论文检索

Yuelin Zhang, Sijie Cheng, Chen Li, Zongzhao Li, Yuxin Huang, Yang Liu, Wenbing Huang

Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video understanding capabilities, while neglecting their complex reasoning potential. Furthermore, processing long video trajectories with VLMs is computationally prohibitive for real-world deployment. To address these challenges, we propose the Recurrent Reasoning Vision-Language Model (\text R ^2VLM). Our model features a recurrent reasoning framework that processes local video snippets iteratively, maintaining a global context through an evolving Chain of Thought (CoT). This CoT explicitly records task decomposition, key steps, and their completion status, enabling the model to reason about complex temporal dependencies. This design avoids the high cost of processing long videos while preserving essential reasoning capabilities. We train \text R ^2VLM on large-scale, automatically generated datasets from ALFRED and Ego4D. Extensive experiments on progress estimation and downstream applications, including progress-enhanced policy learning, reward modeling for reinforcement learning, and proactive assistance, demonstrate that \text R ^2VLM achieves strong performance and generalization, achieving a new state-of-the-art in long-horizon task progress estimation. The models and benchmarks are publicly available at https://huggingface.co/collections/zhangyuelin/r2vlm.

Yogesh Kulkarni, Pooyan Fazli

Multimodal reasoning over long-horizon video is challenging due to the need for precise spatiotemporal fusion and alignment across modalities. While recent methods such as Group Relative Policy Optimization (GRPO) have shown promise in this domain, they suffer from three key limitations: (1) data inefficiency from their on-policy design, (2) a vanishing advantage problem, where identical or near-identical rewards within a group eliminate the learning signal by producing zero-valued advantages, and (3) uniform credit assignment that fails to emphasize critical reasoning steps. We introduce AVATAR (Audio-Video Agent for Alignment and Reasoning, a framework that addresses these limitations through two core components: (1) an off-policy training architecture that improves sample efficiency and resolves vanishing advantages by reusing past experiences with greater reward diversity, and (2) Temporal Advantage Shaping (TAS), a credit assignment strategy that emphasizes early (planning) and late (synthesis) reasoning phases. AVATAR achieves strong performance across various benchmarks, outperforming the Qwen2.5-Omni baseline by +5.4 on MMVU, +4.9 on OmniBench, and +4.5 on Video-Holmes. Furthermore, it surpasses standard GRPO by +3.7 on OmniBench and +1.9 on Video-Holmes, while demonstrating 5 times sample efficiency, requiring 80 fewer generated completions to reach target performance.

Chengjie Fan, Cong Pan, Zijian Liu, Ningzhong Liu, Jie Qin

Inspired by the general Vision-and-Language Navigation (VLN) task, aerial VLN has attracted widespread attention, owing to its significant practical value in applications such as logistics delivery and urban inspection. However, existing methods face several challenges in complex urban environments, including insufficient generalization to unseen scenes, suboptimal performance in long-range path planning, and inadequate understanding of spatial continuity. To address these challenges, we propose HTNav, a new collaborative navigation framework that integrates Imitation Learning (IL) and Reinforcement Learning (RL) within a hybrid IL-RL framework. This framework adopts a staged training mechanism to ensure the stability of the basic navigation strategy while enhancing its environmental exploration capability. By integrating a tiered decision-making mechanism, it achieves collaborative interaction between macro-level path planning and fine-grained action control. Furthermore, a map representation learning module is introduced to deepen its understanding of spatial continuity in open domains. On the CityNav benchmark, our method achieves state-of-the-art performance across all scene levels and task difficulties. Experimental results demonstrate that this framework significantly improves navigation precision and robustness in complex urban environments.

Yaolun Zhang, Ruohui Wang, Jiahao Wang, Yepeng Tang, Xuanyu Zheng, Haonan Duan, Hao Lu, Hanming Deng, Lewei Lu

Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames.Existing approaches typically treat MLLMs as passive recognizers, processing entire videos or uniformly sampled frames without adaptive reasoning.Recent agent-based methods introduce external tools, yet still depend on manually designed workflows and perception-first strategies, resulting in inefficiency on long videos. We present EVA, an Efficient Reinforcement Learning framework for End-to-End Video Agent, which enables planning-before-perception through iterative summary-plan-action-reflection reasoning.EVA autonomously decides what to watch, when to watch, and how to watch, achieving query-driven and efficient video understanding.To train such agents, we design a simple yet effective three-stage learning pipeline--comprising supervised fine-tuning (SFT), Kahneman-Tversky Optimization (KTO), and Group Relative Policy Optimization (GRPO)--that bridges supervised imitation and reinforcement learning.We further construct high-quality datasets for each stage, supporting stable and reproducible training.We evaluate EVA on six video understanding benchmarks, demonstrating its comprehensive capabilities. Compared with existing baselines, EVA achieves a substantial improvement of 6--12% over general MLLM baselines and a further 1--3% gain over prior adaptive agent methods.

Zehao Deng, Tianjie Ju, Zheng Wu, Zhuosheng Zhang, Gongshen Liu

The rapid development of large vision-language model (VLM) has greatly promoted the research of GUI agent. However, GUI agents still face significant challenges in handling long-horizon tasks. First, single-agent models struggle to balance high-level capabilities and low-level execution capability, facing prevalent issues of responsibility coupling and capability conflicts. Second, agents lack awareness of the task state, leading to progress loss in long-horizon tasks. To address these challenges, we propose a staged execution-feedback reinforcement learning algorithm. Unlike training a unified policy model, we focus on training high-level scheduling models. Specifically, we propose and train two agents: a Coordinator, responsible for the strategic planning and task decomposition; and a State Tracker, responsible for context compression and information management to maintain the task's state and coherence. Based on this, we built the Coordinator-Executor-State Tracker (CES) multi-agent framework, which can be integrated with any low-level Executor model, assisting the Executor in solving long-horizon tasks through task scheduling and state management. Experiments on long-horizon task benchmarks demonstrate that CES significantly enhances the system's planning and state management capabilities. Furthermore, analysis confirms that our trained high-level scheduling module is a generalizable, plug-and-play module that significantly enhances the long-horizon capabilities of various Executors.

Qiucheng Wu, Jing Shi, Simon Jenni, Kushal Kafle, Tianyu Wang, Shiyu Chang, Handong Zhao

Recent advances in multimodal large language models (MLLMs) have shown great potential for extending vision-language reasoning to professional tool-based image editing, enabling intuitive and creative editing. A promising direction is to use reinforcement learning (RL) to enable MLLMs to reason about and execute optimal tool-use plans within professional image-editing software. However, training remains challenging due to the lack of reliable, verifiable reward signals that can reflect the inherently subjective nature of creative editing. In this work, we introduce RetouchIQ, a framework that performs instruction-based executable image editing through MLLM agents guided by a generalist reward model. RetouchIQ interprets user-specified editing intentions and generates corresponding, executable Lightroom adjustments, bridging high-level aesthetic goals with precise parameter control. To move beyond conventional, rule-based rewards that compute similarity against a fixed reference image using handcrafted metrics, we propose a generalist reward model, an RL fine-tuned MLLM that evaluates edited results through a set of generated metrics on a case-by-case basis. Then, the reward model provides scalar feedback through multimodal reasoning, enabling reinforcement learning with high-quality, instruction-consistent gradients. We curate an extended dataset with 190k instruction-reasoning pairs and establish a new benchmark for instruction-based image editing. Experiments show that RetouchIQ substantially improves both semantic consistency and perceptual quality over previous MLLM-based and diffusion-based editing systems. Our findings demonstrate the potential of generalist reward-driven MLLM agents as flexible, explainable, and executable assistants for professional image editing.

Wei Fang, James R. Glass

LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests. These failures primarily stem from the disconnect between abstract user goals and technical documentation, and the limited capacity of fixed-size embeddings to model combinatorial tool compositions. To address these challenges, we propose ToolQP, a lightweight framework that models retrieval as iterative query planning. Instead of single-shot matching, ToolQP decomposes instructions into sub-tasks and dynamically generates queries to interact with the retriever, effectively bridging the semantic gap by targeting the specific sub-tasks required for composition. We train ToolQP using synthetic query trajectories followed by optimization with Reinforcement Learning with Verifiable Rewards (RLVR). Experiments demonstrate that ToolQP achieves state-of-the-art performance, exhibiting superior zero-shot generalization, robustness across diverse retrievers, and significant improvements in downstream agentic execution.

Xinmiao Yu, Liwen Zhang, Xiaocheng Feng, Pengjun Xie, Jingren Zhou, Bing Qin, Yong Jiang

Large Language Model(LLM)-based agents have shown strong capabilities in web information seeking, with reinforcement learning (RL) becoming a key optimization paradigm. However, planning remains a bottleneck, as existing methods struggle with long-horizon strategies. Our analysis reveals a critical phenomenon—plan anchor—where the first reasoning step disproportionately impacts downstream behavior in long-horizon web reasoning tasks. Current RL algorithms, fail to account for this by uniformly distributing rewards across the trajectory.To address this, we propose Anchor-GRPO, a two-stage RL framework that decouples planning and execution. In Stage 1, the agent optimizes its first-step planning using fine-grained rubrics derived from self-play experiences and human calibration. In Stage 2, execution is aligned with the initial plan through sparse rewards, ensuring stable and efficient tool usage. We evaluate Anchor-GRPO on four benchmarks: BrowseComp, BrowseComp-Zh, GAIA, and XBench-DeepSearch. Across models from 3B to 30B, Anchor-GRPO outperforms baseline GRPO and First-step GRPO, improving task success and tool efficiency. Notably, WebAnchor-30B achieves 46.0% pass@1 on BrowseComp and 76.4% on GAIA. Anchor-GRPO also demonstrates strong scalability, getting higher accuracy as model size and context length increase.

Jianpeng Zhou, Qisheng Hu, Jiahai Wang, Wenya Wang

Steering large language model (LLM) reasoning via high-level reasoning actions offers a promising approach to improve robustness and interpretability. However, existing action-based paradigms, ranging from training-free prompting to static plan retrieval or prediction, often fail to consistently outperform standard generation because their planners tend to degenerate into repetitive loops or fixed patterns. We propose PG-HAP (Policy-Guided High-Level Action Planning), a lightweight stepwise planner–executor framework that learns to select reasoning actions dynamically while keeping the executor LLM fully frozen. The planner is trained with reinforcement learning to optimize answer correctness. To prevent degeneration, we introduce two targeted mechanisms: (i) an Action-Dependency Logit Mask that enforces valid transitions to avoid redundancy, and (ii) an Action Diversity Reward that discourages mode collapse by promoting varied action sequences. Across mathematical and commonsense reasoning benchmarks, PG-HAP improves accuracy over strong baselines while producing less redundant, more adaptive trajectories. This demonstrates that learning high-level planning alone can substantially strengthen reasoning without expensive end-to-end model tuning.

Wenhao Li, Yuwei Yang, Xiaoqing Wu, Yufeng Han, Cunliang Kong, Yuzhuo Bai, Xin Cong, Maosong Sun

While Large Language Models (LLMs) demonstrate remarkable capabilities in open-ended creative generation, they notably struggle with Format-Constrained Generation tasks—such as poetry and lyrics—where strict adherence to multidimensional structural constraints (i.e., format, phonetics, and rhyme) is prerequisite to aesthetic value. Existing paradigms predominantly rely on unreliable prompting or rigid constrained decoding strategies; the former often fails to ensure compliance, while the latter compromises inference latency and disrupts the natural probability distribution, degrading generation quality. To bridge this gap, we establish CCP-Arena, a rigorous testbed for Chinese Classical Poetry, and proposeProgressive Structural Internalization (PSI) a novel framework designed to embed external constraints into the model’s intrinsic intuition. PSI initiates withStructural Scaffolding via Explicit Cognitive Planning, utilizing explicit template to provide a structural scaffold for subsequent generation. This is followed by a Cascaded Reinforcement Learning stage guided by a Holistic Reward Model, which optimizes for precise structural-semantic alignment. Extensive experiments demonstrate that PSI achieves state-of-the-art performance, surpassing baselines in both strict constraint adherence and literary aesthetics. Furthermore, mechanistic analysis confirms that our method effectively internalizes structural information into the model’s latent representations, offering a robust and efficient solution for constrained creative generation.

Shiyu Liu, Yongjing Yin, Jianhao Yan, Yunbo Tang, Qinggang Zhang, Bei Li, Xin Chen, Jingang Wang, Xunliang Cai, Jinsong Su

RL-based agentic search enables LLMs to solve complex questions via dynamic planning and external search. While this approach significantly enhances accuracy with agent policies optimized via large-scale reinforcement learning, we identify a critical gap in reliability: these agents fail to recognize their reasoning boundaries and rarely admit "I DON’T KNOW" even when evidence is insufficient or reasoning reaches its limit. The lack of reliability often leads to plausible but unreliable answers, introducing significant risks in many real-world scenarios. To this end, we propose Boundary-Aware Policy Optimization (BAPO), a novel RL framework designed to cultivate reliable boundary awareness without compromising accuracy. BAPO introduces two key components: (i) a group-based boundary-aware reward that encourages an IDK response only when the reasoning reaches its limit, and (ii) an adaptive reward modulator that strategically suspends this reward during early exploration, preventing the model from exploiting IDK as a shortcut. Extensive experiments on four benchmarks demonstrate that BAPO substantially enhances the overall reliability of agentic search.

Hongbo Bai, Yujin Zhou, Yile Wu, Chi-Min Chan, Pengcheng Wen, Kunhao Pan, Sirui Han, Yike Guo

Large Multimodal Models (LMMs) have achieved remarkable success in visual understanding, yet they struggle with knowledge-intensive queries involving long-tail entities or evolving information due to static parametric knowledge. Recent search-augmented approaches attempt to address this limitation, but existing methods rely on indiscriminate whole-image retrieval that introduces substantial visual redundancy and noise, and lack deep iterative reflection, limiting their effectiveness on complex visual queries. To overcome these challenges, we propose Glance-or-Gaze (GoG), a fully autonomous framework that shifts from passive perception to active visual planning. GoG introduces a Selective Gaze mechanism that dynamically chooses whether to glance at global context or gaze into high-value regions, filtering irrelevant information before retrieval. We design a dual-stage training strategy: Reflective GoG Behavior Alignment via supervised fine-tuning instills the fundamental GoG paradigm, while Complexity-Adaptive Reinforcement Learning further enhances the model’s capability to handle complex queries through iterative reasoning. Experiments across six benchmarks demonstrate state-of-the-art performance. Ablation studies confirm that both Selective Gaze and complexity-aware RL are essential for effective visual search. We will release our data and models for further exploration soon.

Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy, Aleksandr Panov, Alexey Skrynnik

We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language model to generate and refine high-level plans through a self-learning mechanism, reducing the need for manual dataset annotation. Our approach involves iterative co-training: an RL agent is trained to follow the generated plans, while the language model adapts and modifies these plans based on RL feedback and preferences. This creates a feedback loop where both the agent and the planner improve jointly. We validate our framework in environments with rich dynamics and stochasticity. Results show that SuperIgor agents adhere to instructions more strictly than baseline methods, while also demonstrating strong generalization to previously unseen instructions.

Luis Lara, Aristides Milios, ZhiHao Luo, Aditya Sharma, Ge Ya Luo, Christopher Beckham, Florian Golemo, Christopher Pal

An AI system for professional floor plan design must precisely control room dimensions and areas while respecting the desired connectivity between rooms and maintaining functional and aesthetic quality.Existing generative approaches focus primarily on respecting the requested connectivity between rooms, but do not support generating floor plans that respect numerical constraints. We introduce a text-based floor plan generation approach that fine-tunes a large language model (LLM) on real plans and then applies reinforcement learning with verifiable rewards (RLVR) to improve adherence to topological and numerical constraints while discouraging invalid or overlapping outputs.Furthermore, we design a set of constraint adherence metrics to systematically measure how generated floor plans align with user-defined constraints.Our model generates floor plans that satisfy user-defined connectivity and numerical constraints and outperforms existing methods on Realism, Compatibility, and Diversity metrics. Across all tasks, our approach achieves at least a 94% relative reduction in Compatibility compared with existing methods.Our results demonstrate that LLMs can effectively handle constraints in this setting, suggesting broader applications for text-based generative modeling.

Xiaolong Wei, Zerun Zhu, Simin Niu, Xingyu Zhang, Peiying Yu, Changxuan Xiao, Yuchen Li, Jicheng Yang, Zhejun Zhao, Chong Meng 等

A fundamental challenge in creative writing lies in reconciling the inherent tension between maintaining global coherence in long-form narratives and preserving local expressiveness in short-form texts. While long-context generation necessitates explicit macroscopic planning, short-form creativity often demands spontaneous, constraint-free expression. Existing alignment paradigms, however, typically employ static reward signals and rely heavily on high-quality supervised data, which is costly and difficult to scale. To address this, we propose UniCreative, a unified reference-free reinforcement learning framework. We first introduce AC-GenRM, an adaptive constraint-aware reward model that dynamically synthesizes query-specific criteria to provide fine-grained preference judgments. Leveraging these signals, we propose ACPO, a policy optimization algorithm that aligns models with human preferences across both content quality and structural paradigms without supervised fine-tuning and ground-truth references. Empirical results demonstrate that AC-GenRM aligns closely with expert evaluations, while ACPO significantly enhances performance across diverse writing tasks. Crucially, our analysis reveals an emergent meta-cognitive ability: the model learns to autonomously differentiate between tasks requiring rigorous planning and those favoring direct generation, validating the effectiveness of our direct alignment approach.

Xiang Li, Runhai Jiao, Ruifan Li, Dongnan Wu, Ruojiao Qiao, Lei Liu

Reinforcement learning, with its interpretable path reasoning, has emerged as a promising paradigm for multi-hop question answering over knowledge graphs. However, existing approaches suffer from two inherent limitations: (1) lacking effective intermediate guidance, agents often fall into aimless exploration when confronted with complex multi-hop questions; and (2) policy networks focus on local neighborhood information, making it difficult to anticipate the long-term consequences of decisions. To address these challenges, we propose a Progressive Planning and Reinforced Reasoning (PPRR) framework. Specifically, we introduce large language models as multi-hop reasoning planners, converting decomposed sub-question sequences into stepwise decision guidance and thereby granting the agent human-like, step-by-step problem-solving capabilities. In addition, we design a structure-aware lookahead policy network, which explicitly models inter-node dependencies along the multi-hop reasoning process and performs lookahead value evaluations for candidate actions, thereby enhancing the agent’s global state awareness and decision foresight in complex environments. Finally, we conducted extensive experiments on four public multi-hop question answering benchmarks and one domain-specific dataset. The results demonstrate that our framework surpasses state-of-the-art methods while demonstrating strong generalization.

Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo 等

Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their reliability in real-world applications. This deficiency arises from a lack of systematic mechanisms to incorporate constraint information during the generation process. While existing approaches attempt to mitigate this by relying on external tools or task decomposition, they fail to enhance the model’s intrinsic constraint awareness. To address this, we propose Constraint-Aware Reinforcement Learning (CARL), a novel RL framework designed to strengthen LLMs’ intrinsic focus on constraints. CARL introduces a constraint-aware reward by comparing the model’s output distributions under constrained and unconstrained inputs, encouraging constraint focus and penalizing neglect.Compatible with various RL frameworks and requiring no external solvers or top models, CARL enables scalable, end-to-end constraint-aware planning. Extensive experiments on BlocksWorld, TravelPlanner, and T-Eval demonstrate that CARL significantly outperforms standard Reinforcement Fine-Tuning (RFT) baselines and state-of-the-art reasoning models, exhibiting a markedly increased focus on constraints.

Qi He, Cheng Qian, Xiusi Chen, Bingxiang He, Yi R. Fung, Heng Ji

Claim verification with large language models (LLMs) has recently attracted growing attention, due to their strong reasoning capabilities and transparent verification processes compared to traditional answer-only judgments. However, existing approaches to online claim verification, which requires iterative evidence retrieval and reasoning, still mainly rely on prompt engineering or pre-designed reasoning workflows, without unified training to improve necessary skills. Therefore, we introduce Veri-R1, an online reinforcement learning (RL) framework that enables an LLM to interact with a search engine and to receive reward signals that explicitly shape its planning, retrieval, and reasoning behaviors. The dynamic interaction between models and retrieval systems more accurately reflects real-world verification scenarios and fosters comprehensive verification skills. Empirical results show that Veri-R1 improves joint accuracy by up to 30% and doubles evidence score, often surpassing its larger-scale model counterparts. Ablation studies further reveal the impact of reward components, and the link between output logits and label accuracy. Our results highlight the effectiveness of online RL for precise and faithful claim verification, and provide a foundation for future research.

Liangliang Liu, Yanming Li, Yigang Liu, Jialong Han, Rujia Shen, Yi Guan, Yi Lin, Jingchi Jiang

Tool graphs (TG) model dependencies among tools and resources, enabling more structured organization and management of large toolsets. However, existing methods and benchmarks often formulate tool learning (TL) as a single-solution setting, overlooking the fact that many tasks admit multiple valid tool combinations and therefore require optimal solution selection. Moreover, exploring large-scale TG is computationally expensive, especially under constrained context budgets. To address these challenges, we propose TOPT, an efficient framework for learning optimal TL policies over large TG, as well as construct MultiSoTLBench, a large-scale Multi-Solution TL Benchmark, where each task admits multiple valid solutions. Specifically, to improve search efficiency in large action spaces, TOPT adopts a progressive graph expansion strategy: we train a reinforcement learning (RL) agent to acquire transferable expansion skills and construct, on demand, a compact solvable subgraph that preserves only task-relevant links. This reduces the size of the candidate space and the context usage from the outset. To enable optimal selection, we further propose a progressive graph reasoning framework. It performs RL-driven optimality analysis and scheduling on the expanded subgraph to generate an optimal tool chain that balances path length and tool cost. Comprehensive experiments on MultiSoTLBench demonstrate that TOPT generalizes effectively, improving task success and solution optimality by 46.21% and 66.34%, respectively.

Yutang Ge, Guojiang Zhao, Sihang Li, Zheng Cheng, Zifeng Zhao, Hanchen Xia, Guolin Ke, Linfeng Zhang, Zhifeng Gao, Yu Guang Wang

Designing proteins that satisfy natural language functional requirements is a central goal in protein engineering. A straightforward baseline is to fine-tune generic instruction-tuned LLMs as direct text-to-sequence generators, but this is data- and compute-hungry. With limited supervision, LLMs can produce coherent plans in text yet fail to reliably realize them as sequences. This plan–execute gap motivates ProtoCycle, an agentic framework for protein design that uses LLMs primarily to drive a multi-round, feedback-driven decision cycle. ProtoCycle couples an LLM planner with a lightweight tool environment designed to emulate the iterative workflow of human protein engineers and uses LLM-driven reflection on tool feedback to revise plans. Trained with supervised trajectories and online reinforcement learning, ProtoCycle achieves strong language alignment while maintaining competitive foldability, and ablations show that reflection substantially improves sequence quality.