论文检索

Deep Learning · Generative Models and Autoencoders

Yinghui He, Abhishek Panigrahi, Yong Lin, Sanjeev Arora

Language models often show little to no improvement (i.e., “saturation”) when trained via vanilla supervised fine-tuning (SFT) on data similar to what they saw in their training set (e.g., MATH). We introduce a new fine-tuning strategy, STAT, to train such a student model by using the metacognition ability of a stronger large language model (LLM) as the teacher. The teacher uses the task dataset to create a list of skills needed for the task, and then labels each data point with its required skills (Didolkar et al., 2024). By monitoring the student’s answers, the teacher creates a Missing-Skill-Profile for the student, tracking how often they failed to apply each skill in their responses. We use this idea to build a modified training set in one of two ways. In STAT-Sel, the teacher uses an existing set of training examples but adaptively reweights them according to the Missing-Skill-Profile. In STAT-Syn, the teacher synthesizes additional examples involving missing skills. Across extensive experiments on Llama and Qwen models, our methods yield improvements of up to 7.5% on MATH, whereas SFT provides only limited gains. Furthermore, STAT enhances performance on out-of-distribution benchmarks (e.g., AIME24/25, AMC23, etc.) by an average of 4.6%. Crucially, we find that STAT is complementary to RL via GRPO (Shao et al., 2024): after the model is improved using STAT to address skill gaps, GRPO continues to add further gains. We conclude that skill-targeted adaptive training should broadly improve current training pipelines.

Reinforcement Learning · Deep RL

Guojian Zhan, Letian Tao, Pengcheng Wang, Yixiao Wang, Yuxin Chen, Yiheng Li, Hongyang Li, Masayoshi Tomizuka, Shengbo Li

Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness and computational burden, which is typically controlled by the number of flow steps. In this work, we propose mean velocity policy (MVP), a new generative policy function that models the mean velocity field to achieve the fastest one-step action generation. To ensure its high expressiveness, an instantaneous velocity constraint (IVC) is introduced on the mean velocity field during training. We theoretically prove that this design explicitly serves as a crucial boundary condition, thereby improving learning accuracy and enhancing policy expressiveness. Empirically, our MVP achieves state-of-the-art success rates across several challenging robotic manipulation tasks from Robomimic and OGBench. It also delivers substantial improvements in training and inference speed over existing flow-based policy baselines.

Deep Learning · Everything Else

Tong Zheng, Hongming Zhang, Wenhao Yu, Xiaoyang Wang, He Xing, Runpeng Dai, Rui Liu, Huiwen Bao, Chengsong Huang, Heng Huang 等

Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains challenging. Existing methods mainly rely on supervised fine-tuning (SFT) over synthetic data, which encourages teacher-forced learning rather than exploration and generalization. To address this issue, we propose **Parallel-R1**, the first reinforcement learning (RL) framework that instills parallel thinking for complex real-world reasoning tasks. Our framework employs a progressive curriculum that addresses the cold-start problem in training parallel thinking with RL. We first use SFT on prompt-generated trajectories from easier tasks to instill the parallel thinking behavior, then transition to RL to explore and generalize this skill on harder problems. Experiments on various math benchmarks, including MATH, AMC23, and AIME, show that Parallel-R1 successfully elicits parallel thinking, leading to 8.4% accuracy improvements over the sequential thinking model trained directly on difficult tasks with RL. Further analysis reveals a distinct shift in the model's thinking patterns: in the early stage, it utilizes parallel thinking as an exploration strategy, while in the later stage, it employs this ability for multi-perspective verification. Most significantly, we validate parallel thinking as a **mid-training exploration scaffold**, where this intermediate phase unlocks a higher performance ceiling after RL, yielding a **42.9%** improvement over the sequential RL baseline.

Reinforcement Learning · Deep RL

Artyom Sorokin, Nazar Buzun, Aleksandr Anokhin, Egor VEDERNIKOV, Petr Anokhin, Mikhail Burtsev, Evgeny Burnaev

Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most existing RAG methods focus on single-step retrieval, which is often insufficient for answering complex questions that require multi-step search. Recently, multi-step retrieval approaches have emerged, typically involving the fine-tuning of small LLMs to perform multi-step retrieval. This type of fine-tuning is highly resource-intensive and does not enable the use of larger LLMs. In this work, we propose Q-RAG, a novel approach that fine-tunes the Embedder model for multi-step retrieval using reinforcement learning (RL). Q-RAG offers a competitive, resource-efficient alternative to existing multi-step retrieval methods for open-domain question answering and achieves state-of-the-art results on the popular long-context benchmarks BabiLong and RULER for contexts up to 10M tokens. Code is available at: https://github.com/griver/Q-RAG.

Reinforcement Learning · Deep RL

Johan S Obando Ceron, Walter Mayor, Samuel Lavoie, Scott Fujimoto, Aaron Courville, Pablo Samuel Castro

Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment parallelization; unfortunately, these can sometimes still require large number of environment interactions to achieve a desired level of performance. Noting that well-structured representations can improve the generalization and sample efficiency of deep reinforcement learning (RL) agents, we propose the use of simplicial embeddings: lightweight representation layers that constrain embeddings to simplicial structures. This geometric inductive bias results in sparse and discrete features that stabilize critic bootstrapping and strengthen policy gradients. When applied to FastTD3, FastSAC, and PPO, simplicial embeddings consistently improve sample efficiency and final performance across a variety of continuous- and discrete-control environments, without any loss in runtime speed.

Reinforcement Learning · Deep RL

Seungeun (Ross) Rho, Aaron Trinh, Danfei Xu, Sehoon Ha

Scaling unsupervised skill discovery algorithms to high-DoF agents remains challenging. As dimensionality increases, the exploration space grows exponentially, while the manifold of meaningful skills remains limited. Therefore, semantic meaningfulness becomes essential to effectively guide exploration in high-dimensional spaces. In this work, we present **Reference-Grounded Skill Discovery (RGSD)**, a novel algorithm that grounds skill discovery in a semantically meaningful latent space using reference data. RGSD first performs contrastive pretraining to embed motions on a unit hypersphere, clustering each reference trajectory into a distinct direction. This grounding enables skill discovery to simultaneously involve both imitation of reference behaviors and the discovery of semantically related diverse behaviors. On a simulated SMPL humanoid with $359$-D observations and $69$-D actions, RGSD successfully imitates skills such as walking, running, punching, and sidestepping, while also discover variations of these behaviors. In downstream locomotion tasks, RGSD leverages the discovered skills to faithfully satisfy user-specified style commands and outperforms imitation-learning baselines, which often fail to maintain the commanded style.

Reinforcement Learning · Deep RL

Silin Gao, Antoine Bosselut, Samy Bengio, Emmanuel Abbe

Recent studies have shown that large language models (LLMs), especially smaller ones, often lack robustness in grade school math (GSM) reasoning. In particular, they tend to experience performance drops when faced with distribution shifts, such as changes to numerical or nominal variables, or insertions of distracting clauses. A possible strategy to address this involves generating synthetic data to further "instantiate" reasoning problems on potential variations. In this work, we instead focus on the strategy of ``abstracting'' reasoning problems. This not only helps counteract distribution shifts but also facilitates the connection to symbolic tools for deriving solutions. Focusing on GSM, we find that this abstraction process is better acquired through reinforcement learning (RL) than just supervised fine-tuning, which often fails to produce faithful abstractions. Our method, AbstRaL---which promotes abstract reasoning in LLMs using RL on granular abstraction data---significantly mitigates performance degradation on recent GSM perturbation benchmarks. Besides, improving GSM robustness via AbstRaL is shown to also implicitly benefit LLMs' capabilities on OOD mathematical and general reasoning tasks, indicating that abstract thinking broadly enables better generalizability.

Reinforcement Learning · Deep RL

Som Sagar, Jiafei Duan, Sreevishakh Vasudevan, Yifan Zhou, Heni Ben Amor, Dieter Fox, Ransalu Senanayake

Robot manipulation policies, while central to the promise of physical AI, are highly vulnerable in the presence of external variations in the real world. Diagnosing these vulnerabilities is hindered by two key challenges: (i) the relevant variations to test against are often unknown, and (ii) direct testing in the real world is costly and unsafe. We introduce a framework that tackles both issues by learning a separate deep reinforcement learning (deep RL) policy for vulnerability prediction through virtual runs on a continuous vision-language embedding trained with limited success-failure data. By treating this embedding space, which is rich in semantic and visual variations, as a potential field, the policy learns to move toward vulnerable regions while being repelled from success regions. This vulnerability prediction policy, trained on virtual rollouts, enables scalable and safe vulnerability analysis without expensive physical trials. By querying this policy, our framework builds a probabilistic vulnerability-likelihood map. Experiments across simulation benchmarks and a physical robot arm show that our framework uncovers up to 23\% more unique vulnerabilities than state-of-the-art vision-language baselines, revealing subtle vulnerabilities overlooked by heuristic testing. Additionally, we show that fine-tuning the manipulation policy with the vulnerabilities discovered by our framework improves manipulation performance with much less fine-tuning data.

Reinforcement Learning · Deep RL

Ku Onoda, Paavo Parmas, Manato Yaguchi, Yutaka Matsuo

In policy gradient reinforcement learning, access to a differentiable model enables 1st-order gradient estimation that accelerates learning compared to relying solely on derivative-free 0th-order estimators. However, discontinuous dynamics cause bias and undermine the effectiveness of 1st-order estimators. Prior work addressed this bias by constructing a confidence interval around the REINFORCE 0th-order gradient estimator and using these bounds to detect discontinuities. However, the REINFORCE estimator is notoriously noisy, and we find that this method requires task-specific hyperparameter tuning and has low sample efficiency. This paper asks whether such bias is the primary obstacle and what minimal fixes suffice. First, we re-examine standard discontinuous settings from prior work and introduce DDCG, a lightweight test that switches estimators in nonsmooth regions; with a single hyperparameter, DDCG achieves robust performance and remains reliable with small samples. Second, on differentiable robotics control tasks, we present IVW-H, a per-step inverse-variance implementation that stabilizes variance without explicit discontinuity detection and yields strong results. Together, these findings indicate that while estimator switching improves robustness in controlled studies, careful variance control often dominates in practical deployments.

Reinforcement Learning · Deep RL

Wei Huang, Yi Ge, Shuai Yang, Yicheng Xiao, Huizi Mao, Yujun Lin, Hanrong Ye, Sifei Liu, Ka Chun Cheung, Hongxu (Danny) Yin 等

We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs). While RL is essential for LLMs' reasoning capabilities, it is resource-intensive, requiring substantial GPU memory and long rollout duration. QeRL addresses these issues by combining NVFP4 quantization with Low-Rank Adaptation (LoRA), accelerating rollout phase of RL while reducing memory overhead. Beyond efficiency, our findings show that quantization noise increases policy entropy, enhancing exploration in LoRA-based RL, and enabling the discovery of better strategies during RL. To further optimize exploration, QeRL introduces an Adaptive Quantization Noise (AQN) mechanism, which dynamically adjusts noise throughout training. Experiments demonstrate that QeRL delivers over 1.5× speedup in the rollout phase compared to QLoRA, and around 1.3× speedup compared to BF16 LoRA in 7B model. Moreover, this is the first framework to enable RL training of a 32B LLM on a single H100 80GB GPU, while delivering overall speedups for RL training. It also achieves faster reward growth and higher final accuracy than 16-bit LoRA and QLoRA, while matching the performance of full-parameter fine-tuning on mathematical benchmarks such as GSM8K (90.8%) and MATH 500 (77.4%) in the 7B model. These results establish QeRL as an efficient and effective framework for RL training in LLMs.

Reinforcement Learning · Deep RL

Aditya Ellendula, Yi Wang, Minh Nguyen, Chandrajit Bajaj

We present GRL-SNAM, a geometric reinforcement learning framework for Simultaneous Navigation and Mapping in unknown environments. GRL-SNAM differs from traditional SLAM and other reinforcement learning methods by relying exclusively on local sensory observations without constructing a global map. Our approach formulates navigation and mapping as coupled dynamics on generalized Hamiltonian manifolds: sensory inputs are translated into local energy landscapes that encode reachability, obstacle barriers, and deformation constraints, while policies for sensing, planning, and reconfiguration evolve stagewise under Differential Policy Optimization. A reduced Hamiltonian serves as an adaptive score function, updating kinetic/potential terms, embedding barrier constraints, and continuously refining trajectories as new local information arrives. We evaluate GRL-SNAM on 2D deformable navigation tasks, where a hyperelastic robot learns to squeeze through narrow gaps, detour around obstacles, and generalize to unseen environments. We compare our method against local reactive baselines (PF, CBF, staged DWA), global A* references (rigid, clearance-aware), and deep RL baselines (PPO, TRPO, SAC) under identical stagewise sensing constraints. GRL-SNAM achieves strong path quality while using the minimal map coverage, preserves clearance, and generalizes to unseen layouts. This demonstrates that our Hamiltonian-structured RL framework enables high-quality navigation through minimal exploration via local energy refinement rather than global mapping.

Reinforcement Learning · Deep RL

Artyom Sorokin, Nazar Buzun, Aleksandr Anokhin, Egor VEDERNIKOV, Petr Anokhin, Mikhail Burtsev, Evgeny Burnaev

Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most existing RAG methods focus on single-step retrieval, which is often insufficient for answering complex questions that require multi-step search. Recently, multi-step retrieval approaches have emerged, typically involving the fine-tuning of small LLMs to perform multi-step retrieval. This type of fine-tuning is highly resource-intensive and does not enable the use of larger LLMs. In this work, we propose Q-RAG, a novel approach that fine-tunes the Embedder model for multi-step retrieval using reinforcement learning (RL). Q-RAG offers a competitive, resource-efficient alternative to existing multi-step retrieval methods for open-domain question answering and achieves state-of-the-art results on the popular long-context benchmarks BabiLong and RULER for contexts up to 10M tokens. Code is available at: https://github.com/griver/Q-RAG.

Deep Learning · Algorithms

Aayush Karan, Yilun Du

Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this paradigm, much of the literature has been devoted to disentangling truly novel behaviors that emerge during RL but are not present in the base models. In our work, we approach this question from a different angle, instead asking whether comparable reasoning capabilities can be elicited from base models at inference time by pure sampling, without any additional training. Inspired by Markov chain Monte Carlo (MCMC) techniques for sampling from sharpened distributions, we propose a simple iterative sampling algorithm leveraging the base models' own likelihoods. Over different base models, we show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL on a wide variety of single-shot tasks, including MATH500, HumanEval, and GPQA. Moreover, our sampler avoids the collapse in diversity over multiple samples that is characteristic of RL-posttraining. Crucially, our method does not require training, curated datasets, or a verifier, suggesting broad applicability beyond easily verifiable domains.

Reinforcement Learning · Deep RL

Thomas Rupf, Marco Bagatella, Marin Vlastelica, Andreas Krause

Behavior Foundation Models (BFMs) are capable of retrieving high-performing policy for any reward function specified directly at test-time, commonly referred to as zero-shot reinforcement learning (RL). While this is a very efficient process in terms of compute, it can be less so in terms of data: as a standard assumption, BFMs require computing rewards over a non-negligible inference dataset, assuming either access to a functional form of rewards, or significant labeling efforts. To alleviate these limitations, we tackle the problem of task inference purely through interaction with the environment at test-time. We propose OpTI-BFM, an optimistic decision criterion that directly models uncertainty over reward functions and guides BFMs in data collection for task inference. Formally, we provide a regret bound for well- trained BFMs through a direct connection to upper-confidence algorithms for linear bandits. Empirically, we evaluate OpTI-BFM on established zero-shot benchmarks, and observe that it enables successor-features-based BFMs to identify and optimize an unseen reward function in a handful of episodes with minimal compute overhead.

Reinforcement Learning · Deep RL

Siyuan Wang, Gaokai Zhang, Li Lyna Zhang, Ning Shang, Fan Yang, Dongyao Chen, Mao Yang

Reasoning over long contexts is essential for large language models. While reinforcement learning (RL) enhances short-context reasoning by inducing "Aha" moments in chain-of-thought, the advanced thinking patterns required for long-context reasoning remain largely unexplored, and high-difficulty RL data are scarce. In this paper, we introduce LoongRL, a data-driven RL method for advanced long-context reasoning. Central to LoongRL is KeyChain, a synthesis approach that transforms short multi-hop QA into high-difficulty long-context tasks by inserting UUID chains that hide the true question among large collections of distracting documents. Solving these tasks requires the model to trace the correct chain step-by-step, identify the true question, retrieve relevant facts and reason over them to answer correctly. RL training on KeyChain data induces an emergent plan–retrieve–reason–recheck reasoning pattern that generalizes far beyond training length. Models trained at 16K effectively solve 128K tasks without prohibitive full-length RL rollout costs. On Qwen2.5-7B and 14B, LoongRL substantially improves long-context multi-hop QA accuracy by +23.5% and +21.1% absolute gains. The resulting LoongRL-14B reaches a score of 74.2, rivaling much larger frontier models such as o3-mini (74.5) and DeepSeek-R1 (74.9). It also improves long-context retrieval, passes all 128K needle-in-a-haystack stress tests, and preserves short-context reasoning capabilities. Code is available at https://loongrl.github.io.

Reinforcement Learning · Deep RL

Florent Delgrange, Raphael Avalos, Willem Röpke

Safe policy improvement (SPI) offers theoretical control over policy updates, yet existing guarantees largely concern offline, tabular reinforcement learning (RL). We study SPI in general online settings, when combined with world model and representation learning. We develop a theoretical framework showing that restricting policy updates to a well-defined neighborhood of the current policy ensures monotonic improvement and convergence. This analysis links transition and reward prediction losses to representation quality, yielding online, ''deep'' analogues of classical SPI theorems from the offline RL literature. Building on these results, we introduce DeepSPI, a principled on-policy algorithm that couples local transition and reward losses with regularised policy updates. On the ALE-57 benchmark, DeepSPI matches or exceeds strong baselines, including PPO and DeepMDPs, while retaining theoretical guarantees.

Deep Learning · Generative Models and Autoencoders

Yuchen Yan, Jin Jiang, Zhenbang Ren, Yijun Li, Xudong Cai, Yang Liu, Xin Xu, Mengdi Zhang, Jian Shao, Yongliang Shen 等

Large reasoning models such as OpenAI o1 and DeepSeek-R1 have demonstrated remarkable performance in complex reasoning tasks. A critical component of their training is the incorporation of reference-based reward systems within reinforcement learning (RL), where model outputs are evaluated against ground truth references. However, existing reward benchmarks focus on preference comparisons between responses rather than evaluating verification against ground truth references, leaving a critical gap in our ability to evaluate verification systems used in reasoning model training. In this paper, we introduce VerifyBench and its challenging variant VerifyBench-Hard, two benchmarks specifically designed to assess reference-based reward systems. These benchmarks are constructed through meticulous data collection and curation, followed by careful human annotation to ensure high quality. Our comprehensive evaluation reveals that while larger model-based verifiers show promise on standard cases, all current systems demonstrate substantial room for improvement on challenging instances. Through systematic analysis of performance patterns across reasoning tasks and error categories, we provide insights for advancing reference-based reward systems. These benchmarks establish a standardized framework for improving verification accuracy, ultimately enhancing reasoning capabilities in models trained via RL.

Reinforcement Learning · Deep RL

Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang, Henry Li, Kaiyan Zhang, Che Jiang, Youbang Sun, Ermo Hua, Yuxin Zuo, Xingtai Lv 等

We propose FlowRL: matching the full reward distribution via flow balancing instead of solely maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced reasoning models adopt reward-maximizing methods (e.g., PPO and GRPO), which tend to over-optimize dominant reward signals while neglecting less frequent but valid reasoning paths, thus reducing diversity. In contrast, we transform scalar rewards into a normalized target distribution using a learnable partition function, and then minimize the reverse KL divergence between the policy and the target distribution. We implement this idea as a flow-balanced optimization method that promotes diverse exploration and generalizable reasoning trajectories. We conduct experiments on both math and code reasoning tasks: FlowRL achieves a significant average improvement of $10.0\%$ over GRPO and $5.1\%$ over PPO on math benchmarks, and performs consistently better on code reasoning tasks. These results highlight reward distribution-matching as a key step toward efficient exploration and diverse reasoning in LLM reinforcement learning.

Reinforcement Learning · Deep RL

Yunyue Wei, Chenhui Zuo, Yanan Sui

Controlling high-dimensional biological and robotic systems is challenging due to expansive state–action spaces, where effective exploration is critical. Commonly used exploration strategies in reinforcement learning are largely undirected with sharp degradation as action dimensionality grows. Many existing methods resort to dimensionality reduction, which constrains policy expressiveness and forfeits system flexibility. We introduce Q-guided Flow Exploration (Qflex), a scalable reinforcement learning method that conducts exploration directly in the native high-dimensional action space. During training, Qflex traverses actions from a learnable source distribution along a probability flow induced by the learned value function, aligning exploration with task-relevant gradients rather than isotropic noise. Our proposed method substantially outperforms representative online reinforcement learning baselines across diverse high-dimensional continuous-control benchmarks. Qflex also successfully controls a whole-body human musculoskeletal model to perform agile, complex movements, demonstrating superior scalability and sample efficiency in very high-dimensional settings. Our results indicate that value-guided flows offer a principled and practical route to exploration at scale.

Haozhe Wang, Qixin Xu, Che Liu, Junhong Wu, Fangzhen Lin, Wenhu Chen

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling phenomena like ``aha moments", ``length-scaling'' and entropy dynamics are not disparate occurrences but hallmarks of an emergent reasoning hierarchy, akin to the separation of high-level strategic planning from low-level procedural execution in human cognition. We uncover a compelling two-phase dynamic: initially, a model is constrained by procedural correctness and must improve its low-level skills. The learning bottleneck then decisively shifts, with performance gains being driven by the exploration and mastery of high-level strategic planning. This insight exposes a core inefficiency in prevailing RL algorithms like GRPO, which apply optimization pressure agnostically and dilute the learning signal across all tokens. To address this, we propose Hierarchy-Aware Credit Assignment (HICRA), an algorithm that concentrates optimization efforts on high-impact planning tokens. Our extensive experiments validate that HICRA significantly outperforms strong baselines, and offer deep insights into how reasoning advances through the lens of strategic exploration.