Searcharxiv⌕ Search

arXiv subjects

Cathy Wu

Publications and source records attributed to Cathy Wu.

At least 19 recordsLinked to original sources
arXiv2026

Formalizing and Estimating Task-Space Complexity for Zero-shot Generalization

Generalization is crucial for modern control, but learning across tasks can be costly. Recent work shows that zero-shot transfer, in which a controller designed for a source task is directly deployed to a target task, can achieve strong performance. We formalize task-space complexity, which characterizes the difficulty of achieving sufficiently good performance across a collection of tasks, by casting source selection as a covering problem. We provide bounds on the complexity and demonstrate its applicability.

cs.LG↗
arXiv2026

Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latents

In a decentralized multi-robot team under partial observability, the fact that decides a robot's next action is often visible only to a teammate. Existing decentralized methods communicate kinematic information, such as position or planned trajectory, which cannot convey what the teammate perceives. Learned communication in multi-agent reinforcement learning (MARL) can carry perceptual content, but the resulting messages are task-coupled and opaque. We propose Latent Telepathy. Each robot broadcasts the perceptual latent vector it already computes for its own use, the output of an encoder trained with a self-supervised joint-embedding predictive objective, frozen, and shared across the team. A teammate learns to act on it from task reward alone. Because the encoder already runs for perception, the message costs no additional computation and a single compact vector of bandwidth. Because the encoder is frozen before any policy is trained, the message means the same thing to every robot, and the receiving robot is never told what it means. We evaluate Latent Telepathy with a content-controlled protocol in which bandwidth, latency, topology and receiver are held fixed and only the message content varies. Broadcasting the latent lets a navigator avoid an occluded hazard in 99.7% of episodes, matching a noiseless hand-designed message. Position and trajectory messages remain at chance, and the raw camera image, 186 times wider, is less reliable than the compressed latent. The result holds from a discrete gridworld to rendered pixels under continuous velocity control, and the encoder decodes the hazard from a physical robot's camera in 102 of 102 live decisions. We also identify a requirement for porting MARL communication results to continuous control, that the decision a message informs must remain reachable by exploration, and show how to restore it.

cs.RO↗
arXiv2026

VISTA: A Visual Harness for Reasoning in an Interactive World

We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments. We introduce VISTA, a visual harness that gives a general-purpose multimodal model long-horizon vision. VISTA allows the model to directly perceive the environment through visual observations and maintains a lossless visual memory that preserves past observations in their original form. The model can actively retrieve these observations and reorganize its visual input as it reasons. On ARC-AGI-3, VISTA improves Claude Opus 5.0's Relative Human Action Efficiency score from 40.68 to a perfect 100.00, with the model completing all 25 public games using 57.4% fewer actions than first-time human participants. VISTA's simple design also allows it to extend naturally to diverse visual environments with minimal adaptation. Across three additional benchmarks covering a diverse range of visual games and puzzles, it substantially outperforms baselines using the same underlying model with minimal harnesses. Our results highlight VISTA's potential as a general-purpose visual harness for advancing multimodal agents in complex visual environments.

cs.AI↗
arXiv2026

On the Input Sensitivity of METANET Models and the Robustness of Dynamic Calibration

While traffic modeling and control rely upon effective calibration of macroscopic traffic simulation models like METANET, recent empirical work shows these models can exhibit severe sensitivity to input noise. This paper explains this phenomenon through a string-stability analysis, demonstrating that a calibrated METANET model can amplify small additive perturbations to boundary conditions along the corridor, causing the simulated state to diverge from the nominal baseline. The input sensitivity in off-nominal cases may compromise the model's capabilities for counterfactual analysis, which is required for use cases of interest like the design of large-scale variable speed limits. To address these issues, this work demonstrates how a dynamic, time-varying approach to calibrate model parameters can achieve robustness and improved accuracy of the resulting macrosimulation. We show analytically that under stated regularity and perturbation assumptions, dynamic calibration achieves a tighter cost deviation bound than static calibration, and we validate this behavior in highway environments with synthetic and real-world data. Ultimately, this can enable more trustworthy traffic simulation and more effective evaluation of control strategies.

eess.SY↗
arXiv2026

Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning

In LLM Reinforcement Fine-Tuning (RFT), curriculum learning drives both efficiency and performance. Yet, current methods externalize curriculum judgment via handcrafted heuristics or auxiliary models, risking misalignment with the policy's training dynamics. In this paper, we introduce METIS (METacognitive Internalized Self-judgment), a novel framework that internalizes curriculum judgment as a native capability. Leveraging a critical observation that within-prompt reward variance effectively gauges prompt informativeness, METIS predicts this metric based on recent training outcomes as lightweight in-context learning examples. This intrinsic self-judgment then dynamically dictates the training allocation. Moreover, METIS closes the loop between judgment and optimization by jointly optimizing the standard RFT rewards and a self-judgment reward. This allows the policy to learn what to learn next, as a form of metacognition. Across mathematical reasoning, code generation, and agentic function-calling benchmarks, METIS delivers superior performance while achieving up to a 2.1x training speedup, with controlled ablations and in-depth analysis further validating the benefits of internalized curriculum judgment. By bypassing handcrafted heuristics and auxiliary models, our work establishes a simple, closed-loop, and highly efficient curriculum internalization paradigm for LLM reinforcement fine-tuning.

cs.LG↗
arXiv2026

CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery

Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded exploration rules, which limit the autonomy of LLM agents. We present CORAL, the first framework for autonomous multi-agent evolution on open-ended problems. CORAL replaces rigid control with long-running agents that explore, reflect, and collaborate through shared persistent memory, asynchronous multi-agent execution, and heartbeat-based interventions. It also provides practical safeguards, including isolated workspaces, evaluator separation, resource management, and agent session and health management. Evaluated on diverse mathematical, algorithmic, and systems optimization tasks, CORAL sets new state-of-the-art results on 10 tasks, achieving 3-10 times higher improvement rates with far fewer evaluations than fixed evolutionary search baselines across tasks. On Anthropic's kernel engineering task, four co-evolving agents improve the best known score from 1363 to 1103 cycles. Mechanistic analyses further show how these gains arise from knowledge reuse and multi-agent exploration and communication. Together, these results suggest that greater agent autonomy and multi-agent evolution can substantially improve open-ended discovery. Code is available at https://github.com/Human-Agent-Society/CORAL.

cs.AI↗
arXiv2026

The Calibration Illusion in Traffic Microsimulation

The transportation community seeks to use calibration methods for highway traffic microsimulation. This is a response to the time-consuming and subjective nature of traditional manual calibration, as well as the growing prevalence of data for calibration. This work argues that this "automatic" calibration is largely an illusion. A significant - and unquantified - amount of bespoke manual work is hidden behind these methods. This illusion inhibits a core component of scientific advancement: objective comparison against a shared standard. This impedes evaluation, undermines reproducibility, and fragments research. To address this gap, this paper introduces a comprehensive benchmark designed to simultaneously expose the calibration illusion for highway microsimulation and provide a common ruler. The results across a range of scenarios present a new baseline for what the algorithms can achieve without bespoke tuning, revealing the research gap that remains and providing a tool to advance a cumulative science of calibration. Additional experiments provide insights into the source of calibration errors that arise in large-scale highway calibration relative to the simplified settings under which methods are commonly developed.

eess.SY↗
arXiv2026

Toward Controllability-Aware Performance Measures: A Case Study on Controllable Highway Congestion

Advancements in emerging intelligent transportation systems (ITS) have shown immense benefit in reducing congestion, emissions, and accidents and enable lower-cost alternatives to highway lane expansion. However, there currently exists no standard metric by which agencies can assess the improvement potential from these interventions. As a result, they may fail to deploy infrastructure where it will be most promising or risk investing in infrastructure that does not meaningfully enhance performance. Our objective is to guide ITS deployment by developing a metric that quantifies the upper bound of congestion improvement from controlling speed limits on a highway. We propose controllable congestion, a metric that quantifies the maximum achievable reduction in system delay. To estimate controllable congestion, we develop a nonlinear optimization framework grounded in a reformulation of the METANET macroscopic traffic model and solved using model predictive control (MPC). Using both a synthetic scenario and highway data from the I-24 SMART Corridor in Tennessee, we find that controllable congestion is largely independent of total delay, revealing that for two days with identical travel times, controllable congestion can vary from 13\% to 80\%. We further show that the realizable share of this upper bound depends on the operational constraints imposed. On I-24, the minimum posted speed limit has little effect on controllable congestion, while frequency of speed limit update and maximum difference between adjacent gantries have large impacts. This framework allows highway operators to distinguish between congestion that is structurally unavoidable and congestion that is highly responsive to ITS, enabling more cost-effective deployment of control-based traffic infrastructure.

eess.SY↗
arXiv2026

Task Specialization Fine-Tuning for Contextual Reinforcement Learning

Contextual Reinforcement Learning (CRL) seeks to generalize classical RL by maximizing task coverage across a context space of related tasks. While prior works often train from scratch and rely on either multi-task learning for a single policy or strategically training multiple policies, we advocate for a unified alternative: pretraining a single policy with good initial performance, followed by fine-tuning multiple policies for task specialization. This new paradigm, however, introduces unique challenges, such as heterogeneous marginal returns and sample inefficiency. This raises a critical research question: given a pretrained policy and a constrained budget, how much fine-tuning should each task region receive to enable sample-efficient CRL? To this end, we propose Task Specialization Fine-Tuning (TSFT), an online framework that predicts fine-tuning performance with a simple parametric model and exactly solves the resulting discrete budget allocation problem via integer linear programming. Extensive experiments across diverse decision domains, including combinatorial optimization, continuous control, and LLM fine-tuning, demonstrate that TSFT significantly outperforms baselines in task coverage and approaches oracle performance. Our work charts a new direction for model-based CRL, aligning with the modern pretrain-finetune era.

cs.LG↗
arXiv2026

Measuring the State of Open Science in Transportation Using Large Language Models

Open science initiatives have strengthened scientific integrity and accelerated research progress across many fields, but the state of their practice within transportation research remains under-investigated. Key features of open science, defined here as data and code availability, are difficult to extract due to the inherent complexity of the field. Previous work has either been limited to small-scale studies due to the labor-intensive nature of manual analysis or has relied on large-scale bibliometric approaches that sacrifice contextual richness. This paper introduces an automatic and scalable feature-extraction pipeline to measure code and data availability in transportation research. We employ Large Language Models (LLMs) for this task and validate their performance against a manually curated dataset and through an inter-rater agreement analysis. We applied this pipeline to examine 10,724 research articles published in the Transportation Research Part series of journals between 2019 and 2024. Our analysis found that only 5% of quantitative papers shared a code repository, 4% of quantitative papers shared a data repository, and about 3% of papers shared both, with trends differing across journals, topics, and geographic regions. We found no significant difference in citation counts or review duration between papers that provided data and code and those that did not, suggesting a misalignment between open science efforts and traditional academic metrics. Consequently, encouraging these practices will likely require structural interventions from journals and funding agencies to supplement the lack of direct author incentives. The pipeline developed in this study can be readily scaled to other journals, representing a critical step toward the automated measurement and monitoring of open science practices in transportation research.

cs.DL↗
arXiv2026

A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention

Mixed-integer linear programming (MILP) is a foundational framework for combinatorial optimization across science and engineering, but remains hard to solve at scale due to NP-hardness. Recent learning-based methods typically model MILP instances as variable-constraint bipartite graphs and use Graph Neural Networks (GNNs) for representation learning, yet their locality limits representation power. We propose an attention-driven neural backbone that adopts an element-centric view of variables and constraints, with dual attention performing parallel intra-type self-attention and inter-type cross-attention. Across three representative tasks at the instance, element, and solving-state levels, our model consistently outperforms conventional GNN-based architectures, highlighting attention-based, element-centric modeling as a powerful foundation for learning-enhanced combinatorial optimization.

cs.AI↗
arXiv2026

An Open-Source Tool for Reproducible Freeway Network Extraction from OpenStreetMap

Freeway simulation is often difficult to deploy at scale not only because of model formulation, but because preparing road network inputs remains a manual, corridor-specific, and difficult-to-reproduce task. This paper presents an open-source tool that extracts freeway networks from OpenStreetMap (OSM) and converts them into a compact, station-referenced representation suitable for downstream freeway simulation. Unlike existing tools that primarily support arterial or general network conversion tasks, the proposed workflow is designed around the specific requirements of freeway traffic studies. The tool supports not only OSM data cleaning and conversion, but also the broader workflow required in practice: corridor-specific querying, visual inspection of extracted segments, extraction validation against OSM, and source-data validation against aerial imagery. A locally hosted frontend allows users to define corridor-specific queries, select endpoints visually, and inspect extracted segments. The extraction logic is designed to address several recurring challenges in freeway OSM data, including inconsistent route references, ambiguous path selection through interchanges, managed-lane interference, incomplete corridor capture from naive bounding-box queries, and inconsistent ramp classifications. The workflow was first tested on two prototype corridors, where the extract-first-then-validate approach proposed here required roughly one-third the analyst effort of manual ramp encoding from scratch. It was then deployed across 359.6 miles of freeway in Orange County, California, with total processing and validation averaging about 41 seconds per mile. This deployment also suggests that, in a well-mapped region, OSM is sufficiently accurate for many freeway traffic studies. Overall, the tool provides a more scalable and reproducible foundation for freeway network preparation.

cs.IR↗
arXiv2026

Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks

Neural Combinatorial Optimization (NCO) achieves strong performance, yet its black-box nature remains a key roadblock to deployment and scientific diagnosis. Standard interpretability tools, such as Concept Bottleneck Models (CBMs), are ill-equipped for NCO, whose decisions are dynamic, state-dependent, and lack proper concept vocabulary definition. To close this gap, we introduce Evolving Programmatic Bottlenecks (EPB), to our knowledge, the first framework for interpreting NCO policies by distilling black-box NCO models into human-readable program portfolios. EPB employs an LLM to autonomously evolve a bank of programs, where each program's per-step action distribution serves as the bottleneck. EPB works through an iterative framework: Block I fixes program bank capacity and introduces a hybrid textual-numerical gradient descent scheme that couples numerical gradients for student router updates and textual gradients for LLM-based program revision; Block II dynamically adapts bank capacity via fault-targeted expansion and redundancy pruning. Extensive experiments demonstrate EPB's effectiveness and broad applicability, where the distilled program portfolios largely match original performance. EPB also reveals that NCO behavior shifts across optimization stages and can be approximated as a composition of classic heuristic variants. Our work advances interpretable NCO and establishes EPB as a promising tool for interpreting sequential decision-making models.

cs.AI↗
arXiv2026

AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library

Optimization modeling underlies critical decision-making across industries, yet remains difficult to automate: natural-language problem descriptions must be translated into precise mathematical formulations and executable solver code. Existing LLM-based approaches typically rely on brittle prompting or costly retraining, both of which offer limited generalization. Recent work suggests that large models can improve via experience reuse, but how to systematically acquire, refine, and reuse such experience in structurally constrained settings remains unclear. We present \textbf{AlphaOPT}, a self-improving experience library that enables LLMs to learn optimization modeling knowledge from limited supervision, including answer-only feedback without gold-standard programs, annotated reasoning traces, or parameter updates. AlphaOPT operates in a continual two-phase cycle: a \emph{Library Learning} phase that extracts solver-verified, structured insights from failed attempts, and a \emph{Library Evolution} phase that refines the applicability of stored insights based on aggregate evidence across tasks. This design allows the model to accumulate reusable modeling principles, improve transfer across problem instances, and maintain bounded library growth over time. Evaluated on multiple optimization benchmarks, AlphaOPT steadily improves as more training data become available (65\% $\rightarrow$ 72\% from 100 to 300 training items) and outperforms the strongest baseline by 9.1\% and 8.2\% on two out-of-distribution datasets. These results demonstrate that structured experience learning, grounded in solver feedback, provides a practical alternative to retraining for complex reasoning tasks requiring precise formulation and execution. All code and data are available at: https://github.com/Minw913/AlphaOPT.

cs.AI↗
arXiv2026

Dynamic Gradient-Based Calibration for Robust and Accurate Traffic Macrosimulation

Robust and accurate calibration of macroscopic traffic flow models such as METANET is critical for reliable prediction and effective control. While gradient-based methods are desirable for high-dimensional parameter spaces, their application to real-world traffic scenarios is hindered by highly nonconvex optimization landscapes. Consequently, standard static calibration frequently yields parameter sets that produce unstable, unrealistic traffic dynamics, undermining confidence in the estimated parameters and compromising the simulation's utility for counterfactual scenario testing. To address this, we propose a dynamic, rolling-horizon calibration framework. By reformulating static one-time estimation into a dynamic control problem, parameters better maintain stability and accuracy amid measurement noise. Using real-world data from the I-24 MOTION testbed, this work empirically characterizes the instability of standard methods. It then shows that the proposed approach simultaneously enhances robustness to perturbations and achieves a 48% improvement in predictive accuracy over conventional static calibration.

eess.SY↗
arXiv2026

AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning?

Transit network design depends not only on the optimization algorithm but also on who shows up to the public hearing. Current practice often collects one-directional comments from self-selected attendees, leaving participant mix as an uncontrolled source of outcome variation. We present AGORA, a framework that holds the network, demand, and solver fixed while systematically varying meeting composition through stakeholder agents, structured deliberation, and governance gates. Across two standard benchmark networks at different scales, we find that (i) aggregate outcomes vary little across compositions, but on tail risk and fairness disparity, representative sampling still tends to outperform skewed compositions; (ii) without deliberation, composition produces no variation at all, showing that deliberation is the mechanism through which who attends affects outcomes; and (iii) governance gates compress cross-profile variance without shifting the average outcome on Mandl, but low acceptance on Mumford0 shows thresholds require instance-specific calibration. These findings reframe participation bias from an uncontrollable input to a process-design problem: even without guaranteed representative attendance, well-structured deliberation and governance criteria can substantially reduce how much outcomes depend on who is in the room.

cs.CY↗
arXiv2026

FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization

Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimization problems often require a harder capability: designing scalable algorithms that exploit problem structure and outperform direct formulation-and-solve baselines. Existing benchmarks are limited to small or simplified examples far below real-world scale and complexity. We introduce FrontierOR, among the first benchmarks to systematically evaluate LLM-based efficient algorithm design for realistic large-scale optimization problems. FrontierOR includes 180 tasks derived from methodologically diverse papers published in top-tier operations research venues, each with standardized instances and a hidden, expert-verified evaluation suite. We evaluate seven LLMs spanning frontier, cost-effective, and open-source models both in one-shot and test-time evolution settings. The results reveal that frontier models still struggle to move from executable formulations to efficient optimization algorithms: the strongest one-shot model outperforms Gurobi in only 31% of cases in both solution quality and computational efficiency, and even strong coding agents with test-time evolution achieve only 50% on selected hard tasks. FrontierOR establishes a practical evaluation platform for LLM-based optimization algorithm design, which enables future LLMs and agents to be systematically tested on whether they can move beyond correct formulation toward a feasible, high-quality, and efficient algorithm. Code and data are publicly released at https://github.com/Minw913/FrontierOR.

cs.AI↗
arXiv2026

Route Recommendations for Traffic Management Under Learned Partial Driver Compliance

In this paper, we aim to mitigate congestion in traffic management systems by guiding travelers along system-optimal (SO) routes. However, we recognize that most theoretical approaches assume perfect driver compliance, which often does not reflect reality, as drivers tend to deviate from recommendations to fulfill their personal objectives. Therefore, we propose a route recommendation framework that explicitly learns partial driver compliance and optimizes traffic flow under realistic adherence. We first compute an SO edge flow through flow optimization techniques. Next, we train a compliance model based on historical driver decisions to capture individual responses to our recommendations. Finally, we formulate a stochastic optimization problem that minimizes the gap between the target SO flow and the realized flow under conditions of imperfect adherence. Our simulations conducted on a grid network reveal that our approach significantly reduces travel time compared to baseline strategies, demonstrating the practical advantage of incorporating learned compliance into traffic management.

eess.SY↗