论文检索

Deep Learning · Generative Models and Autoencoders

Jaemoo Choi, Yuchen Zhu, Wei Guo, Petr Molodyk, Bo Yuan, Jinbin Bai, Yi Xin, Molei Tao, Yongxin Chen

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide a systematic analysis of the RL design space by disentangling three factors: i) policy-gradient objectives, ii) likelihood estimators, and iii) rollout sampling schemes. We show that adopting an evidence lower bound (ELBO) based model likelihood estimator, computed only from the final generated sample, is the dominant factor enabling effective, efficient, and stable RL optimization, outweighing the impact of the specific policy-gradient loss functional. We validate our findings across multiple reward benchmarks using SD 3.5 Medium, and observe consistent trends across all tasks. Our method improves the GenEval score from $0.24$ to $0.95$ in $90$ GPU hours, which is $4.6\times$ more efficient than FlowGRPO and $2\times$ more efficient than the SOTA method DiffusionNFT without reward hacking.

Deep Learning · Large Language Models

Rulin Shao, Stella Li, Rui Xin, Scott Geng, Yiping Wang, Sewoong Oh, Simon Du, Nathan Lambert, Sewon Min, Ranjay Krishna 等

We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain language models even with spurious rewards that have little, no, or outright negative correlation with the correct answer. For example, RLVR training with GRPO improves MATH-500 performance for Qwen2.5-Math-7B in absolute points by 21.4% using randomly assigned rewards, nearly matching the 29.1% gained with ground truth rewards. To explain this counterintuitive observation, we show that GRPO exhibits a clipping bias arising from the clip term, which can amplify high-prior behaviors learned during pre-training even without informative rewards. As a case study, we identify one such high-prior behavior for Qwen2.5-Math models, which we term code reasoning---reasoning in code without actual code execution; code reasoning frequency increases from 65% to over 90% with spurious rewards. However, the presence of such amplifiable behaviors is highly model-dependent. In practice, spurious rewards that are effective for Qwen models often fail to produce gains for other model families, such as Llama3 or OLMo2. Our results highlight the importance of validating RL methods across diverse models rather than relying on a single de facto choice: large performance gains can arise on Qwen models even from random rewards that do not reflect genuine capability improvements.

Deep Learning · Large Language Models

Rosie Zhao, Anshul Shah, Xiaoyu Zhu, Xinke Deng, Zhongyu Jiang, Yang Yang, Joerg Liebelt, Arnab Kumar Mondal

Reinforcement learning (RL) fine-tuning is now widely used to improve LLM reasoning, and recent work has begun extending it to vision-language models (VLMs). While RL-tuned VLMs can improve visual reasoning benchmark performance, they can still suffer from weak visual grounding, hallucinations, and over-reliance on textual cues. We show that simple, controlled textual perturbations—misleading captions or incorrect chain-of-thought (CoT) traces—cause substantial drops in robustness and confidence, and that these effects are more pronounced when CoT consistency is taken into account across open-source multimodal reasoning models. Entropy-based metrics further show that these perturbations reshape model uncertainty on the correct option, exposing model-specific trends in miscalibration. To better understand these vulnerabilities, we further analyze RL fine-tuning dynamics and uncover an accuracy–faithfulness trade-off: fine-tuning raises benchmark accuracy, but can simultaneously erode the reliability of the accompanying CoT and its robustness to contextual shifts. Although adversarial augmentation improves robustness, it does not by itself prevent faithfulness drift. Incorporating a faithfulness-aware reward can restore alignment between answers and reasoning, but when paired with augmentation, training risks collapsing onto shortcut strategies and robustness remains elusive. Together, these findings highlight the limitations of accuracy-only evaluations and motivate training and assessment protocols that jointly emphasize correctness, robustness, and the faithfulness of visually grounded reasoning.

Deep Learning · Large Language Models

Xian Wu, Kaijie Zhu, Ying Zhang, Lun Wang, Wenbo Guo

Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking. In LLM reasoning, existing works also explore various solutions for learning effective process reward models (PRM) with or without the help of an expert policy. However, existing methods either rely on strong assumptions about the expert policies (e.g., requiring their reward functions) or suffer intrinsic limitations (e.g., entropy collapse), resulting in weak PRMs or limited generalizability. In this paper, we introduce rePIRL, an inverse RL-inspired framework that learns effective PRMs with minimal assumptions about expert policies. Specifically, we design a dual learning process that updates the policy and the PRM interchangeably. Our learning algorithm has customized techniques to address the challenges of scaling traditional inverse RL to LLMs. We theoretically show that our proposed learning framework can unify both online and offline PRM learning methods, justifying that rePIRL can learn PRMs with minimal assumptions. Empirical evaluations on standardized math and coding reasoning datasets demonstrate the effectiveness of rePIRL over existing methods. We further show the application of our trained PRM in test-time training, test-time scaling, and providing an early signal for training hard problems. Finally, we validate our training recipe and key design choices via a detailed ablation study.

Reinforcement Learning · Deep RL

Hao Wang, Lei Sha, Jie Zhang

Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct answers are obtained through inconsistent reasoning. We propose StepCodeReasoner, a framework that introduces explicit intermediate execution-state supervision. By automatically inserting structured print-based execution-trace anchors into code, the model is trained to predict runtime states at each step, transforming code reasoning into a verifiable, stepwise execution modeling problem. Building on this execution-aware method, we introduce Bi-Level GRPO}, a reinforcement learning algorithm for structured credit assignment at two levels: inter-trajectory, comparing alternative execution paths, and intra-trajectory, rewarding intermediate accuracy based on its impact on downstream correctness. Extensive experiments demonstrate that StepCodeReasoner achieves SOTA performance in code reasoning. In particular, our 7B model achieves 91.1\% on CRUXEval and 86.5\% on LiveCodeBench, outperforming the CodeReasoner-7B baseline (86.0\% and 77.7\%) and GPT-4o (85.6\% and 75.1\%). Furthermore, on the execution-trace benchmark REval, our model scores 82.9\%, outperforming baseline CodeReasoner-7B (72.3\%), its 14B counterpart (81.1\%), and GPT-4o (77.3\%). Additionally, our approach also improves code generation performance, demonstrating that explicit execution modeling enhances both code reasoning and code generation.

Reinforcement Learning · Deep RL

Zhibin Duan, Guowei Rong, Zhuo Li, Bo Chen, Mingyuan Zhou, Dandan Guo

Reward models learned from human preferences are central to aligning large language models (LLMs) via reinforcement learning from human feedback, yet they are often vulnerable to reward hacking due to noisy annotations and systematic biases such as response length or style. We propose Bayesian Non-Negative Reward Model (BNRM), a principled reward modeling framework that integrates non-negative factor analysis into Bradley–Terry (BT) preference model. BNRM represents rewards through a sparse, non-negative latent factor generative process that operates at two complementary levels: instance-specific latent variables induce disentangled reward representations, while sparsity over global latent factors acts as an implicit debiasing mechanism that suppresses spurious correlations. Together, this disentanglement-then-debiasing structure enables robust uncertainty-aware reward learning. To scale BNRM to modern LLMs, we develop an amortized variational inference network conditioned on deep model representations, allowing efficient end-to-end training. Extensive empirical results demonstrate that BNRM substantially mitigates reward over-optimization, improves robustness under distribution shifts, and yields more interpretable reward decompositions than strong baselines.

Reinforcement Learning · Deep RL

Jing-Cheng Pang, Sun Liu, Chang Zhou, Xian Tang, Haichuan Ma, KUN JIANG, Jianlong Wang, Kai Zhang, Sijie Wu, Haoran Cai 等

Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is curriculum learning, which pre-orders training samples based on metrics like difficulty to improve learning efficiency compared to a random sampling strategy. However, most existing methods for LLM fine-tuning rely on a static curriculum, designed prior to training, which lacks adaptability to the model's evolving needs during fine-tuning. To address this, we propose EDCO, a novel framework based on two key concepts: \textit{inference entropy} and \textit{dynamic curriculum orchestration}. Inspired by recent findings that maintaining high answer entropy benefits long-term reasoning gains, EDCO prioritizes samples with high inference entropy in a continuously adapted curriculum. EDCO integrates three core components: an efficient entropy estimator that uses prefix tokens to approximate full-sequence entropy, an entropy-based curriculum generator that selects data points with the highest inference entropy, and an LLM trainer that optimizes the model on the selected curriculum. Comprehensive experiments in communication, medicine and law domains, EDCO outperforms traditional curriculum strategies for fine-tuning Qwen3-4B and Llama3.2-3B models under supervised and reinforcement learning settings. Furthermore, the proposed efficient entropy estimation reduces computational time by 83.5\% while maintaining high accuracy.

Reinforcement Learning · Deep RL

Arip Asadulaev, Maksim Bobrin, Salem Lahlou, Dmitry V. Dylov, Fakhri Karray, Martin Takac

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function overestimation bias. These issues become even more noticeable in *zero-shot* reinforcement learning, where an agent trained on reward-free data must adapt to new tasks at test time without additional training. In this work, we address the off-policy problem in a zero-shot setting by discovering a theoretical connection of successor measures to stationary density ratios. Using this insight, our algorithm can infer optimal importance sampling ratios, effectively performing a stationary distribution correction with an optimal policy *for any task on the fly*. We benchmark our method in motion tracking tasks on SMPL Humanoid, continuous control on ExoRL, and for the long-horizon OGBench tasks. Our technique seamlessly integrates into forward-backward representation frameworks and enables *fast-adaptation* to new tasks in a *raining-free* regime. More broadly, this work bridges off-policy learning and zero-shot adaptation, offering benefits to both research areas.

Deep Learning · Other Representation Learning

Arip Asadulaev, Rayan Banerjee, Fakhri Karray, Martin Takac

Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a network’s depth, allowing it to compactly emulate the capacity of larger models. However, the performance of recursively added layers remains behind the capabilities of one‑pass models with the same feed-forward depth. This means that in the looped version, not every recursive step effectively contributes to depth. This raises the question: when and why does latent reasoning improve performance, and when does it result in dead compute? In our work, we analyze the algorithms that latent reasoning provides answer to this question. We show that latent reasoning can be formalized as a classifier‑free guidance and policy improvement algorithm. Building on these insights, we propose to use a training schemes from RL and diffusion methods for latent reasoning modles. Using the Tiny Recursive Model as our testbed, we show that with our modifications we can avoid dead compute steps and reduce the total number of forward passes by 18× while maintaining performance. Broadly speaking, we show how a policy improvement perspective on recursive steps can explain model behavior and provide insights for further improvements.

Reinforcement Learning · Deep RL

Xingyu Jiang, Yuheng Pan, Mukang You, Xiuhui Zhang, Ning Gao, Guanwei Yan, Hao Li, Yue Deng

Model-based reinforcement learning aims to construct world models for efficient sampling. Current mainstream algorithms can be broadly categorized into two paradigms: maximum likelihood and value-aware world models. The former employs structured Recurrent/Transformer State-Space Models to capture environmental dynamics but overlooks task-relevant features. The latter prioritizes decision-critical states but suffers from sub-optimal performance. While recent efforts have sought to integrate these approaches, they typically rely on auxiliary modules or heavy external priors that significantly increase computational complexity. In this work, we propose a Value-Aligned World Model, a minimalist framework designed to synergize these two paradigms with negligible overhead. Specifically, We introduce an intrinsic latent-space value-alignment regularization that compels the world model to prioritize task-relevant features while maintaining the structural integrity of stochastic dynamics. To ensure stable optimization, we develop an adaptive weighting mechanism that acts as a self-regulating curriculum, balancing reconstruction fidelity with decision-making utility. Extensive experiments on Atari 100k and DeepMind Control benchmarks demonstrate that our algorithm consistently boosts existing methods with minimal added code and computational overhead. Code is available at supplementary material.

Deep Learning · Large Language Models

Lovish Madaan, Aniket Didolkar, Suchin Gururangan, John Quan, Ruan Silva, Russ Salakhutdinov, Manzil Zaheer, Sanjeev Arora, Anirudh Goyal

Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length, token/compute cost, and answer latency. We ask: Can current models leverage their metacognition to provide other combinations on this Pareto frontier, e.g., better accuracy with lower context length and/or latency? Abstractly, we view the model as an improvement operator on its own "thoughts" with a continuum of possible strategies. We identify an interesting inference family Parallel-Distill-Refine (PDR), which performs the following: (i) generate diverse drafts in parallel; (ii) distill them into a bounded, textual workspace; and (iii) refine conditioned on this workspace, producing an output that seeds the next round. Importantly, context length (hence compute cost) is controllable via degree of parallelism, and is no longer conflated with the total number of generated tokens. We report PDR instantiations of current models that give better accuracy than long CoT while incurring lower latency. Setting degree of parallelism to 1 yields an interesting subcase, Sequential Refinement (SR) (iteratively improve a single candidate answer) which provides performance superior to long CoT. Success of such model orchestrations raises the question whether further training could shift the Pareto frontier. To this end, we train an 8B thinking model with Reinforcement Learning (RL) to make it consistent with PDR as the inference method. On math tasks with verifiable answers, iterative pipelines surpass single-pass baselines at matched sequential budgets, with PDR delivering the largest gains (e.g., +11% on AIME 2024 and +9% on AIME 2025).

Theory · Deep Learning

Yu Huang, Zixin Wen, Yuejie Chi, Yuting Wei, Aarti Singh, Yingbin LIANG, Yuxin Chen

Reinforcement Learning with Verifiable Rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier to extended reasoning. To understand this, we develop a theory of the training dynamics of RL for transformers on compositional reasoning tasks. Our theory characterizes how the effectiveness of RLVR is governed by the smoothness of the difficulty spectrum. When data contains abrupt discontinuities in difficulty, learning undergoes grokking-type phase transitions, giving rise to prolonged plateaus before progress recurs. In contrast, a smooth difficulty spectrum leads to a *relay effect*: stable gradient signals on easier problems elevate the model's capabilities to the point where harder ones become tractable, resulting in steady and continuous learning. Our theory explains how RLVR can improve performance at the edge of competence, and suggests that appropriately designed data mixtures can yield scalable gains. As a technical contribution, our analysis develops and adapts tools from Fourier analysis on finite groups to our setting. We validate the predicted mechanisms empirically via synthetic experiments.

Deep Learning · Large Language Models

Harman Singh, Xiuyu Li, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan, Xiaoxia (Shirley) Wu, Junxiong Wang, Alpay Ariyak, Qingyang Wu, Samir Khaki 等

Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, for example by independently sampling and aggregating multiple solutions, results in significantly better task outcomes. However, a critical bottleneck is _verification_: sampling is only effective if correct solutions can be reliably identified among candidates. While existing approaches typically evaluate candidates independently via scalar scoring, we demonstrate that models are substantially stronger at **pairwise self-verification**. Leveraging this insight, we introduce **V1**, a framework that unifies generation and verification through efficient pairwise ranking. V1 comprises two components: **V1-Infer**, an uncertainty-guided algorithm using a tournament-based ranking that dynamically allocates self-verification compute to candidate pairs whose relative correctness is most uncertain; and **V1-PairRL**, an RL framework that **jointly trains** a single model as both generator and pairwise self-verifier, ensuring the verifier adapts to the generator's evolving distribution. On code generation (LiveCodeBench, CodeContests) and math reasoning (AIME, HMMT) benchmarks, V1-Infer improves Pass@1 by up to 10\% over pointwise verification and outperforms recent test-time scaling methods while being significantly more efficient. Furthermore, V1-PairRL achieves 7-9\% test-time scaling gains over standard RL and pointwise joint training, and improves base Pass@1 by up to 8.7\% over standard RL.

Deep Learning · Large Language Models

白 寅岐, Xialiang Tong, Jie Wang, Hongyu Liu, Longdi Pan, Jiashuo Li, Zehao Wang, Jianye Hao, Mingxuan Yuan, Feng Wu

Asynchronous reinforcement learning (RL) has shown notable success in accelerating the post-training of large language models (LLMs). However, its decoupled data generation and training paradigm introduces a fundamental distributional mismatch between data generated by stale behavior policies and current policy, leading to unstable training and degraded performance. To address this challenge, we propose D-ARL, a **D**istribution-matched **A**synchronous **R**einforcement **L**earning framework that selects high-quality asynchronous samples whose distributions are well aligned with the current policy for policy optimization. Specifically, D-ARL maintains a replay buffer that collects samples from the most recent $K$ behavior policies and proposes a variance-guided metric to select distribution-matched data. During training, D-ARL introduces a multi-behavior policy optimization algorithm to leverage the multi-source nature of the selected samples for policy update. Experiments on six widely used reasoning benchmarks show that D-ARL outperforms state-of-the-art asynchronous methods, achieving an average improvement of 6.4\% in reasoning performance and 34.7\% in sample efficiency.

Applications · Language, Speech and Dialog

Wenxuan Huang, Yu Zeng, Qiuchen Wang, Zhen Fang, Shaosheng Cao, Zheng Chu, Qingyu Yin, Shuang Chen, Zhenfei Yin, Lin Chen 等

Multimodal large language models (MLLMs) have achieved remarkable success across a broad range of vision tasks. However, constrained by the capacity of their internal world knowledge, prior work has proposed augmenting MLLMs by ``reasoning-then-tool-call'' for visual and textual search engines to obtain substantial gains on tasks requiring extensive factual information. However, these approaches typically define multimodal search in a naive setting, assuming that a single full-level or entity-level image query and few text query suffices to retrieve the key evidence needed to answer the question, which is unrealistic in real-world scenarios with substantial visual noise. Moreover, they are often limited in the reasoning depth and search breadth, making it difficult to solve complex questions that require aggregating evidence from diverse visual and textual sources. Building on this, we propose Vision-DeepResearch, which proposes one new multimodal deep-research paradigm, i.e., performs multi-turn, multi-entity and multi-scale visual and textual search to robustly hit real-world search engines under heavy noise. Our Vision-DeepResearch supports dozens of reasoning steps and hundreds of engine interactions, while internalizing deep-research capabilities into the MLLM via cold-start supervision and RL training, resulting in a strong end-to-end multimodal deep-research MLLM. It substantially outperforming existing multimodal deep-research MLLMs, and workflows built on strong closed-source foundation model such as GPT-5, Gemini-2.5-pro and Claude-4-Sonnet.

Deep Learning · Large Language Models

Yuanzhe Shen, Zisu Huang, Zhengyuan Wang, Muzhao Tian, Zhengkang Guo, Chenyang Zhang, Shuaiyu Zhou, Zengjie Hu, Dailin Li, Kaimin Wang 等

As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evolving user behavior over long, multi-turn interactions. To bridge this gap, we introduce \textbf{TRIP-Bench}, a long-horizon benchmark grounded in realistic travel-planning scenarios. TRIP-Bench leverages real-world data, offers 18 curated tools and 40+ travel requirements, and supports automated evaluation. It includes splits of varying difficulty; the hard split emphasizes long and ambiguous interactions, style shifts, feasibility changes, and iterative version revision. Dialogues span up to 15 user turns, can involve 150+ tool calls, and may exceed 200k tokens of context. Experiments show that even advanced models achieve at most 50\% success on the easy split, with performance dropping below 10\% on hard subsets. We further propose GTPO, an online multi-turn reinforcement learning method with specialized reward normalization and reward differencing. Applied to Qwen2.5-32B-Instruct, GTPO improves constraint satisfaction and interaction robustness, outperforming Gemini-3-Pro in our evaluation. We expect TRIP-Bench to advance practical long-horizon interactive agents, and GTPO to provide an effective online RL recipe for robust long-horizon training.

Deep Learning · Large Language Models

Sijia Li, Yuchen Huang, Zifan LIU, Zijian LI, Jingjing Fu, Lei Song, Jiang Bian, Jun Zhang, Rui Wang

As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories are often too context-specific to transfer, while tool-level reuse ignores the context and environment. In this paper, we introduce a hybrid episodic–procedural memory strategy (H-EPM) that enables experience-induced self-evolution of multi-turn tool-use policies, by adaptively reusing partially overlapping successful experiences in both inference and training. Inspired by human episodic–procedural integration, we build a tool graph from accumulated trajectories, where recurring tool-to-tool dependencies capture procedural routines and each edge is augmented with a compact episodic summaries of relevant context. At inference, the agent dynamically balances episodic recall for contextual reasoning and procedural execution for routine steps. Beyond inference, H-EPM introduces a memory-guided reinforcement learning paradigm that directly addresses a core challenge in multi-turn agent RL: ineffective exploration over long trajectories. By biasing exploration toward historically successful tool transitions, H-EPM learns a stronger policy that generalizes during inference without relying on domain-specific experience collection. Experiments show that H-EPM consistently delivers substantial inference-time gains over strong baselines across multi-turn tool-use benchmarks, reaching up to 50\%+. It also boosts RL policy performance, achieving up to 40\%+ improvement on out-of-distribution tasks.

Deep Learning · Large Language Models

Jinhe Bi, Aniri -, Minglai Yang, Xingcheng Zhou, Wenke Huang, Sikuan Yan, Yujun Wang, Zixuan Cao, Michael Färber, Xun Xiao 等

Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceeds, the learning signal can collapse thus makes the training gain become marginal and ineffective. Specifically, a growing fraction of prompts' rollouts become advantage-degenerated: all the self-generated rollouts show verified-success, making the standard deviation over their rewards be zero; accordingly each rollout's advantage becomes degenerated (zero) as well. Given such rollouts' advantages, the policy-gradient for model optimization eventually vanishes, capping the training performance. We argue that some of these rollouts still contain valuable learning signals but unfortunately omitted with the existing RLVR methods. In this paper, inspired through analyzing the entropy pattern behind golden trajectories produced by external expert models, we propose EchoRL for better exploiting the advantage-degenerated rollouts to further improve the training performance. EchoRL is a lightweight module that first identifies an EchoClip from verified-success rollouts based on their step-level entropy values, and then feeds this clip back as an auxiliary supervision signal in the RL objective. Extensive experiments across 10 benchmarks, 5 LLM backbones, and 7 popular RLVR post-training methods demonstrate that EchoRL consistently improves RLVR post-training with minimal overhead.

Reinforcement Learning · Deep RL

Yuexuan Wang, Jingyuan Zhou, Kaidi Yang

Hierarchical decision-making frameworks are pivotal for addressing complex control tasks, enabling agents to decompose intricate problems into manageable subgoals. Despite their promise, existing hierarchical policies face critical limitations: (i) reinforcement learning (RL)-based methods struggle to guarantee strict constraint satisfaction, and (ii) optimal control (OC)-based approaches often rely on myopic and computationally prohibitive formulations. To reconcile these trade-offs, hierarchical RL-OC architectures have emerged as a promising paradigm. However, the formulation of the lower-level optimization within these frameworks remains underexplored, often relying on heuristic or myopic objectives. In this work, we propose a principled framework that systematically integrates upper-level goal abstraction with structured lower-level decision making. We adopt an inverse optimization approach to inform the structure of the lower-level problem from expert demonstrations, ensuring that the objective of the lower-level policy remains aligned with the overall long-term task goal. To validate the approach, our framework is evaluated on distinct decision making tasks: network-based resource allocation and continuous collision avoidance. Empirical results demonstrate that our method consistently outperforms strong baselines based on end-to-end RL, learning-augmented optimal control, and existing hierarchical RL approaches in both efficiency and decision quality.

Deep Learning · Large Language Models

Zhanhong Jiang

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly understood. Direct Preference Optimization (DPO) avoids explicit reward modeling but lacks convergence guarantees under federated and decentralized training, where communication constraints and non-IID preferences fundamentally alter optimization dynamics. We provide the first convergence and time-complexity analysis of DPO in distributed environments. Modeling personalized offline RL with user-specific preference distributions, we characterize the induced global optimization landscape. For federated DPO, we derive convergence rates that quantify the impact of client drift, communication frequency, and preference heterogeneity; for decentralized DPO, we establish convergence over general communication graphs and show how spectral connectivity governs optimization speed and consensus. Our results lay a theoretical foundation for scalable and privacy-preserving distributed preference optimization.