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%.
Sample efficiency and exploration remain critical challenges in Deep Reinforcement Learning (DRL), particularly in complex domains. Offline RL, which enables agents to learn optimal policies from static, pre-collected datasets, has emerged as a promising alternative. However, offline RL is constrained by issues such as out-of-distribution (OOD) actions that limit policy performance and generalization. To overcome these limitations, we propose Meta Offline-Online Reinforcement Learning (MOORL), a hybrid framework that unifies offline and online RL for efficient and scalable learning. While previous hybrid methods rely on extensive design components and added computational complexity to utilize offline data effectively, MOORL introduces a meta-policy that seamlessly adapts across offline and online trajectories. This enables the agent to leverage offline data for robust initialization while utilizing online interactions to drive efficient exploration. Our theoretical analysis demonstrates that the hybrid approach enhances exploration by effectively combining the complementary strengths of offline and online data. Furthermore, we demonstrate that MOORL learns a stable Q-function without added complexity. Extensive experiments on 28 tasks from the D4RL and V-D4RL benchmarks validate its effectiveness, showing consistent improvements over state-of-the-art offline and hybrid RL baselines. With minimal computational overhead, MOORL achieves strong performance, underscoring its potential for practical applications in real-world scenarios.
Symbolic regression is a fundamental tool for discovering interpretable mathematical expressions from data, with broad applications across scientific and engineering domains. Recently, large language models (LLMs) have demonstrated strong performance in this task, leveraging embedded scientific priors and reasoning capabilities to surpass traditional methods. However, existing LLM-based approaches, such as LLM-SR, often over-rely on internal priors, lacking explicit data understanding and systematic reflection during equation generation. To address these limitations, we propose DrSR (Dual Reasoning Symbolic Regression), a framework that combines data-driven insight with reflective learning to enhance both robustness and discovery capability. Specifically, DrSR guides LLMs to analyze structural relationships (e.g., monotonicity, nonlinearity, and correlation) within the data to generate structured descriptions. Simultaneously, it monitors equation performance and establishes a feedback loop to refine subsequent generations. By integrating data understanding and generation reflection in a closed loop, DrSR enables more efficient exploration of the symbolic expression space. Experiments across interdisciplinary datasets in physics, chemistry, biology, and materials science demonstrate that DrSR substantially improves the valid equation rate and consistently outperforms both classical and recent LLM-based methods in terms of accuracy, generalization, and search efficiency. These results underscore its potential for scientific equation discovery.
Language-instructed active object localization is a critical challenge for robots, requiring efficient exploration of partially observable environments. However, state-of-the-art approaches either struggle to generalize beyond demonstration datasets (e.g., imitation learning methods) or fail to generate physically grounded actions (e.g., VLMs). To address these limitations, we introduce WoMAP (World Models for Active Perception): a recipe for training open-vocabulary object localization policies that: (i) uses a Gaussian Splatting-based real-to-sim-to-real pipeline for scalable data generation without the need for expert demonstrations, (ii) distills dense rewards signals from open-vocabulary object detectors, and (iii) leverages a latent world model for dynamics and rewards prediction to ground high-level action proposals at inference time. Rigorous simulation and hardware experiments demonstrate WoMAP's superior performance in a broad range of zero-shot object localization tasks, with more than 9x and 2x higher success rates compared to VLM and diffusion policy baselines, respectively. Further, we show that WoMAP achieves strong generalization and sim-to-real transfer on a TidyBot.
Protein binder design is central to therapeutics, diagnostics, and synthetic biology, yet practical deployment remains challenging due to fragmented workflows, high computational costs, and complex tool integration. We present HelixDesign-Binder, a production-grade, high-throughput platform built on HelixFold3 that automates the full binder design pipeline, from backbone generation and sequence design to structural evaluation and multi-dimensional scoring. By unifying these stages into a scalable and user-friendly system, HelixDesign-Binder enables efficient exploration of binder candidates with favorable structural, energetic, and physicochemical properties. The platform leverages Baidu Cloud's high-performance infrastructure to support large-scale design and incorporates advanced scoring metrics, including ipTM, predicted binding free energy, and interface hydrophobicity. Benchmarking across six protein targets demonstrates that HelixDesign-Binder reliably produces diverse and high-quality binders, some of which match or exceed validated designs in predicted binding affinity. HelixDesign-Binder is accessible via an interactive web interface in PaddleHelix platform, supporting both academic research and industrial applications in antibody and protein binder development.
Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven construction. We introduce MermaidFlow, a framework that redefines the agentic search space through safety-constrained graph evolution. At its core, MermaidFlow represent workflows as a verifiable intermediate representation using Mermaid, a structured and human-interpretable graph language. We formulate domain-aware evolutionary operators, i.e., crossover, mutation, insertion, and deletion, to preserve semantic correctness while promoting structural diversity, enabling efficient exploration of a high-quality, statically verifiable workflow space. Without modifying task settings or evaluation protocols, MermaidFlow achieves consistent improvements in success rates and faster convergence to executable plans on the agent reasoning benchmark. The experimental results demonstrate that safety-constrained graph evolution offers a scalable, modular foundation for robust and interpretable agentic reasoning systems.
Sparse-reward reinforcement learning (RL) can model a wide range of highly complex tasks. Solving sparse-reward tasks is RL's core premise - requiring efficient exploration coupled with long-horizon credit assignment - and overcoming these challenges is key for building self-improving agents with superhuman ability. We argue that solving complex and high-dimensional tasks requires solving simpler tasks that are relevant to the target task. In contrast, most prior work designs strategies for selecting exploratory tasks with the objective of solving any task, making exploration of challenging high-dimensional, long-horizon tasks intractable. We find that the sense of direction, necessary for effective exploration, can be extracted from existing RL algorithms, without needing any prior information. Based on this finding, we propose a method for directed sparse-reward goal-conditioned very long-horizon RL (DISCOVER), which selects exploratory goals in the direction of the target task. We connect DISCOVER to principled exploration in bandits, formally bounding the time until the target task becomes achievable in terms of the agent's initial distance to the target, but independent of the volume of the space of all tasks. Empirically, we perform a thorough evaluation in high-dimensional environments. We find that the directed goal selection of DISCOVER solves exploration problems that are beyond the reach of prior state-of-the-art exploration methods in RL.
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, yet they lag significantly behind humans in spatial reasoning. We investigate this gap through Transformation-Driven Visual Reasoning (TVR), a challenging task requiring identification of object transformations across images under varying viewpoints. While traditional Supervised Fine-Tuning (SFT) fails to generate coherent reasoning paths in cross-view settings, sparse-reward Reinforcement Learning (RL) suffers from inefficient exploration and slow convergence. To address these limitations, we propose STAR-R1, a novel framework that integrates a single-stage RL paradigm with a fine-grained reward mechanism tailored for TVR. Specifically, STAR-R1 rewards partial correctness while penalizing excessive enumeration and passive inaction, enabling efficient exploration and precise reasoning. Comprehensive evaluations demonstrate that STAR-R1 achieves state-of-the-art performance across all 11 metrics, outperforming SFT by 23% in cross-view scenarios. Further analysis reveals STAR-R1's anthropomorphic behavior and highlights its unique ability to compare all objects for improving spatial reasoning. Our work provides critical insights in advancing the research of MLLMs and reasoning models. The codes, model weights, and data will be publicly available at https://github.com/zongzhao23/STAR-R1.
As climate change increases the threat of weather-related disasters, research on weather control is gaining importance. The objective of weather control is to mitigate disaster risks by administering interventions with optimal timing, location, and intensity. However, the optimization process is highly challenging due to the vast scale and complexity of weather phenomena, which introduces two major challenges. First, obtaining accurate gradient information for optimization is difficult. In addition, numerical weather prediction (NWP) models demand enormous computational resources, necessitating parameter optimization with minimal function evaluations. To address these challenges, this study proposes a method for designing weather interventions based on black-box optimization, which enables efficient exploration without requiring gradient information. The proposed method is evaluated in two distinct control scenarios: one-shot initial value intervention and sequential intervention based on model predictive control. Furthermore, a comparative analysis is conducted among four representative black-box optimization methods in terms of total rainfall reduction. Experimental results show that Bayesian optimization achieves higher control effectiveness than the others, particularly in high-dimensional search spaces. These findings suggest that Bayesian optimization is a highly effective approach for weather intervention computation.
Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promotes generalization through exploration. While existing robot learning approaches using IL-based pre-training followed by RL-based fine-tuning are promising, this two-step learning paradigm often suffers from instability and poor sample efficiency during the RL fine-tuning phase. In this work, we introduce IN-RIL, INterleaved Reinforcement learning and Imitation Learning, for policy fine-tuning, which periodically injects IL updates after multiple RL updates and hence can benefit from the stability of IL and the guidance of expert data for more efficient exploration throughout the entire fine-tuning process. Since IL and RL involve different optimization objectives, we develop gradient separation mechanisms to prevent destructive interference during \ABBR fine-tuning, by separating possibly conflicting gradient updates in orthogonal subspaces. Furthermore, we conduct rigorous analysis, and our findings shed light on why interleaving IL with RL stabilizes learning and improves sample-efficiency. Extensive experiments on 14 robot manipulation and locomotion tasks across 3 benchmarks, including FurnitureBench, OpenAI Gym, and Robomimic, demonstrate that \ABBR can significantly improve sample efficiency and mitigate performance collapse during online finetuning in both long- and short-horizon tasks with either sparse or dense rewards. IN-RIL, as a general plug-in compatible with various state-of-the-art RL algorithms, can significantly improve RL fine-tuning, e.g., from 12\% to 88\% with 6.3x improvement in the success rate on Robomimic Transport. Project page: https://github.com/ucd-dare/IN-RIL.
We study policy distillation under privileged information, where a student policy with only partial observations must learn from a teacher with full-state access. A key challenge is information asymmetry: the student cannot directly access the teacher's state space, leading to distributional shifts and policy degradation. Existing approaches either modify the teacher to produce realizable but sub-optimal demonstrations or rely on the student to explore missing information independently, both of which are inefficient. Our key insight is that the student should strategically interact with the teacher --querying only when necessary and resetting from recovery states --to stay on a recoverable path within its own observation space. We introduce two methods: (i) an imitation learning approach that adaptively determines when the student should query the teacher for corrections, and (ii) a reinforcement learning approach that selects where to initialize training for efficient exploration. We validate our methods in both simulated and real-world robotic tasks, demonstrating significant improvements over standard teacher-student baselines in training efficiency and final performance. The project website is available at : https://portal-cornell.github.io/CritiQ_ReTRy/
Language model (LM) agents are increasingly used as autonomous decision-makers who need to actively gather information to guide their decisions. A crucial cognitive skill for such agents is the efficient exploration and understanding of the causal structure of the world -- key to robust, scientifically grounded reasoning. Yet, it remains unclear whether LMs possess this capability or exhibit systematic biases leading to erroneous conclusions. In this work, we examine LMs' ability to explore and infer causal relationships, using the well-established "Blicket Test" paradigm from developmental psychology. We find that LMs reliably infer the common, intuitive disjunctive causal relationships but systematically struggle with the unusual, yet equally (or sometimes even more) evidenced conjunctive ones. This "disjunctive bias" persists across model families, sizes, and prompting strategies, and performance further declines as task complexity increases. Interestingly, an analogous bias appears in human adults, suggesting that LMs may have inherited deep-seated reasoning heuristics from their training data. To this end, we quantify similarities between LMs and humans, finding that LMs exhibit adult-like inference profiles (but not children-like). Finally, we propose a test-time sampling method which explicitly samples and eliminates hypotheses about causal relationships from the LM. This scalable approach significantly reduces the disjunctive bias and moves LMs closer to the goal of scientific, causally rigorous reasoning.
Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL). Without clear feedback on actions at each step in sparse-reward setting, previous methods struggle with precise credit assignment among agents and effective exploration. In this paper, we introduce a novel method to deal with both credit assignment and exploration problems in reward-sparse domains. Accordingly, we propose an algorithm that calculates the Influence Scope of Agents (ISA) on states by taking specific value of the dimensions/attributes of states that can be influenced by individual agents. The mutual dependence between agents' actions and state attributes are then used to calculate the credit assignment and to delimit the exploration space for each individual agent. We then evaluate ISA in a variety of sparse-reward multi-agent scenarios. The results show that our method significantly outperforms the state-of-art baselines.
We developed an interpretability informed Bayesian optimization framework to optimize underwater acoustic coatings based on polyurethane elastomers with embedded metamaterial features. A data driven model was employed to analyze the relationship between acoustic performance, specifically sound absorption and the corresponding design variables. By leveraging SHapley Additive exPlanations (SHAP), a machine learning interpretability tool, we identified the key parameters influencing the objective function and gained insights into how these parameters affect sound absorption. The insights derived from the SHAP analysis were subsequently used to automatically refine the bounds of the optimization problem automatically, enabling a more targeted and efficient exploration of the design space. The proposed approach was applied to two polyurethane materials with distinct hardness levels, resulting in improved optimal solutions compared to those obtained without SHAP-informed guidance. Notably, these enhancements were achieved without increasing the number of simulation iterations. Our findings demonstrate the potential of SHAP to streamline optimization processes by uncovering hidden parameter relationships and guiding the search toward promising regions of the design space. This work underscores the effectiveness of combining interpretability techniques with Bayesian optimization for the efficient and cost-effective design of underwater acoustic metamaterials under strict computational constraints and can be generalized towards other materials and engineering optimization problems.
Efficient exploration is critical for learning relational models in large-scale environments with complex, long-horizon tasks. Random exploration methods often collect redundant or irrelevant data, limiting their ability to learn accurate relational models of the environment. Goal-literal babbling (GLIB) improves upon random exploration by setting and planning to novel goals, but its reliance on random actions and random novel goal selection limits its scalability to larger domains. In this work, we identify the principles underlying efficient exploration in relational domains: (1) operator initialization with demonstrations that cover the distinct lifted effects necessary for planning and (2) refining preconditions to collect maximally informative transitions by selecting informative goal-action pairs and executing plans to them. To demonstrate these principles, we introduce Baking-Large, a challenging domain with extensive state-action spaces and long-horizon tasks. We evaluate methods using oracle-driven demonstrations for operator initialization and precondition-targeting guidance to efficiently gather critical transitions. Experiments show that both the oracle demonstrations and precondition-targeting oracle guidance significantly improve sample efficiency and generalization, paving the way for future methods to use these principles to efficiently learn accurate relational models in complex domains.
The recent global spread of monkeypox, particularly in regions where it has not historically been prevalent, has raised significant public health concerns. Early and accurate diagnosis is critical for effective disease management and control. In response, this study proposes a novel deep learning-based framework for the automated detection of monkeypox from skin lesion images, leveraging the power of transfer learning, dimensionality reduction, and advanced machine learning techniques. We utilize the newly developed Monkeypox Skin Lesion Dataset (MSLD), which includes images of monkeypox, chickenpox, and measles, to train and evaluate our models. The proposed framework employs the Xception architecture for deep feature extraction, followed by Principal Component Analysis (PCA) for dimensionality reduction, and the Natural Gradient Boosting (NGBoost) algorithm for classification. To optimize the model's performance and generalization, we introduce the African Vultures Optimization Algorithm (AVOA) for hyperparameter tuning, ensuring efficient exploration of the parameter space. Our results demonstrate that the proposed AVOA-NGBoost model achieves state-of-the-art performance, with an accuracy of 97.53%, F1-score of 97.72% and an AUC of 97.47%. Additionally, we enhance model interpretability using Grad-CAM and LIME techniques, providing insights into the decision-making process and highlighting key features influencing classification. This framework offers a highly precise and efficient diagnostic tool, potentially aiding healthcare providers in early detection and diagnosis, particularly in resource-constrained environments.
An integration of satellites and terrestrial networks is crucial for enhancing performance of next generation communication systems. However, the networks are hindered by the long-distance path loss and security risks in dense urban environments. In this work, we propose a satellite-terrestrial covert communication system assisted by the aerial active simultaneous transmitting and reflecting reconfigurable intelligent surface (AASTAR-RIS) to improve the channel capacity while ensuring the transmission covertness. Specifically, we first derive the minimal detection error probability (DEP) under the worst condition that the Warden has perfect channel state information (CSI). Then, we formulate an AASTAR-RIS-assisted satellite-terrestrial covert communication optimization problem (ASCCOP) to maximize the sum of the fair channel capacity for all ground users while meeting the strict covert constraint, by jointly optimizing the trajectory and active beamforming of the AASTAR-RIS. Due to the challenges posed by the complex and high-dimensional state-action spaces as well as the need for efficient exploration in dynamic environments, we propose a generative deterministic policy gradient (GDPG) algorithm, which is a generative deep reinforcement learning (DRL) method to solve the ASCCOP. Concretely, the generative diffusion model (GDM) is utilized as the policy representation of the algorithm to enhance the exploration process by generating diverse and high-quality samples through a series of denoising steps. Moreover, we incorporate an action gradient mechanism to accomplish the policy improvement of the algorithm, which refines the better state-action pairs through the gradient ascent. Simulation results demonstrate that the proposed approach significantly outperforms important benchmarks.
Understanding how humans leverage prior knowledge to navigate unseen environments while making exploratory decisions is essential for developing autonomous robots with similar abilities. In this work, we propose ForesightNav, a novel exploration strategy inspired by human imagination and reasoning. Our approach equips robotic agents with the capability to predict contextual information, such as occupancy and semantic details, for unexplored regions. These predictions enable the robot to efficiently select meaningful long-term navigation goals, significantly enhancing exploration in unseen environments. We validate our imagination-based approach using the Structured3D dataset, demonstrating accurate occupancy prediction and superior performance in anticipating unseen scene geometry. Our experiments show that the imagination module improves exploration efficiency in unseen environments, achieving a 100% completion rate for PointNav and an SPL of 67% for ObjectNav on the Structured3D Validation split. These contributions demonstrate the power of imagination-driven reasoning for autonomous systems to enhance generalizable and efficient exploration.
The green vehicle routing problem with private capacitated alternative fuel stations (GVRP-PCAFS) extends the traditional green vehicle routing problem by considering refueling stations limited capacity, where a limited number of vehicles can refuel simultaneously with additional vehicles must wait. This feature presents new challenges for route planning, as waiting times at stations must be managed while keeping route durations within limits and reducing total travel distance. This article presents METS, a novel memetic algorithm (MA) with separate constraint-based tour segmentation (SCTS) and efficient local search (ELS) for solving GVRP-PCAFS. METS combines global and local search effectively through three novelties. For global search, the SCTS strategy splits giant tours to generate diverse solutions, and the search process is guided by a comprehensive fitness evaluation function to dynamically control feasibility and diversity to produce solutions that are both diverse and near-feasible. For local search, ELS incorporates tailored move operators with constant-time move evaluation mechanisms, enabling efficient exploration of large solution neighborhoods. Experimental results demonstrate that METS discovers 31 new best-known solutions out of 40 instances in existing benchmark sets, achieving substantial improvements over current state-of-the-art methods. Additionally, a new large-scale benchmark set based on real-world logistics data is introduced to facilitate future research.
Training LLMs in distributed environments presents significant challenges due to the complexity of model execution, deployment systems, and the vast space of configurable strategies. Although various optimization techniques exist, achieving high efficiency in practice remains difficult. Accurate performance models that effectively characterize and predict a model's behavior are essential for guiding optimization efforts and system-level studies. We propose Lumos, a trace-driven performance modeling and estimation toolkit for large-scale LLM training, designed to accurately capture and predict the execution behaviors of modern LLMs. We evaluate Lumos on a production ML cluster with up to 512 NVIDIA H100 GPUs using various GPT-3 variants, demonstrating that it can replay execution time with an average error of just 3.3%, along with other runtime details, across different models and configurations. Additionally, we validate its ability to estimate performance for new setups from existing traces, facilitating efficient exploration of model and deployment configurations.