive unlearning. In the first stage, the model generates half of the trajectories; it then undergoes a lightweight unlearning step to temporarily suppress these sampled responses, forcing the second stage to explore different regions of the output space. This *sample-then-forget* mechanism disrupts the self-reinforcing loop and promotes wider exploration during rollouts. Across five reasoning benchmarks, EEPO outperforms GRPO, achieving average relative gains of 24.3\% on Qwen2.5-3B, 33.0\% on Llama3.2-3B-Instruct, and 10.4\% on Qwen3-8B-Base.

Reinforcement Learning · Deep RL

Anisha Gunjal, Anthony Wang, Elaine Lau, Vaskar Nath, Yunzhong He, Bing Liu, Sean Hendryx

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding. However, extending it to real-world reasoning tasks is challenging, as evaluation depends on nuanced, multi-criteria judgments rather than binary correctness. Instance-specific rubrics have recently been used in evaluation benchmarks to capture such judgments, but their potential as reward signals for on-policy post-training remains underexplored. We introduce $\textbf{Rubrics as Rewards (\textit{RaR})}$, an on-policy reinforcement learning method that extends RLVR beyond verifiable domains by using rubric-based feedback. Across both medical and science domains, we evaluate multiple strategies for aggregating rubric feedback into rewards. The best RaR variant achieves relative improvements of up to 31\% on HealthBench and 7\% on GPQA-Diamond over popular LLM-as-judge baselines that rely on direct Likert-based rewards. These results demonstrate that RaR-trained policies adapt well to diverse evaluation formats, performing strongly on both rubric-based and multiple-choice tasks. Moreover, we find that using rubrics as structured reward signals yields better alignment for smaller judges and reduces performance variance across judge scales.

Reinforcement Learning · Deep RL

David McAllister, Songwei Ge, Brent Yi, Chung Min Kim, Ethan Weber, Hongsuk Choi, Haiwen Feng, Angjoo Kanazawa

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm that brings flow matching into the policy gradient framework. FPO casts policy optimization as maximizing an advantage-weighted ratio computed from the conditional flow matching loss, in a manner compatible with the popular PPO-clip framework. It sidesteps the need for exact likelihood computation while preserving the generative capabilities of flow-based models. Unlike prior approaches for diffusion-based reinforcement learning that bind training to a specific sampling method, FPO is agnostic to the choice of diffusion or flow integration at both training and inference time. We show that FPO can train diffusion-style policies from scratch in a variety of continuous control tasks. We find that flow-based models can capture multimodal action distributions and achieve higher performance than Gaussian policies, particularly in under-conditioned settings.

Reinforcement Learning · Deep RL

Yiyang Jin, Kunzhao Xu, Hang Li, Xueting Han, Yanmin Zhou, Cheng Li, Jing Bai

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models. Howerer, existing methods rely solely on outcome rewards, without explicitly optimizing verification or leveraging reliable signals from realistic environments, leading to unreliable self-verification and limited test-time scaling. To address this, we widen the verification–generation asymmetry by explicitly optimizing self-verification, making it a reliable driver of deeper test-time scaling. We introduce ReVeal, a multi-turn Reinforcement learning framework that evolves code generation through self-Verification and tool-based evaluation. ReVeal structures long-horizon reasoning as iterative generation–verification turns and incorporates TAPO for turn-level credit assignment, fostering the co-evolution of code and test generation. At inference, this strengthened self-verification enables the model to use self-constructed tests and tool feedback to continuously evolve code for 20+ turns on LiveCodeBench despite training on only three. It also significantly improves Pass@k, indicating stronger exploration that expands the reasoning boundaries of the base model. These findings highlight the promise of ReVeal as a scalable paradigm for RL training and test-time scaling, paving the way for more robust and autonomous AI agents. Code is available at [https://ReVeal.github.io/](https://shimly-2.github.io/ReVeal.github.io/).

Reinforcement Learning · Deep RL

Ofir Nabati, Bo Dai, Shie Mannor, Guy Tennenholtz

Representation learning is critical to the empirical and theoretical success of reinforcement learning. However, many existing methods are induced from model-learning aspects, misaligning them with the RL task in hand. This work introduces the Spectral Bellman Method, a novel framework derived from the Inherent Bellman Error (IBE) condition. It aligns representation learning with the fundamental structure of Bellman updates across a space of possible value functions, making it directly suited for value-based RL. Our key insight is a fundamental spectral relationship: under the zero-IBE condition, the transformation of a distribution of value functions by the Bellman operator is intrinsically linked to the feature covariance structure. This connection yields a new, theoretically-grounded objective for learning state-action features that capture this Bellman-aligned covariance, requiring only a simple modification to existing algorithms. We demonstrate that our learned representations enable structured exploration by aligning feature covariance with Bellman dynamics, improving performance in hard-exploration and long-horizon tasks. Our framework naturally extends to multi-step Bellman operators, offering a principled path toward learning more powerful and structurally sound representations for value-based RL.

Reinforcement Learning · Deep RL

Chi Ruan, Dongfu Jiang, Yubo Wang, Wenhu Chen

Reinforcement Learning (RL) has emerged as a popular training paradigm, particularly when paired with reasoning models. While effective, it primarily focuses on generating responses and lacks mechanisms to explicitly foster critique or reflection. Several recent studies, like Critique-Fine-Tuning (CFT) and Critique-Guided-Distillation (CGD) have shown the benefits of explicitly teaching LLMs how to critique. Motivated by them, we propose Critique Reinforcement Learning (CRL), where the model is tasked with generating a critique for a given (question, solution) pair. The reward is determined solely by whether the final judgment label $c \in \{\texttt{True}, \texttt{False}\}$ of the generated critique aligns with the ground-truth judgment $c^*$. Building on this point, we introduce Critique-Coder, which is trained on a hybrid of RL and CRL by substituting 20\% of the standard RL data with CRL data. We fine-tune multiple models (Critique-Coder) and evaluate them on different benchmarks to show their advantages over RL-only models. We show that Critique-Coder consistently outperforms RL-only baselines on all the evaluated benchmarks. Notably, our Critique-Coder-8B can reach over 60\% on LiveCodeBench (v5), outperforming other reasoning models like DeepCoder-14B and GPT-o1. Beyond code generation, Critique-Coder also demonstrates enhanced general reasoning abilities, as evidenced by its better performance on logic reasoning tasks from the BBEH dataset. This indicates that the application of CRL on coding datasets enhances general reasoning and critique abilities, which are transferable across a broad range of tasks. Hence, we believe that CRL works as a great complement to standard RL for LLM reasoning.

Theory · Learning Theory

Xuyang Chen, Fengzhuo Zhang, Keyu Yan, Lin Zhao

Actor–critic (AC) algorithms underpin many of today’s most successful reinforcement learning (RL) applications, yet their finite-time convergence in realistic settings remains largely underexplored. Existing analyses often rely on oversimplified formulations and are largely confined to linear function approximation. In practice, however, nonlinear approximations with deep neural networks dominate AC implementations, leaving a substantial gap between theory and practice. In this work, we provide the first finite-time analysis of single-timescale AC with deep neural network approximation in continuous state-action spaces. In particular, we consider the challenging time-average reward setting, where one needs to simultaneously control three highly-coupled error terms including the reward error, the critic error, and the actor error. Our novel analysis is able to establish convergence to a stationary point at a rate $\widetilde{\mathcal{O}}(T^{-1/2})$, where $T$ denotes the total number of iterations, thereby providing theoretical grounding for widely used deep AC methods. We substantiate these theoretical guarantees with experiments that confirm the proven convergence rate and further demonstrate strong performance on MuJoCo benchmarks.

Reinforcement Learning · Deep RL

Jiaxuan Gao, Wei Fu, Minyang Xie, Shusheng Xu, Chuyi He, Zhiyu Mei, Banghua Zhu, Yi Wu

Recent advancements in LLM-based agents have demonstrated remarkable capabilities in handling knowledge-intensive tasks using external tools. One representative example is search agent. Existing open-source search agents heavily rely on advanced commercial LLMs: they either collect trajectories from the larger, stronger models for supervised fine-tuning or directly use them as specialized tools. In this work, we develop ASearcher, a single-model search agent purely trained by reinforcement learning (RL) without using any commercial APIs for data or tools. Based on an RL-trained QwQ-32B model, ASearcher is capable of conducting complex reasoning, such as uncertainty analysis and conflict verification, and achieve comparable performances to commercial search agents. There are two key techniques to unlock such long-horizon information-seeking abilities: first, we design a two-staged agentic process to synthesize high-quality QA pairs as the training data for RL; second, we conduct large-scale long-horizon RL, allowing the agent to take up to 128 actions per rollout for sufficient exploration. In particular, after RL training, ASearcher achieved scores of GAIA 58.1, xBench 51.1, and Frames 74.5 using only basic search tools. Furthermore, ASearcher also demonstrates strong zero-shot transferability: ASearcher can be further augmented with an additional summary tool, which is supported by DeepSeek-V3, and test-time scaling, which aggregates the answer from 16 parallel rollouts. With both zero-shot enhancements, the performances of ASearcher further rise to 71.8, 75.0, and 83.4, respectively, outperforming OpenAI DeepResearch and Kimi-Researcher, suggesting the great potential of RL scaling for agentic tasks. We release all the code and data at an anonymous link. The model will be released after the review process.