arXiv subjects

Jiqian Dong

Publications and source records attributed to Jiqian Dong.

16 recordsLinked to original sources

arXiv2026

ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond

Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is a central challenge for autonomous machine learning and scientific discovery, as progress hinges on continuously managing evolving state, exploration decisions, and computational resources. Pioneering autoresearch agents, despite great success, still lack mechanisms for continuity, recovery from dead ends, and value-driven compute allocation, which inherently undermines overall search efficiency, wastes computational resources, and lowers the chance of ultimate success. To bridge this gap, we introduce ScienceFlow, an end-to-end autoresearch agent framework that organizes long-horizon research work into research segments grounded in executable workspaces. It represents research progress as recoverable executable states, enabling efficient exploration, revision, and execution. Transitions between research segments are governed by Executable-State Transition through Re-Anchoring (ESTRA), which selects either the live state or an archived state as the next anchor and determines whether to continue or redirect the research trajectory. An evidence-aware execution controller allocates resources to physical jobs based on resource availability, remaining budget, and validated progress. We evaluate ScienceFlow on tasks spanning machine learning, scientific modeling, and mathematical optimization. Results on diverse long-horizon benchmarks demonstrate its ability to sustain effective research processes, highlighted by a SOTA 70.22 percent Any-Medal score on the full MLE-bench within a 24-hour budget, outperforming prior reported results by 4.92 percentage points. The efficacy of ScienceFlow further demonstrates that efficient state management, adaptive exploration, and objective-aligned execution are critical for scaling autonomous research beyond short-horizon interactions.

cs.AI↗

arXiv2026

Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning

Reinforcement learning (RL) refines large language models (LLMs) by directly optimizing model behavior through reward signals. While accurate state value estimation is critical for stable training in classical RL, it remains an underexplored challenge in LLM post-training. In this work, we introduce the State Value Estimation Benchmark (SVEB) to assess state estimation within existing RL frameworks and show that critics in standard approaches like PPO collapse to a coarse group-average baseline. To address this, we propose two techniques: Numca, which leverages numerical spans as gradable milestones for state value estimation, and Hista, a framework that uses LLM's hidden states as representation to weighted average disjoint rollouts and their return. Extensive experiments demonstrate that both methods yield more accurate state value estimates and enhance training performance across different RL algorithms and model sizes without incurring significant computational overhead.

cs.LG↗

arXiv2026

Generative Models in Decision Making: A Survey

Generative models have fundamentally reshaped the landscape of decision-making, reframing the problem from pure scalar reward maximization to high-fidelity trajectory generation and distribution matching. This paradigm shift addresses intrinsic limitations in classical Reinforcement Learning (RL), particularly the limited expressivity of standard unimodal policy distributions in capturing complex, multi-modal behaviors embedded in diverse datasets. However, current literature often treats these models as isolated algorithmic improvements, rarely synthesizing them into a single comprehensive framework. This survey proposes a principled taxonomy grounding generative decision-making within the probabilistic framework of Control as Inference. By performing a variational factorization of the trajectory posterior, we conceptualize four distinct functional roles: Controllers for amortized policy inference, Modelers for dynamics priors, Optimizers for iterative trajectory refinement, and Evaluators for trajectory guidance and value assessment. Unlike existing architecture-centric reviews, this function-centric framework allows us to critically analyze representative generative families across distinct dimensions. Furthermore, we examine deployment in high-stakes domains, specifically Embodied AI, Autonomous Driving, and AI for Science, highlighting systemic risks such as dynamics hallucination in world models and proxy exploitation. Finally, we chart the path toward Generalist Physical Intelligence, identifying pivotal challenges in inference efficiency, trustworthiness, and the emergence of Physical Foundation Models.

cs.LG↗

arXiv2023

Deep Reinforcement Learning Based Framework for Mobile Energy Disseminator Dispatching to Charge On-the-Road Electric Vehicles

The exponential growth of electric vehicles (EVs) presents novel challenges in preserving battery health and in addressing the persistent problem of vehicle range anxiety. To address these concerns, wireless charging, particularly, Mobile Energy Disseminators (MEDs) have emerged as a promising solution. The MED is mounted behind a large vehicle and charges all participating EVs within a radius upstream of it. Unfortuantely, during such V2V charging, the MED and EVs inadvertently form platoons, thereby occupying multiple lanes and impairing overall corridor travel efficiency. In addition, constrained budgets for MED deployment necessitate the development of an effective dispatching strategy to determine optimal timing and locations for introducing the MEDs into traffic. This paper proposes a deep reinforcement learning (DRL) based methodology to develop a vehicle dispatching framework. In the first component of the framework, we develop a realistic reinforcement learning environment termed "ChargingEnv" which incorporates a reliable charging simulation system that accounts for common practical issues in wireless charging deployment, specifically, the charging panel misalignment. The second component, the Proximal-Policy Optimization (PPO) agent, is trained to control MED dispatching through continuous interactions with ChargingEnv. Numerical experiments were carried out to demonstrate the demonstrate the efficacy of the proposed MED deployment decision processor. The experiment results suggest that the proposed model can significantly enhance EV travel range while efficiently deploying a optimal number of MEDs. The proposed model is found to be not only practical in its applicability but also has promises of real-world effectiveness. The proposed model can help travelers to maximize EV range and help road agencies or private-sector vendors to manage the deployment of MEDs efficiently.

cs.RO↗

arXiv2023

Transfusor: Transformer Diffusor for Controllable Human-like Generation of Vehicle Lane Changing Trajectories

With ongoing development of autonomous driving systems and increasing desire for deployment, researchers continue to seek reliable approaches for ADS systems. The virtual simulation test (VST) has become a prominent approach for testing autonomous driving systems (ADS) and advanced driver assistance systems (ADAS) due to its advantages of fast execution, low cost, and high repeatability. However, the success of these simulation-based experiments heavily relies on the realism of the testing scenarios. It is needed to create more flexible and high-fidelity testing scenarios in VST in order to increase the safety and reliabilityof ADS and ADAS.To address this challenge, this paper introduces the "Transfusor" model, which leverages the transformer and diffusor models (two cutting-edge deep learning generative technologies). The primary objective of the Transfusor model is to generate highly realistic and controllable human-like lane-changing trajectories in highway scenarios. Extensive experiments were carried out, and the results demonstrate that the proposed model effectively learns the spatiotemporal characteristics of humans' lane-changing behaviors and successfully generates trajectories that closely mimic real-world human driving. As such, the proposed model can play a critical role of creating more flexible and high-fidelity testing scenarios in the VST, ultimately leading to safer and more reliable ADS and ADAS.

cs.AI↗

arXiv2021

Urban traffic dynamic rerouting framework: A DRL-based model with fog-cloud architecture

Past research and practice have demonstrated that dynamic rerouting framework is effective in mitigating urban traffic congestion and thereby improve urban travel efficiency. It has been suggested that dynamic rerouting could be facilitated using emerging technologies such as fog-computing which offer advantages of low-latency capabilities and information exchange between vehicles and roadway infrastructure. To address this question, this study proposes a two-stage model that combines GAQ (Graph Attention Network - Deep Q Learning) and EBkSP (Entropy Based k Shortest Path) using a fog-cloud architecture, to reroute vehicles in a dynamic urban environment and therefore to improve travel efficiency in terms of travel speed. First, GAQ analyzes the traffic conditions on each road and for each fog area, and then assigns a road index based on the information attention from both local and neighboring areas. Second, EBkSP assigns the route for each vehicle based on the vehicle priority and route popularity. A case study experiment is carried out to investigate the efficacy of the proposed model. At the model training stage, different methods are used to establish the vehicle priorities, and their impact on the results is assessed. Also, the proposed model is tested under various scenarios with different ratios of rerouting and background (non-rerouting) vehicles. The results demonstrate that vehicle rerouting using the proposed model can help attain higher speed and reduces possibility of severe congestion. This result suggests that the proposed model can be deployed by urban transportation agencies for dynamic rerouting and ultimately, to reduce urban traffic congestion.

cs.AI↗

arXiv2021

Addressing crash-imminent situations caused by human driven vehicle errors in a mixed traffic stream: a model-based reinforcement learning approach for CAV

It is anticipated that the era of fully autonomous vehicle operations will be preceded by a lengthy "Transition Period" where the traffic stream will be mixed, that is, consisting of connected autonomous vehicles (CAVs), human-driven vehicles (HDVs) and connected human-driven vehicles (CHDVs). In recognition of the fact that public acceptance of CAVs will hinge on safety performance of automated driving systems, and that there will likely be safety challenges in the early part of the transition period, significant research efforts have been expended in the development of safety-conscious automated driving systems. Yet still, there appears to be a lacuna in the literature regarding the handling of the crash-imminent situations that are caused by errant human driven vehicles (HDVs) in the vicinity of the CAV during operations on the roadway. In this paper, we develop a simple model-based Reinforcement Learning (RL) based system that can be deployed in the CAV to generate trajectories that anticipate and avoid potential collisions caused by drivers of the HDVs. The model involves an end-to-end data-driven approach that contains a motion prediction model based on deep learning, and a fast trajectory planning algorithm based on model predictive control (MPC). The proposed system requires no prior knowledge or assumption about the physical environment including the vehicle dynamics, and therefore represents a general approach that can be deployed on any type of vehicle (e.g., truck, buse, motorcycle, etc.). The framework is trained and tested in the CARLA simulator with multiple collision imminent scenarios, and the results indicate the proposed model can avoid the collision at high successful rate (>85%) even in highly compact and dangerous situations.

cs.RO↗

arXiv2021

Development and testing of an image transformer for explainable autonomous driving systems

In the last decade, deep learning (DL) approaches have been used successfully in computer vision (CV) applications. However, DL-based CV models are generally considered to be black boxes due to their lack of interpretability. This black box behavior has exacerbated user distrust and therefore has prevented widespread deployment DLCV models in autonomous driving tasks even though some of these models exhibit superiority over human performance. For this reason, it is essential to develop explainable DL models for autonomous driving task. Explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify anydefects and weaknesses of the model during the system development phase. In this paper, we propose an explainable end-to-end autonomous driving system based on "Transformer", a state-of-the-art (SOTA) self-attention based model, to map visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations. The model achieves a soft attention over the global features of the image. The results demonstrate the efficacy of our proposed model as it exhibits superior performance (in terms of correct prediction of actions and explanations) compared to the benchmark model by a significant margin with lower computational cost.

cs.CV↗

arXiv2021

Reason induced visual attention for explainable autonomous driving

Deep learning (DL) based computer vision (CV) models are generally considered as black boxes due to poor interpretability. This limitation impedes efficient diagnoses or predictions of system failure, thereby precluding the widespread deployment of DLCV models in safety-critical tasks such as autonomous driving. This study is motivated by the need to enhance the interpretability of DL model in autonomous driving and therefore proposes an explainable DL-based framework that generates textual descriptions of the driving environment and makes appropriate decisions based on the generated descriptions. The proposed framework imitates the learning process of human drivers by jointly modeling the visual input (images) and natural language, while using the language to induce the visual attention in the image. The results indicate strong explainability of autonomous driving decisions obtained by focusing on relevant features from visual inputs. Furthermore, the output attention maps enhance the interpretability of the model not only by providing meaningful explanation to the model behavior but also by identifying the weakness of and potential improvement directions for the model.

cs.CV↗

arXiv2020

Leveraging the Capabilities of Connected and Autonomous Vehicles and Multi-Agent Reinforcement Learning to Mitigate Highway Bottleneck Congestion

Active Traffic Management strategies are often adopted in real-time to address such sudden flow breakdowns. When queuing is imminent, Speed Harmonization (SH), which adjusts speeds in upstream traffic to mitigate traffic showckwaves downstream, can be applied. However, because SH depends on driver awareness and compliance, it may not always be effective in mitigating congestion. The use of multiagent reinforcement learning for collaborative learning, is a promising solution to this challenge. By incorporating this technique in the control algorithms of connected and autonomous vehicle (CAV), it may be possible to train the CAVs to make joint decisions that can mitigate highway bottleneck congestion without human driver compliance to altered speed limits. In this regard, we present an RL-based multi-agent CAV control model to operate in mixed traffic (both CAVs and human-driven vehicles (HDVs)). The results suggest that even at CAV percent share of corridor traffic as low as 10%, CAVs can significantly mitigate bottlenecks in highway traffic. Another objective was to assess the efficacy of the RL-based controller vis-à-vis that of the rule-based controller. In addressing this objective, we duly recognize that one of the main challenges of RL-based CAV controllers is the variety and complexity of inputs that exist in the real world, such as the information provided to the CAV by other connected entities and sensed information. These translate as dynamic length inputs which are difficult to process and learn from. For this reason, we propose the use of Graphical Convolution Networks (GCN), a specific RL technique, to preserve information network topology and corresponding dynamic length inputs. We then use this, combined with Deep Deterministic Policy Gradient (DDPG), to carry out multi-agent training for congestion mitigation using the CAV controllers.

cs.LG↗

arXiv2020

A DRL-based Multiagent Cooperative Control Framework for CAV Networks: a Graphic Convolution Q Network

Connected Autonomous Vehicle (CAV) Network can be defined as a collection of CAVs operating at different locations on a multilane corridor, which provides a platform to facilitate the dissemination of operational information as well as control instructions. Cooperation is crucial in CAV operating systems since it can greatly enhance operation in terms of safety and mobility, and high-level cooperation between CAVs can be expected by jointly plan and control within CAV network. However, due to the highly dynamic and combinatory nature such as dynamic number of agents (CAVs) and exponentially growing joint action space in a multiagent driving task, achieving cooperative control is NP hard and cannot be governed by any simple rule-based methods. In addition, existing literature contains abundant information on autonomous driving's sensing technology and control logic but relatively little guidance on how to fuse the information acquired from collaborative sensing and build decision processor on top of fused information. In this paper, a novel Deep Reinforcement Learning (DRL) based approach combining Graphic Convolution Neural Network (GCN) and Deep Q Network (DQN), namely Graphic Convolution Q network (GCQ) is proposed as the information fusion module and decision processor. The proposed model can aggregate the information acquired from collaborative sensing and output safe and cooperative lane changing decisions for multiple CAVs so that individual intention can be satisfied even under a highly dynamic and partially observed mixed traffic. The proposed algorithm can be deployed on centralized control infrastructures such as road-side units (RSU) or cloud platforms to improve the CAV operation.

cs.AI↗

arXiv2020

A Cooperative Control Framework for CAV Lane Change in a Mixed Traffic Environment

In preparing for connected and autonomous vehicles (CAVs), a worrisome aspect is the transition era which will be characterized by mixed traffic (where CAVs and human-driven vehicles (HDVs) share the roadway). Consistent with expectations that CAVs will improve road safety, on-road CAVs may adopt rather conservative control policies, and this will likely cause HDVs to unduly exploit CAV conservativeness by driving in ways that imperil safety. A context of this situation is lane-changing by the CAV. Without cooperation from other vehicles in the traffic stream, it can be extremely unsafe for the CAV to change lanes under dense, high-speed traffic conditions. The cooperation of neighboring vehicles is indispensable. To address this issue, this paper develops a control framework where connected HDVs and CAV can cooperate to facilitate safe and efficient lane changing by the CAV. Throughout the lane-change process, the safety of not only the CAV but also of all neighboring vehicles, is ensured through a collision avoidance mechanism in the control framework. The overall traffic flow efficiency is analyzed in terms of the ambient level of CHDV-CAV cooperation. The analysis outcomes are including the CAVs lane-change feasibility, the overall duration of the lane change. Lane change is a major source of traffic disturbance at multi-lane highways that impair their traffic flow efficiency. In providing a control framework for lane change in mixed traffic, this study shows how CHDV-CAV cooperation could help enhancing system efficiency.

eess.SY↗

arXiv2020

Using Empirical Trajectory Data to Design Connected Autonomous Vehicle Controllers for Traffic Stabilization

Emerging transportation technologies offer unprecedented opportunities to improve the efficiency of the transportation system from the perspectives of energy consumption, congestion, and emissions. One of these technologies is connected and autonomous vehicles (CAVs). With the prospective duality of operations of CAVs and human driven vehicles in the same roadway space (also referred to as a mixed stream), CAVs are expected to address a variety of traffic problems particularly those that are either caused or exacerbated by the heterogeneous nature of human driving. In efforts to realize such specific benefits of CAVs in mixed-stream traffic, it is essential to understand and simulate the behavior of human drivers in such environments, and microscopic traffic flow (MTF) models can be used to carry out this task. By helping to comprehend the fundamental dynamics of traffic flow, MTF models serve as a powerful approach to assess the impacts of such flow in terms of safety, stability, and efficiency. In this paper, we seek to calibrate MTF models based on empirical trajectory data as basis of not only understanding traffic dynamics such as traffic instabilities, but ultimately using CAVs to mitigate stop-and-go wave propagation. The paper therefore duly considers the heterogeneity and uncertainty associated with human driving behavior in order to calibrate the dynamics of each HDV. Also, the paper designs the CAV controllers based on the microscopic HDV models that are calibrated in real time. The data for the calibration is from the Next Generation SIMulation (NGSIM) trajectory datasets. The results are encouraging, as they indicate the efficacy of the designed controller to significantly improve not only the stability of the mixed traffic stream but also the safety of both CAVs and HDVs in the traffic stream.

eess.SY↗

arXiv2020

Facilitating Connected Autonomous Vehicle Operations Using Space-weighted Information Fusion and Deep Reinforcement Learning Based Control

The connectivity aspect of connected autonomous vehicles (CAV) is beneficial because it facilitates dissemination of traffic-related information to vehicles through Vehicle-to-External (V2X) communication. Onboard sensing equipment including LiDAR and camera can reasonably characterize the traffic environment in the immediate locality of the CAV. However, their performance is limited by their sensor range (SR). On the other hand, longer-range information is helpful for characterizing imminent conditions downstream. By contemporaneously coalescing the short- and long-range information, the CAV can construct comprehensively its surrounding environment and thereby facilitate informed, safe, and effective movement planning in the short-term (local decisions including lane change) and long-term (route choice). In this paper, we describe a Deep Reinforcement Learning based approach that integrates the data collected through sensing and connectivity capabilities from other vehicles located in the proximity of the CAV and from those located further downstream, and we use the fused data to guide lane changing, a specific context of CAV operations. In addition, recognizing the importance of the connectivity range (CR) to the performance of not only the algorithm but also of the vehicle in the actual driving environment, the paper carried out a case study. The case study demonstrates the application of the proposed algorithm and duly identifies the appropriate CR for each level of prevailing traffic density. It is expected that implementation of the algorithm in CAVs can enhance the safety and mobility associated with CAV driving operations. From a general perspective, its implementation can provide guidance to connectivity equipment manufacturers and CAV operators, regarding the default CR settings for CAVs or the recommended CR setting in a given traffic environment.

cs.AI↗

arXiv2020

Leveraging Vehicle Connectivity and Autonomy to Stabilize Flow in Mixed Traffic Conditions: Accounting for Human-driven Vehicle Driver Behavioral Heterogeneity and Perception-reaction Time Delay

The erratic nature of human driving tends to trigger undesired waves that amplify as successive driver reactions propagate from the errant vehicle to vehicles upstream. Known as phantom jams, this phenomenon has been identified in the literature as one of the main causes of traffic congestion. This paper is based on the premise that vehicle automation and connectivity can help mitigate such jams. In the paper, we design a controller for use in a connected and autonomous vehicle (CAV) to stabilize the flow of human-driven vehicles (HDVs) that are upstream of the CAV, and consequently to lower collision risk in the upstream traffic environment. In modeling the HDV dynamics in the mixed traffic stream, we duly consider HDV driver heterogeneity and the time delays associated with their perception reaction time. We can find that the maximum number of HDVs that a CAV can stabilize is lower when human drivers potential time delay and heterogeneity are considered, compared to the scenario where such are not considered. This result suggests that heterogeneity and time delay in HDV behavior impairs the CAVs capability to stabilize traffic. Therefore, in designing CAV controllers for traffic stabilization, it is essential to consider such uncertainty-related conditions. In our demonstration, we also show that the designed controller can significantly improve both the stability of the mixed traffic stream and the safety of both CAVs and HDVs in the stream. The results are useful for real-time calibration of the model parameters that characterize HDV movements in the mixed stream.

eess.SY↗

arXiv2018

A Dynamic Network and Representation LearningApproach for Quantifying Economic Growth fromSatellite Imagery

Quantifying the improvement in human living standard, as well as the city growth in developing countries, is a challenging problem due to the lack of reliable economic data. Therefore, there is a fundamental need for alternate, largely unsupervised, computational methods that can estimate the economic conditions in the developing regions. To this end, we propose a new network science- and representation learning-based approach that can quantify economic indicators and visualize the growth of various regions. More precisely, we first create a dynamic network drawn out of high-resolution nightlight satellite images. We then demonstrate that using representation learning to mine the resulting network, our proposed approach can accurately predict spatial gross economic expenditures over large regions. Our method, which requires only nightlight images and limited survey data, can capture city-growth, as well as how people's living standard is changing; this can ultimately facilitate the decision makers' understanding of growth without heavily relying on expensive and time-consuming surveys.

cs.SI↗