arXiv subjects

Chunlin Chen

Publications and source records attributed to Chunlin Chen.

At least 19 recordsLinked to original sources

arXiv2026

Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models

Vision-Language-Action (VLA) models acquire broad embodied capabilities through large-scale pretraining, yet their generalization remains far more fragile than that of LLMs and VLMs. The prevailing remedy, post-training via supervised fine-tuning or reinforcement learning, improves task-specific performance but narrows the generalist capability that makes pretraining valuable. We identify a key bottleneck: VLA failures stem not only from action generation but also from action evaluation. A diagnostic pass@k study confirms that frozen VLAs already contain competent behaviors in their output distribution, with overall success rates rising from 33% at pass@1 to 92% at pass@32. Inspired by this, we propose SVA (Search, Value, and Act), a simple framework that equips frozen VLA policies with long-term consequence awareness. SVA first uses Monte-Carlo tree search in simulation to fully explore the VLA's output distribution and collect diverse trajectories annotated with empirical returns; this knowledge is then distilled into a lightweight Q-value model that predicts the expected consequence of candidate actions; at deployment, the frozen VLA proposes multiple candidates and the evaluator selects the one with the highest uncertainty-regularized Q-value, requiring no simulator access. By decoupling action proposal from consequence evaluation, SVA preserves the generalization capacity of the VLA backbone while substantially improving task success rates. Experiments across embodied benchmarks show that SVA consistently improves generalization on unseen tasks and exhibits strong test-time scaling behavior. Strikingly, SVA enables a 9B VLA to outperform a 27B VLA by 7 points at 27% lower inference latency, suggesting that scaling test-time evaluation is more cost-effective than scaling model size.

cs.RO↗

arXiv2026

Scaling law of asymptotic freedom in collective charging of quantum batteries

We establish a universal scaling law for collective charging of quantum batteries, independent of microscopic details. We prove that the ergotropy-to-energy ratio approaches unity at least as fast as $\sim N^{-1}$ with the number of batteries $N$, implying generic asymptotic freedom. We further show how the universal $1/N$ scaling can be overcome: when the battery state becomes asymptotically pure, the convergence can be substantially faster, including $\sim N^{-b}$ with $b>1$ and even exponential scaling in $N^2$. Rigorous finite-$N$ upper and lower bounds on the ergotropy-to-energy ratio are further derived, providing nonasymptotic guarantees for the universal $1/N$ scaling.

quant-ph↗

arXiv2026

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG

Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields. While Retrieval-Augmented Generation (RAG) mitigates these issues, existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning. In this paper, we propose MA-RAG (Multi-Round Agentic RAG), a framework that facilitates test-time scaling for complex medical reasoning by iteratively evolving both external evidence and internal reasoning history within an agentic refinement loop. At each round, the agent transforms semantic conflict among candidate responses into actionable queries to retrieve external evidence, while optimizing history reasoning traces to mitigate long-context degradation. MA-RAG extends the self-consistency principle by leveraging the lack of consistency as a proactive signal for multi-round agentic reasoning and retrieval, and mirrors a boosting mechanism that iteratively minimizes the residual error toward a stable, high-fidelity medical consensus. Extensive evaluations across 7 medical Q&A benchmarks show that MA-RAG consistently surpasses competitive inference-time scaling and RAG baselines, delivering substantial +6.8 points on average accuracy over the backbone model. Our code is available at https://github.com/NJU-RL/MA-RAG.

cs.CL↗

arXiv2026

Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation

Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks. A fundamental limitation remains \textit{the curse of diversity collapse}, where the objective formulation and optimization landscape inherently collapse the policy to a Dirac delta distribution. To address this challenge, we propose \textbf{DRIFT} (\textbf{D}ive\textbf{R}sity-\textbf{I}ncentivized Reinforcement \textbf{F}ine-\textbf{T}uning for Versatile Image Generation), an innovative framework that systematically incentivizes output diversity throughout the on-policy fine-tuning process, reconciling strong task alignment with high generation diversity to enhance versatility essential for applications that demand diverse candidate generations. We approach the problem across three representative perspectives: i) \textbf{sampling} a reward-concentrated subset that filters out reward outliers to prevent premature collapse; ii) \textbf{prompting} with stochastic variations to expand the conditioning space, and iii) \textbf{optimization} of the intra-group diversity with a potential-based reward shaping mechanism. Experimental results show that DRIFT achieves superior Pareto dominance regarding task alignment and generation diversity, yielding a $ 9.08\%\!\sim\! 43.46\%$ increase in diversity at equivalent alignment levels and a $ 59.65\% \!\sim\! 65.86\%$ increase in alignment at equivalent levels of diversity.

cs.LG↗

arXiv2025

Yanyun-3: Enabling Cross-Platform Strategy Game Operation with Vision-Language Models

Cross-platform strategy game automation remains a challenge due to diverse user interfaces and dynamic battlefield environments. Existing Vision--Language Models (VLMs) struggle with generalization across heterogeneous platforms and lack precision in interface understanding and action execution. We introduce Yanyun-3, a VLM-based agent that integrates Qwen2.5-VL for visual reasoning and UI-TARS for interface execution. We propose a novel data organization principle -- combination granularity -- to distinguish intra-sample fusion and inter-sample mixing of multimodal data (static images, multi-image sequences, and videos). The model is fine-tuned using QLoRA on a curated dataset across three strategy game platforms. The optimal strategy (M*V+S) achieves a 12.98x improvement in BLEU-4 score and a 63% reduction in inference time compared to full fusion. Yanyun-3 successfully executes core tasks (e.g., target selection, resource allocation) across platforms without platform-specific tuning. Our findings demonstrate that structured multimodal data organization significantly enhances VLM performance in embodied tasks. Yanyun-3 offers a generalizable framework for GUI automation, with broader implications for robotics and autonomous systems.

cs.AI↗

arXiv2025

Conditional Diffusion Model for Multi-Agent Dynamic Task Decomposition

Task decomposition has shown promise in complex cooperative multi-agent reinforcement learning (MARL) tasks, which enables efficient hierarchical learning for long-horizon tasks in dynamic and uncertain environments. However, learning dynamic task decomposition from scratch generally requires a large number of training samples, especially exploring the large joint action space under partial observability. In this paper, we present the Conditional Diffusion Model for Dynamic Task Decomposition (C$\text{D}^\text{3}$T), a novel two-level hierarchical MARL framework designed to automatically infer subtask and coordination patterns. The high-level policy learns subtask representation to generate a subtask selection strategy based on subtask effects. To capture the effects of subtasks on the environment, C$\text{D}^\text{3}$T predicts the next observation and reward using a conditional diffusion model. At the low level, agents collaboratively learn and share specialized skills within their assigned subtasks. Moreover, the learned subtask representation is also used as additional semantic information in a multi-head attention mixing network to enhance value decomposition and provide an efficient reasoning bridge between individual and joint value functions. Experimental results on various benchmarks demonstrate that C$\text{D}^\text{3}$T achieves better performance than existing baselines.

cs.AI↗

arXiv2025

High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning

The ability to model interactions among agents is crucial for effective coordination and understanding their cooperation mechanisms in multi-agent reinforcement learning (MARL). However, previous efforts to model high-order interactions have been primarily hindered by the combinatorial explosion or the opaque nature of their black-box network structures. In this paper, we propose a novel value decomposition framework, called Continued Fraction Q-Learning (QCoFr), which can flexibly capture arbitrary-order agent interactions with only linear complexity $\mathcal{O}\left({n}\right)$ in the number of agents, thus avoiding the combinatorial explosion when modeling rich cooperation. Furthermore, we introduce the variational information bottleneck to extract latent information for estimating credits. This latent information helps agents filter out noisy interactions, thereby significantly enhancing both cooperation and interpretability. Extensive experiments demonstrate that QCoFr not only consistently achieves better performance but also provides interpretability that aligns with our theoretical analysis.

cs.MA↗

arXiv2025

Diversity-Incentivized Exploration for Versatile Reasoning

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a crucial paradigm for incentivizing reasoning capabilities in Large Language Models (LLMs). Due to vast state-action spaces and reward sparsity in reasoning tasks, existing methods often struggle with deficient exploration and poor sample efficiency. In the paper, we propose \textbf{DIVER} (\textbf{D}iversity-\textbf{I}ncentivized Exploration for \textbf{V}ersatil\textbf{E} \textbf{R}easoning), an innovative framework that highlights the pivotal role of global sequence-level diversity to incentivize deep exploration for versatile reasoning. We first conduct a primary empirical study to reveal a strong positive correlation between global diversity and reasoning capacity. Building on this insight, we introduce global diversity incentives as an intrinsic reward to promote deep exploration in a semantically structured space. Incorporating the intrinsic reward, we develop a potential-based reward shaping mechanism to preserve optimal policy invariance and design simple heuristics to mitigate possible reward hacking. Experimental results show that DIVER outperforms competitive RLVR baselines with various exploration strategies on both in-domain and out-of-domain tasks, excelling in both Pass@1 and Pass@k evaluations. Our code is available at https://github.com/NJU-RL/DIVER.

cs.AI↗

arXiv2025

Concept Learning for Cooperative Multi-Agent Reinforcement Learning

Despite substantial progress in applying neural networks (NN) to multi-agent reinforcement learning (MARL) areas, they still largely suffer from a lack of transparency and interoperability. However, its implicit cooperative mechanism is not yet fully understood due to black-box networks. In this work, we study an interpretable value decomposition framework via concept bottleneck models, which promote trustworthiness by conditioning credit assignment on an intermediate level of human-like cooperation concepts. To address this problem, we propose a novel value-based method, named Concepts learning for Multi-agent Q-learning (CMQ), that goes beyond the current performance-vs-interpretability trade-off by learning interpretable cooperation concepts. CMQ represents each cooperation concept as a supervised vector, as opposed to existing models where the information flowing through their end-to-end mechanism is concept-agnostic. Intuitively, using individual action value conditioning on global state embeddings to represent each concept allows for extra cooperation representation capacity. Empirical evaluations on the StarCraft II micromanagement challenge and level-based foraging (LBF) show that CMQ achieves superior performance compared with the state-of-the-art counterparts. The results also demonstrate that CMQ provides more cooperation concept representation capturing meaningful cooperation modes, and supports test-time concept interventions for detecting potential biases of cooperation mode and identifying spurious artifacts that impact cooperation.

cs.AI↗

arXiv2025

Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise

Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense individual rewards to guide the agents toward efficient exploration. However, individual rewards generally rely on manually engineered shaping-reward functions that lack high-order intelligence, thus it behaves ineffectively than humans regarding learning and generalization in complex problems. To tackle these issues, we combine the above two paradigms and propose a novel framework, LIGHT (Learning Individual Intrinsic reward via Incorporating Generalized Human experTise), which can integrate human knowledge into MARL algorithms in an end-to-end manner. LIGHT guides each agent to avoid unnecessary exploration by considering both individual action distribution and human expertise preference distribution. Then, LIGHT designs individual intrinsic rewards for each agent based on actionable representational transformation relevant to Q-learning so that the agents align their action preferences with the human expertise while maximizing the joint action value. Experimental results demonstrate the superiority of our method over representative baselines regarding performance and better knowledge reusability across different sparse-reward tasks on challenging scenarios.

cs.LG↗

arXiv2025

Mixture-of-Experts Meets In-Context Reinforcement Learning

In-context reinforcement learning (ICRL) has emerged as a promising paradigm for adapting RL agents to downstream tasks through prompt conditioning. However, two notable challenges remain in fully harnessing in-context learning within RL domains: the intrinsic multi-modality of the state-action-reward data and the diverse, heterogeneous nature of decision tasks. To tackle these challenges, we propose T2MIR (Token- and Task-wise MoE for In-context RL), an innovative framework that introduces architectural advances of mixture-of-experts (MoE) into transformer-based decision models. T2MIR substitutes the feedforward layer with two parallel layers: a token-wise MoE that captures distinct semantics of input tokens across multiple modalities, and a task-wise MoE that routes diverse tasks to specialized experts for managing a broad task distribution with alleviated gradient conflicts. To enhance task-wise routing, we introduce a contrastive learning method that maximizes the mutual information between the task and its router representation, enabling more precise capture of task-relevant information. The outputs of two MoE components are concatenated and fed into the next layer. Comprehensive experiments show that T2MIR significantly facilitates in-context learning capacity and outperforms various types of baselines. We bring the potential and promise of MoE to ICRL, offering a simple and scalable architectural enhancement to advance ICRL one step closer toward achievements in language and vision communities. Our code is available at https://github.com/NJU-RL/T2MIR.

cs.LG↗

arXiv2025

Scalable In-Context Q-Learning

Recent advancements in language models have demonstrated remarkable in-context learning abilities, prompting the exploration of in-context reinforcement learning (ICRL) to extend the promise to decision domains. Due to involving more complex dynamics and temporal correlations, existing ICRL approaches may face challenges in learning from suboptimal trajectories and achieving precise in-context inference. In the paper, we propose \textbf{S}calable \textbf{I}n-\textbf{C}ontext \textbf{Q}-\textbf{L}earning (\textbf{S-ICQL}), an innovative framework that harnesses dynamic programming and world modeling to steer ICRL toward efficient reward maximization and task generalization, while retaining the scalability and stability of supervised pretraining. We design a prompt-based multi-head transformer architecture that simultaneously predicts optimal policies and in-context value functions using separate heads. We pretrain a generalized world model to capture task-relevant information, enabling the construction of a compact prompt that facilitates fast and precise in-context inference. During training, we perform iterative policy improvement by fitting a state value function to an upper-expectile of the Q-function, and distill the in-context value functions into policy extraction using advantage-weighted regression. Extensive experiments across a range of discrete and continuous environments show consistent performance gains over various types of baselines, especially when learning from suboptimal data. Our code is available at \textcolor{magenta}{\href{https://github.com/NJU-RL/SICQL}{https://github.com/NJU-RL/SICQL}}.

cs.AI↗

arXiv2025

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning

While showing sophisticated reasoning abilities, large language models (LLMs) still struggle with long-horizon decision-making tasks due to deficient exploration and long-term credit assignment, especially in sparse-reward scenarios. Inspired by the divide-and-conquer principle, we propose an innovative framework **GLIDER** (**G**rounding **L**anguage Models as Eff**I**cient **D**ecision-Making Agents via Offline Hi**E**rarchical **R**einforcement Learning) that introduces a parameter-efficient and generally applicable hierarchy to LLM policies. We develop a scheme where the low-level controller is supervised with abstract, step-by-step plans that are learned and instructed by the high-level policy. This design decomposes complicated problems into a series of coherent chain-of-thought reasoning sub-tasks, providing flexible temporal abstraction to significantly enhance exploration and learning for long-horizon tasks. Furthermore, GLIDER facilitates fast online adaptation to non-stationary environments owing to the strong transferability of its task-agnostic low-level skills. Experiments on ScienceWorld and ALFWorld benchmarks show that GLIDER achieves consistent performance gains, along with enhanced generalization capabilities.

cs.AI↗

arXiv2025

ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representations

Visual-Interleaved Chain-of-Thought (VI-CoT) enables Multi-modal Large Language Models (MLLMs) to continually update their understanding and decision space based on step-wise intermediate visual states (IVS), much like a human would, which has demonstrated impressive success in various tasks, thereby leading to emerged advancements in related downstream benchmarks. Despite promising progress, current benchmarks provide models with relatively fixed IVS, rather than free-style IVS, whch might forcibly distort the original thinking trajectories, failing to evaluate their intrinsic reasoning capabilities. More importantly, existing benchmarks neglect to systematically explore the impact factors that IVS would impart to the untamed reasoning performance. To tackle above gaps, we introduce a specialized benchmark termed ViC-Bench, consisting of four representive tasks, i.e., maze navigation, jigsaw puzzle, embodied long-horizon planning, as well as complex counting, where each task has dedicated free-style IVS generation pipeline supporting adaptive function calls. To systematically examine VI-CoT capability, we propose a thorough evaluation suite incorporating a progressive three-stage strategy with targeted new metrics. Besides, we establish Incremental Prompting Information Injection strategy to ablatively explore the prompting factors for VI-CoT. We extensively conduct evaluations for 18 advanced MLLMs, revealing key insights into their VI-CoT capability. The introduced ViC-Bench has been made publicly available at Huggingface.

cs.CV↗

arXiv2025

Learning Diverse Natural Behaviors for Enhancing the Agility of Quadrupedal Robots

Achieving animal-like agility is a longstanding goal in quadrupedal robotics. While recent studies have successfully demonstrated imitation of specific behaviors, enabling robots to replicate a broader range of natural behaviors in real-world environments remains an open challenge. Here we propose an integrated controller comprising a Basic Behavior Controller (BBC) and a Task-Specific Controller (TSC) which can effectively learn diverse natural quadrupedal behaviors in an enhanced simulator and efficiently transfer them to the real world. Specifically, the BBC is trained using a novel semi-supervised generative adversarial imitation learning algorithm to extract diverse behavioral styles from raw motion capture data of real dogs, enabling smooth behavior transitions by adjusting discrete and continuous latent variable inputs. The TSC, trained via privileged learning with depth images as input, coordinates the BBC to efficiently perform various tasks. Additionally, we employ evolutionary adversarial simulator identification to optimize the simulator, aligning it closely with reality. After training, the robot exhibits diverse natural behaviors, successfully completing the quadrupedal agility challenge at an average speed of 1.1 m/s and achieving a peak speed of 3.2 m/s during hurdling. This work represents a substantial step toward animal-like agility in quadrupedal robots, opening avenues for their deployment in increasingly complex real-world environments.

cs.RO↗

arXiv2025

Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision

Offline meta-RL usually tackles generalization by inferring task beliefs from high-quality samples or warmup explorations. The restricted form limits their generality and usability since these supervision signals are expensive and even infeasible to acquire in advance for unseen tasks. Learning directly from the raw text about decision tasks is a promising alternative to leverage a much broader source of supervision. In the paper, we propose \textbf{T}ext-to-\textbf{D}ecision \textbf{A}gent (\textbf{T2DA}), a simple and scalable framework that supervises offline meta-RL with natural language. We first introduce a generalized world model to encode multi-task decision data into a dynamics-aware embedding space. Then, inspired by CLIP, we predict which textual description goes with which decision embedding, effectively bridging their semantic gap via contrastive language-decision pre-training and aligning the text embeddings to comprehend the environment dynamics. After training the text-conditioned generalist policy, the agent can directly realize zero-shot text-to-decision generation in response to language instructions. Comprehensive experiments on MuJoCo and Meta-World benchmarks show that T2DA facilitates high-capacity zero-shot generalization and outperforms various types of baselines. Our code is available at \textcolor{magenta}{\href{https://github.com/NJU-RL/T2DA}{https://github.com/NJU-RL/T2DA}}.

cs.AI↗

arXiv2024

Fast Disentangled Slim Tensor Learning for Multi-view Clustering

Tensor-based multi-view clustering has recently received significant attention due to its exceptional ability to explore cross-view high-order correlations. However, most existing methods still encounter some limitations. (1) Most of them explore the correlations among different affinity matrices, making them unscalable to large-scale data. (2) Although some methods address it by introducing bipartite graphs, they may result in sub-optimal solutions caused by an unstable anchor selection process. (3) They generally ignore the negative impact of latent semantic-unrelated information in each view. To tackle these issues, we propose a new approach termed fast Disentangled Slim Tensor Learning (DSTL) for multi-view clustering . Instead of focusing on the multi-view graph structures, DSTL directly explores the high-order correlations among multi-view latent semantic representations based on matrix factorization. To alleviate the negative influence of feature redundancy, inspired by robust PCA, DSTL disentangles the latent low-dimensional representation into a semantic-unrelated part and a semantic-related part for each view. Subsequently, two slim tensors are constructed with tensor-based regularization. To further enhance the quality of feature disentanglement, the semantic-related representations are aligned across views through a consensus alignment indicator. Our proposed model is computationally efficient and can be solved effectively. Extensive experiments demonstrate the superiority and efficiency of DSTL over state-of-the-art approaches. The code of DSTL is available at https://github.com/dengxu-nju/DSTL.

cs.CV↗

arXiv2024

Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement

A longstanding goal of artificial general intelligence is highly capable generalists that can learn from diverse experiences and generalize to unseen tasks. The language and vision communities have seen remarkable progress toward this trend by scaling up transformer-based models trained on massive datasets, while reinforcement learning (RL) agents still suffer from poor generalization capacity under such paradigms. To tackle this challenge, we propose Meta Decision Transformer (Meta-DT), which leverages the sequential modeling ability of the transformer architecture and robust task representation learning via world model disentanglement to achieve efficient generalization in offline meta-RL. We pretrain a context-aware world model to learn a compact task representation, and inject it as a contextual condition to the causal transformer to guide task-oriented sequence generation. Then, we subtly utilize history trajectories generated by the meta-policy as a self-guided prompt to exploit the architectural inductive bias. We select the trajectory segment that yields the largest prediction error on the pretrained world model to construct the prompt, aiming to encode task-specific information complementary to the world model maximally. Notably, the proposed framework eliminates the requirement of any expert demonstration or domain knowledge at test time. Experimental results on MuJoCo and Meta-World benchmarks across various dataset types show that Meta-DT exhibits superior few and zero-shot generalization capacity compared to strong baselines while being more practical with fewer prerequisites. Our code is available at https://github.com/NJU-RL/Meta-DT.

cs.LG↗