论文检索

Reinforcement Learning · Everything Else

Qili Shen, Kairui Feng, Ang He, Xuanhong Chen, Dake Zhang

Recent work increasingly adopts AI for Science (AI4S) models to replace expensive PDE solvers as simulation environments for reinforcement learning (RL), enabling faster training in complex physical control tasks. However, using approximate simulators introduces modeling errors that affect the learned policy. In this paper, we introduce a unified $\varepsilon$-$N$ framework that quantifies the minimal computational cost $N^*(\varepsilon)$ required for an AI4S model to ensure that tabular RL can estimate the value function with unbiasedness, with probability at least $1 - \delta$. This characterization allows us to connect surrogate accuracy, grid resolution, and RL policy quality under a shared probabilistic language. We analyze how the discretization level $K$ of AI4S and RL space governs both PDE surrogate error and RL lattice approximation error, and we employ spectral theory and Sobolev estimates to derive optimal grid strategies that minimize total cost while preserving learning fidelity. Our theory reveals that different systems, such as ODE- and PDE-governed environments, require different allocations of effort between physical simulation and RL optimization. Overall, our framework offers a principled foundation for designing efficient, scalable, and cost-aware AI4S-RL systems with provable learning guarantees.

Optimization · Optimization and Learning under Uncertainty

Yang Hu, Jieren Tan, Changliang Zou, Yajie Bao, Haojie Ren

Robust decision-making is crucial in numerous risk-sensitive applications where outcomes are uncertain and the cost of failure is high. Conditional Robust Optimization (CRO) offers a framework for such tasks by constructing prediction sets for the outcome that satisfy predefined coverage requirements and then making decisions based on these sets. Many existing approaches leverage conformal prediction to build prediction sets with guaranteed coverage for CRO. However, since coverage is a *sufficient but not necessary* condition for robustness, enforcing such constraints often leads to overly conservative decisions. To overcome this limitation, we propose a novel framework named Conformal Robustness Control (CRC), that directly optimizes the prediction set construction under explicit robustness constraints, thereby enabling more efficient decisions without compromising robustness. We develop efficient algorithms to solve the CRC optimization problem, and also provide theoretical guarantees on both robustness and optimality. Empirical results show that CRC consistently yields more effective decisions than existing baselines while still meeting the target robustness level.

Applications · Everything Else

Apurva Gandhi, Graham Neubig

One of the fundamental problems in digital agents is their lack of understanding of their environment. For instance, a web browsing agent may get lost in unfamiliar websites, uncertain what pages must be visited to achieve its goals. To address this, we propose Go-Browse, a method for automatically collecting diverse and realistic web agent data at scale through structured exploration of web environments. Go-Browse achieves efficient exploration by framing data collection as a graph search, enabling reuse of information across exploration episodes. We instantiate our method on the WebArena benchmark, collecting a dataset of 10K successful task-solving trajectories and 40K interaction steps across 100 URLs. Fine-tuning a 7B parameter language model on this dataset achieves a success rate of 21.7% on the WebArena benchmark, beating GPT-4o mini by 2.4% and exceeding current state-of-the-art results for sub-10B parameter models by 2.9%.

Applications · Neuroscience, Cognitive Science

Zheng Huang, Enpei Zhang, Weikang Qiu, Yinghao Cai, Carl Yang, Elynn Chen, Xiang Zhang, Rex Ying, Dawei Zhou, Yujun Yan

Understanding how the brain encodes visual information is a central challenge in neuroscience and machine learning. A promising approach is to reconstruct visual stimuli—essentially images—from functional Magnetic Resonance Imaging (fMRI) signals. This involves two stages: transforming fMRI signals into a latent space and then using a pre-trained generative model to reconstruct images. The reconstruction quality depends on how similar the latent space is to the structure of neural activity and how well the generative model produces images from that space. Yet, it remains unclear which type of latent space best supports this transformation and how it should be organized to represent visual stimuli effectively. We present two key findings. First, fMRI signals are more similar to the text space of a language model than to either a vision-based space or a joint text–image space. Second, text representations and the generative model should be adapted to capture the compositional nature of visual stimuli, including objects, their detailed attributes, and relationships. Building on these insights, we propose PRISM, a model that Projects fMRI sIgnals into a Structured text space as an interMediate representation for visual stimuli reconstruction. It includes an object-centric diffusion module that generates images by composing individual objects to reduce object detection errors, and an attribute/relationship search module that automatically identifies key attributes and relationships that best align with the neural activity. Extensive experiments on real-world datasets demonstrate that our framework outperforms existing methods, achieving up to an 6% reduction in perceptual loss. These results highlight the importance of using structured text as an intermediate space to bridge fMRI signals and image reconstruction. Codes are available at https://github.com/GraphmindDartmouth/PRISM.

Reinforcement Learning · Everything Else

Jiacheng Lin, Zhongruo Wang, Kun Qian, Tian Wang, Arvind Srinivasan, Hansi Zeng, Ruochen Jiao, Xie Zhou, Jiri Gesi, Dakuo Wang 等

Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their general capabilities. In this work, we revisit this trade-off and present both empirical and theoretical insights. First, we show that SFT does not always hurt: using a smaller learning rate can substantially mitigate general performance degradation while preserving comparable target-domain performance. We then provide a theoretical analysis that explains these phenomena and further motivates a new method, Token-Adaptive Loss Reweighting (TALR). Building on this, and recognizing that smaller learning rates alone do not fully eliminate general-performance degradation in all cases, we evaluate a range of strategies for reducing general capability loss, including L2 regularization, LoRA, model averaging, FLOW, and our proposed TALR. Experimental results demonstrate that while no method completely eliminates the trade-off, TALR consistently outperforms these baselines in balancing domain-specific gains and general capabilities. Finally, we distill our findings into practical guidelines for adapting LLMs to new domains: (i) using a small learning rate to achieve a favorable trade-off, and (ii) when a stronger balance is further desired, adopt TALR as an effective strategy.

Reinforcement Learning · Planning

Yaorui SHI, Yuxin Chen, Siyuan Wang, Sihang Li, Hengxing Cai, Qi GU, Xiang Wang, An Zhang

Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory corpus that is dynamically updated during a single-pass document scan, also known as the "memorize while reading" methods. While this approach scales efficiently, it suffers from irreversible forward-only processing, information loss through overwriting, and sparse reinforcement learning signals. To tackle these challenges, we present ReMemR1, a memory-augmented agent with callback-enhanced memory that allows selective retrieval from the entire memory history and allows non-linear reasoning and revisiting of early evidence. To further strengthen training, we propose Reinforcement Learning with Multi-Level Rewards (RLMLR), which combines final-answer rewards with dense, step-level signals that guide effective memory use. Together, these contributions mitigate information degradation, improve supervision, and support multi-hop memory utilizing. Experiments on long-document QA show significant gains over existing memory-based approaches, which validates ReMemR1 as an effective solution for long-context reasoning agents.

Reinforcement Learning · Planning

Priyam Parashar, Jacob Krantz, Matthew Chang, Kavit Shah, Xavier Puig, Roozbeh Mottaghi

We develop a novel memory representation for embodied planning models performing long-horizon mobile manipulation in dynamic, large-scale indoor environments. Prior memory representations fall short in this setting, as they struggle with object movements, suffer from computational deficiencies, and often depend on the heuristic integration of multiple models. To overcome these limitations, we present the Embodied Perception Memory (EPM), a learnable memory designed for embodied planning. EPM is implemented as a unified Vision-Language Model (VLM) that uses egocentric vision to maintain and update a textual environment representation. We further introduce two complementary methods for training planners to leverage the EPM: an imitation strategy that uses human trajectories for natural exploration and interaction, and a novel reinforcement learning approach, Dynamic Difficulty-Aware Fine-Tuning (DDAFT), which improves planning performance via difficulty-aware exploration. Our memory representation, when integrated with our planning training methods, leads to significant improvements on planning tasks, showing up to a 55% increase in success rate on the PARTNR benchmark compared to strong baselines. Also, our planning method outperforms these baselines even when they have access to groundtruth perception.

Theory · Learning Theory

Zicheng Hu, Zihao Wang, Cheng Chen

This paper studies federated multi-armed bandit (MAB) problems in which multiple agents work together to solve a common MAB problem through a communication network. We focus on the heterogeneous setting in which no single agent can identify the globally best arm using only locally biased observations. In this setting, different agents may select the same arm at the same time step, but receive different rewards. We propose a novel algorithm called \textsc{FedFTRL} for this problem and, to our knowledge, it is the first to achieve near-optimal regret guarantees in both stochastic and adversarial environments. Notably, in the adversarial regime, our algorithm achieves $O(T^{\frac{1}{2}})$ regret, a significant improvement over the state-of-the-art regret of $O(T^{\frac{2}{3}})$ \citep{yi2023doubly}. We also provide empirical evaluations comparing our algorithm with baseline methods, demonstrating the effectiveness of our approach on both synthetic and real-world datasets.

Reinforcement Learning · Online

Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Jun Rao, Min Zhang

Large Reasoning Models (LRMs) demonstrate strong performance in complex tasks but often face the challenge of *overthinking*, leading to substantially high inference costs. Existing approaches synthesize shorter reasoning responses for LRMs to learn, but are inefficient for online usage due to the time-consuming data generation and filtering processes. Meanwhile, online reinforcement learning mainly adopts a length reward to encourage short reasoning responses, but it tends to lose reflection ability and harm performance. To address these issues, we propose REA-RL, which introduces a small reflection model for efficient scaling in online training, offering both parallel sampling and sequential revision. Besides, a reflection reward is designed to further prevent LRMs from favoring short yet non-reflective responses. Experiments show that both methods maintain or enhance performance while significantly improving inference efficiency. Their combination achieves a good balance between performance and efficiency, reducing inference costs by 36\% without compromising performance. Further analysis demonstrates that our methods are effective by maintaining reflection frequency for hard problems while appropriately reducing it for easier ones without losing reflection ability. Code is available at https://github.com/hexuandeng/REA-RL.

Reinforcement Learning · Online

Zhuo Li, Guodong DU, Weiyang Guo, Yigeng Zhou, Xiucheng Li, Wenya Wang, Fangming Liu, Yequan Wang, Deheng Ye, Min Zhang 等

Aligning large language models (LLMs) to simultaneously satisfy multiple objectives remains a significant challenge, especially given the diverse and often conflicting nature of human preferences. Existing alignment methods struggle to balance trade-offs effectively, often requiring costly retraining or yielding suboptimal results across the Pareto frontier of preferences. In this paper, we introduce HoE (Hierarchical Mixture-of-Experts), a lightweight, parameter-efficient, and plug-and-play approach that eliminates the need for model retraining, while enabling LLMs to adapt across the entire Pareto frontier and accommodate diverse user preferences. In particular, HoE consists of three hierarchical components: LoRA Experts, Router Experts and Weighting Router, reaching optimal Pareto frontiers and achieving a trade-off between parameter size, training cost, and performance. We evaluate HoE across various tasks on 16 objectives and 200 different preferences among 8 benchmarks, demonstrating superior performance over 15 recent baselines.

Applications · Chemistry and Drug Discovery

Lu Yu, Wei Xiang, Kang Han, Gaowen Liu, Ramana Kompella

A key step in protein optimization is modeling the fitness landscape, which maps proteins to functional assay readouts. Existing methods typically either use property-agnostic likelihoods/embeddings from pretrained protein language models (PLMs) for fitness prediction, or assume independent mutational effects, limiting their ability to capture higher-order interactions. In this work, we introduce RankFlow, a conditional flow framework that refines PLM representations to be a property-aligned distribution via a tailored energy function and captures multi-mutation interactions through learnable embeddings. To align optimization with evaluation protocols, we propose the Rank-Consistent Conditional Flow Loss (RC$^2$), a differentiable ranking objective that enforces the correct order of mutants rather than absolute values, which improves out-of-distribution generalization. Finally, we introduce a Property-guided Steering Gate (PSG) that concentrates learning on positions carrying signals for the target property while suppressing unrelated evolutionary biases. Across the ProteinGym, PEER, and FLIP benchmarks, RankFlow obtains state-of-the-art ranking accuracy and superior generalization performance.

Applications · Neuroscience, Cognitive Science

Yiting Dong, Jianhao Ding, Zijie Xu, Tong Bu, Zhaofei Yu, Tiejun Huang

Spiking Neural Networks (SNNs), with their temporal processing capabilities and biologically plausible dynamics, offer a natural platform for unsupervised representation learning. However, current unsupervised SNNs predominantly employ shallow architectures or localized plasticity rules, limiting their ability to model long-range temporal dependencies and maintain temporal feature consistency. This results in semantically unstable representations, thereby impeding the development of deep unsupervised SNNs for large-scale temporal video data. We propose PredNext, which explicitly models temporal relationships through cross-view future Step Prediction and Clip Prediction. This plug-and-play module seamlessly integrates with diverse self-supervised objectives. We firstly establish standard benchmarks for SNN self-supervised learning on UCF101, HMDB51, and MiniKinetics, which are substantially larger than conventional DVS datasets. PredNext delivers significant performance improvements across different tasks and self-supervised methods. PredNext achieves performance comparable to ImageNet-pretrained supervised weights, through unsupervised training solely on UCF101. Additional experiments demonstrate that PredNext, distinct from forced consistency constraints, substantially improves temporal feature consistency while enhancing network generalization capabilities. This work provides a effective foundation for unsupervised deep SNNs on large-scale temporal video data.

Applications · Neuroscience, Cognitive Science

Shaolong Wei, Qiyu Sun, Mingliang Wang, Liang Sun, Weiping Ding, Jiashuang Huang

Modeling the temporal dynamics of the human brain remains a core challenge in computational neuroscience and artificial intelligence. Traditional methods often ignore the biological spike characteristics of brain activity and find it difficult to reveal the dynamic dependencies and causal interactions between brain regions, limiting their effectiveness in brain function research and clinical applications. To address this issue, we propose a Spike-based Digital Brain (Spike-DB), a novel fundamental model that introduces the spike computing paradigm into brain time series modeling. Spike-DB encodes fMRI signals as spike trains and learns the temporal driving relationships between anchor and target regions to achieve high-precision prediction of brain activity and reveal underlying causal dependencies and dynamic relationship characteristics. Based on Spike-DB, we further conducted downstream tasks including brain disease classification, abnormal brain region identification, and effective connectivity inference. Experimental results on real-world epilepsy datasets and the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that Spike-DB outperforms existing mainstream methods in both prediction accuracy and downstream tasks, demonstrating its broad potential in clinical applications and brain science research. Our code is available at https://github.com/UAIBC-Brain/Spike-DB.

Reinforcement Learning · Online

Jianyu Xu, Vidhi Jain, Bryan Wilder, Aarti Singh

With advances in generative AI, decision-making agents can now dynamically create new actions during online learning, but action generation typically incurs costs that must be balanced against potential benefits. We study an online learning problem where an agent can generate new actions at any time step by paying a one-time cost, with these actions becoming permanently available for future use. The challenge lies in learning the optimal sequence of two-fold decisions: which action to take and when to generate new ones, further complicated by the triangular tradeoffs among exploitation, exploration and *creation*. To solve this problem, we propose a doubly-optimistic algorithm that employs Lower Confidence Bounds (LCB) for action selection and Upper Confidence Bounds (UCB) for action generation. Empirical evaluation on healthcare question-answering datasets demonstrates that our approach achieves favorable generation-quality trade-offs compared to baseline strategies. From theoretical perspectives, we prove that our algorithm achieves the optimal regret of $O(T^{\frac{d}{d+2}}d^{\frac{d}{d+2}} + d\sqrt{T\log T})$, providing the first sublinear regret bound for online learning with expanding action spaces.

Reinforcement Learning · Online

Mengmeng Li, Philipp Schneider, Jelisaveta Aleksic, Daniel Kuhn

We introduce the first best-of-both-worlds algorithm for contextual combinatorial semi-bandits that simultaneously guarantees $\widetilde{\mathcal{O}}(\sqrt{T})$ regret in the adversarial regime and $\widetilde{\mathcal{O}}(\ln T)$ regret in the corrupted stochastic regime. Our approach builds on the Follow-the-Regularized-Leader (FTRL) framework equipped with a Shannon entropy regularizer, yielding a flexible method that admits efficient implementations. Beyond regret bounds, we tackle the practical bottleneck in FTRL (or, equivalently, Online Stochastic Mirror Descent) arising from the high-dimensional projection step encountered in each round of interaction. By leveraging the Karush-Kuhn-Tucker conditions, we transform the $K$-dimensional convex projection problem into a single-variable root-finding problem, dramatically accelerating each round. Empirical evaluations demonstrate that this combined strategy not only attains the attractive regret bounds of best-of-both-worlds algorithms but also delivers substantial per-round speed-ups, making it well-suited for large-scale, real-time applications.

Reinforcement Learning · Online

Peng Zhao-Han, Shaohui Li, Zhi Li, Shulan Ruan, Yu LIU, You He

While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structurally similar scenes and remain vulnerable to spurious variations such as textures or color shifts. From a cognitive science perspective, humans segment continuous sensory streams into discrete events and rely on these key events for decision-making. Motivated by this principle, we propose the Event-Aware World Model (EAWM), a general framework that learns event-aware representations to streamline policy learning without requiring handcrafted labels. EAWM employs an automated event generator to derive events from raw observations and introduces a Generic Event Segmentor (GES) to identify event boundaries, which mark the start and end time of event segments. Through event prediction, the representation space is shaped to capture meaningful spatio-temporal transitions. Beyond this, we present a unified formulation of seemingly distinct world model architectures and show the broad applicability of our methods. Experiments on Atari 100K, Craftax 1M, and DeepMind Control 500K, DMC-GB2 500K demonstrate that EAWM consistently boosts the performance of strong MBRL baselines by 10\%–45\%, setting new state-of-the-art results across benchmarks. Our code is released at [https://github.com/MarquisDarwin/EAWM](https://github.com/MarquisDarwin/EAWM).

Reinforcement Learning · Multi-agent

Laurin Luttmann, Lin Xie

Self-improvement has emerged as a state-of-the-art paradigm in Neural Combinatorial Optimization (NCO), where models iteratively refine their policies by generating and imitating high-quality solutions. Despite strong empirical performance, existing methods face key limitations. Training is computationally expensive, as policy updates require sampling numerous candidate solutions per instance to extract a single expert trajectory. More fundamentally, these approaches fail to exploit the structure of combinatorial problems involving the coordination of multiple agents, such as vehicles in min-max routing or machines in scheduling. By supervising on single-action trajectories, they fail to exploit agent-permutation symmetries, where distinct sequences of actions yield identical solutions, hindering generalization and the ability to learn coordinated behavior. We address these challenges by extending self-improvement to operate over joint multi-agent actions. Our model architecture predicts complete agent-task assignments jointly at each decision step. To explicitly leverage symmetries, we employ a set-prediction loss, which supervises the policy on multiple expert assignments for any given state. This approach enhances sample efficiency and the model's ability to learn coordinated behavior. Furthermore, by generating multi-agent actions in parallel, it drastically accelerates the solution generation phase of the self-improvement loop. Empirically, we validate our method on several combinatorial problems, demonstrating consistent improvements in the quality of the final solution and a reduced generation latency compared to standard self-improvement.

Computer Vision · 3D Rendering & Reconstruction

Chen Shi, Shaoshuai Shi, Xiaoyang Lyu, Chunyang Liu, Kehua Sheng, Bo Zhang, Li Jiang

Feed-forward 3D reconstruction for autonomous driving has advanced rapidly, yet existing methods struggle with the joint challenges of sparse, non-overlapping camera views and complex scene dynamics. We present UniSplat, a general feed-forward framework that learns robust dynamic scene reconstruction through unified latent spatio-temporal fusion. UniSplat constructs a 3D latent scaffold, a structured representation that captures geometric and semantic scene context by leveraging pretrained foundation models. To effectively integrate information across spatial views and temporal frames, we introduce an efficient fusion mechanism that operates directly within the 3D scaffold, enabling consistent spatio-temporal alignment. To ensure complete and detailed reconstructions, we design a dual-branch decoder that generates dynamic-aware Gaussians from the fused scaffold by combining point-anchored refinement with voxel-based generation, and maintain a persistent memory of static Gaussians to enable streaming scene completion beyond current camera coverage. Extensive experiments on real-world datasets demonstrate that UniSplat achieves state-of-the-art performance in novel view synthesis, while providing robust and high-quality renderings even for viewpoints outside the original camera coverage.

Reinforcement Learning · Multi-agent

Junjie Sheng, Yantian Wang, Bo Jin, Hongyuan Zha, Jun Wang, Wenhao Li, Xiangfeng Wang

We focus on the relative over-generalization (RO) issue in fully cooperative multi-agent reinforcement learning (MARL). Existing methods show that endowing agents with reasoning can help mitigate RO empirically, but there is little theoretical insight. We first prove that RO is avoided when agents satisfy a consistent reasoning requirement. We then propose a new negotiated reasoning framework connecting reasoning and RO with theoretical guarantees. Based on it, we develop an algorithm called Stein variational negotiated reasoning (SVNR), which uses Stein variational gradient descent to form a negotiation policy that provably bypasses RO under maximum-entropy policy iteration. SVNR is further parameterized with neural networks for computational efficiency. Experiments demonstrate that SVNR significantly outperforms baselines on RO-challenged tasks, including Multi-Agent Particle World and MaMuJoCo, confirming its advantage in achieving better cooperation.

Yuqing Huang, Rongyang Zhang, Xuesong He, Xuyang Zhi, Hao Wang, Nuo Chen, Zongbo Liu, Xin Li, Feiyang Xu, Deguang Liu 等

The emergence of Large Language Models (LLMs) in chemistry marks a significant advancement in applying artificial intelligence to chemical sciences. While these models show promising potential, their effective application in chemistry demands sophisticated evaluation protocols that address the field's inherent complexities. To bridge this critical gap, we introduce ChemEval, an innovative hierarchical assessment framework specifically designed to evaluate LLMs' capabilities across chemical domains. Our methodology incorporates a distinctive four-tier progression system, spanning from basic chemical concepts to advanced theoretical principles. Sixty-two textual and multimodal tasks are designed to enable researchers to conduct fine-grained analysis of model capabilities and achieve precise evaluation via carefully crafted assessment protocols. The framework integrates carefully curated open-source datasets with expert-validated materials, ensuring both practical relevance and scientific rigor. In our experiments, we evaluated the performance of most main-stream LLMs using both zero-shot and few-shot approaches, with carefully designed examples and prompts. Results indicate that general-purpose LLMs, while proficient in understanding chemical literature and following instructions, struggle with tasks requiring deep chemical expertise. In contrast, chemical LLMs perform better in technical tasks but show limitations in general language processing. These findings highlight both the current limitations and future opportunities for LLMs in chemistry. Our research provides a systematic framework for advancing the application of artificial intelligence in chemical research, potentially facilitating new discoveries in the field.