arXiv:2605.16176v1 Announce Type: new
Abstract: The groundbreaking metric age of information (AoI) has been introduced to measure information freshness in communication networks. As transformational as it is, AoI metric falls short in some applications, such as remote monitoring, since it is a semantic-agnostic metric which does not consider the dynamics of the random process. There is a need to quantify the performance of a remote estimator via a metric that combines freshness and semantic aspects. To this end, in this paper, we introduce a novel metric coined age of staleness (AoS) that measures when the last time that the current estimation was correct. First, we analyze a simple scenario where an $n$-ary symmetric Markov source is observed by a monitor via a constant sampling rate, obtain a closed-form expression for the AoS, and show that it is a monotonically decreasing function of the sampling rate. Next, we consider multiple distinct Markov sources, and formulate an optimization problem, where the remote monitor allocates the total sampling rate to tracking the sources. Although the optimization problem is non-convex, its structure is suitable for obtaining a near-optimal solution using the polyblock algorithm, which leverages the monotonicity of the objective function. While the new AoS metric could be applicable in many scenarios, we believe it is particularly well-suited for a digital twin network (DTN) where multiple physical objects (POs) are monitored with a total sampling rate constraint to maintain a digital representation of them, namely, their digital twin (DT).
Science Journals
arXiv:2512.15734v2 Announce Type: replace
Abstract: Differentially flat models are frequently used to design feedforward controllers for electromechanical systems. However, control performance depends on model accuracy, which makes feedback imperative. This paper presents a control scheme for electromechanical systems in which measuring or estimating the output to be controlled -- typically the position -- is not feasible. It employs an identifiable-model-based controller and predictor, coupled with an iterative loop that updates model parameters using the error between a measurable output and its prediction. Simulations on electromechanical switching devices show effective tracking of the desired position trajectory using only coil current measurements.
arXiv:2605.15224v1 Announce Type: new
Abstract: Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed, the model may fail again on the same query, indicating that it has not internalized the critique's guidance into its underlying capability. Meanwhile, a frozen critic cannot improve its feedback quality over time, limiting the potential for iterative self-improvement. To address this, we propose learning to internalize self-critique with reinforcement learning(ICRL), a novel framework that jointly trains a solver and a critic from a shared backbone to convert critique-induced success into unassisted solver ability. The critic is rewarded based on the solver's subsequent performance gain, incentivizing actionable feedback. To address the distribution shift between critique-conditioned and critique-free behavior, ICRL introduces a distribution-calibration re-weighting ratio that selectively transfers critique-guided improvements compatible with the solver's own prompt distribution. Additionally, a role-wise group advantage estimation stabilizes joint optimization across the two roles. Together, these mechanisms ensure that the solver learns to improve itself without external critique, rather than becoming dependent on critique-conditioned behavior. We evaluate ICRL on diverse benchmarks spanning agentic and mathematical reasoning tasks, using Qwen3-4B and Qwen3-8B as backbones. Results show consistent improvements, with average gains of 6.4 points over GRPO on agentic tasks, and 7.0 points on mathematical reasoning. Notably, the learned 8B critic is comparable to 32B critics while using substantially fewer tokens. The code is available at https://github.com/brick-pid/ICRL.
arXiv:2605.16229v1 Announce Type: new
Abstract: Dependence among marginally constrained observations can break a finite-sample barrier. To formalize this phenomenon, we introduce the \emph{minimum list entropy coupling} $H(P\|Q_1,\dots,Q_m)$, the minimum conditional entropy $H(X|Y_1,\dots,Y_m)$ over all joint distributions with prescribed discrete marginals $X\sim P$ and $Y_i\sim Q_i$. Unlike classical formulations based on independent observations, our model allows $Y_1,\dots,Y_m$ to be arbitrarily dependent while keeping each marginal fixed. This enlarged coupling space reveals a sharp dichotomy: independent observations reduce residual uncertainty exponentially, whereas dependent observations can eliminate it exactly after finitely many samples. We characterize this zero-entropy regime through necessary and sufficient conditions and give concrete structural criteria under which it occurs. In particular, under mild support assumptions, zero entropy is achieved with $O(\log(1/P_{\min}))$ observations, where $P_{\min}$ is the minimum nonzero mass of $P$. We also develop a greedy algorithm with monotone approximation guarantees for computing $H(P\|Q_1,\dots,Q_m)$. Finally, we show that the same framework formalizes finite-sample limits in distribution-matching representation learning and randomness extraction, where zero entropy corresponds to exact recovery and exact extraction.
arXiv:2605.16182v1 Announce Type: new
Abstract: Temporal random walks, which sample causality-preserving paths, are widely used to analyze time-stamped interactions in domains such as microservices, finance, and online platforms. Generating such walks at scale is challenging because real-world graphs evolve as high-volume streams, making continuous ingestion, efficient memory usage, and strict temporal ordering essential for practical deployment. We present Tempest (TEMPoral nEtwork Streaming Traversals), a GPU-accelerated engine for streaming temporal random walks. Tempest combines a GPU-native dual-index organization over a shared edge store with a hierarchical cooperative scheduler that dispatches walks at thread, warp, or block granularity based on per-step node convergence, enabling efficient start-edge selection, hop-by-hop causality enforcement, and window-based eviction without synchronization. It further provides closed-form constant-time samplers for common temporal bias functions. Our evaluation demonstrates sustained real-time processing of billion-edge streams under sliding windows, outperforming prior systems in ingestion and walk generation throughput while preserving causal correctness.
arXiv:2511.21277v3 Announce Type: replace
Abstract: This paper presents LatencyScope, a mathematical framework for computing one-way uplink and downlink latency in fifth-generation radio access networks across diverse system configurations. LatencyScope models latency sources across the protocol stack, including radio interfaces, scheduling decisions, processing delays, frame structures, and hardware and software constraints, while capturing dependencies among configuration parameters and stochastic sources of delay. The framework also includes a configuration analyzer that uses these models to search billions of candidate settings and identify those that satisfy latency-reliability targets under user-specified constraints. We validate LatencyScope on two open-source fifth-generation radio access network testbeds, as well as on measurements from a public commercial fifth-generation network. The results show that LatencyScope closely matches empirical latency distributions, captures observed lower and upper latency bounds, and substantially outperforms prior analytical models and widely used fifth-generation network simulators. LatencyScope can determine whether ultra-reliable low-latency communication targets are feasible for a given deployment and, when they are feasible, efficiently find satisfying configurations, helping network operators reason about latency modeling, configuration analysis, and system-level bottlenecks.
arXiv:2605.16107v1 Announce Type: new
Abstract: Machine-generated texts (MGTs) pose risks such as disinformation and phishing, underscoring the need for reliable detection. Metric-based methods, which extract statistically distinguishable features of MGTs, are often more practical than complex model-based methods that are prone to overfitting. Given their diverse designs, we first place representative metric-based methods within a unified framework, enabling a clear assessment of their advantages and limitations. Our analysis identifies a core challenge across these methods: the token-level detection score is easily biased by the inherent randomness of the MGTs generation process. Then, we theoretically derive the multi-hop transitions of the token-level detection score and explore their local and global relations. Based on these findings, we propose a multi-level contextual token relation modeling framework for MGT detection. Specifically, for local relations, we model them through a lightweight Markov-informed calibration module that refines token-level evidence before aggregation. For global relations, we introduce a rule-support reasoning module that uses explicit logical rules derived from contextual score statistics. Finally, we combine the local calibrated score and the global rule-support reasoning signal in a joint multi-level inference framework. Extensive experiments show broad and substantial improvements across various real-world scenarios, including cross-LLM and cross-domain settings, with low computational overhead.
arXiv:2511.19399v3 Announce Type: replace
Abstract: Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with verifiable rewards, which does not extend to realistic long-form tasks. We address this with Reinforcement Learning with Evolving Rubrics (RLER), where rubrics are constructed and maintained to co-evolve with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact checking and more discriminative on-policy feedback. Using RLER, we develop Deep Research Tulu (DR Tulu-8B), the first fully open model that is directly trained for open-ended, long-form deep research. Across four long-form deep research benchmarks in science, healthcare, and general domains, DR Tulu substantially outperforms existing open deep research agents (by 15.6% over Tongyi DR on average) and matches or exceeds proprietary deep research agents (by 0.7% over OpenAI DR on average), while being significantly smaller and cheaper per query (1000x cheaper than OpenAI DR per query).
arXiv:2511.18225v2 Announce Type: replace
Abstract: Quantum machine learning seeks to leverage quantum computers to improve upon classical machine learning algorithms. Currently, robust uncertainty quantification methods remain underdeveloped in the quantum domain, despite the critical need for reliable and trustworthy predictions. Recent work has introduced quantum conformal prediction, a framework that produces prediction sets that are guaranteed to contain the true outcome with a user-specified probability. In this work, we formalise how the time-varying noise inherent in quantum processors can undermine conformal guarantees, even when calibration and test data are exchangeable. To address this challenge, we draw on Adaptive Conformal Inference, a method which maintains validity over time via repeated recalibration. We introduce Adaptive Quantum Conformal Prediction (AQCP), an algorithm which provides asymptotic average coverage guarantees under arbitrary hardware noise conditions. Empirical studies on an IBM quantum processor demonstrate that AQCP achieves the target coverage level and exhibits greater stability than quantum conformal prediction.
arXiv:2605.15223v1 Announce Type: new
Abstract: This paper presents an LLM-empowered workflow for RISC-V supply chain analysis, integrating Vision-Language Models (VLMs) and Model-Driven Engineering (MDE) to enable comprehensive, multimodal data-driven insights. The proposed approach addresses the challenges of heterogeneous and unstructured supply chain data by leveraging LLMs for textual understanding and VLMs for extracting information from visual artifacts such as diagrams, tables, and scanned documents. These models collaboratively identify key entities and relationships, which are then organized into a knowledge graph representing supply chain components and their interdependencies. For analytical reasoning, the workflow incorporates MDE techniques and constraint-based modeling to enable formal validation of dependencies, detection of bottlenecks, and assessment of risks. The synergy between LLM- and VLM-based semantic understanding and MDE-based formal analysis supports both exploratory and systematic evaluation of supply chain resilience. A human-in-the-loop mechanism further enables interactive querying and expert validation. The approach is evaluated in RISC-V ecosystem scenarios, demonstrating its effectiveness in generating actionable insights, enhancing transparency, and supporting decision-making in complex semiconductor supply chains.
arXiv:2605.15978v1 Announce Type: new
Abstract: Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, and investigations are in natural language and require manual reading. We propose a framework using symbolic methods for converting narratives into evidence-linked facts. Our objective is to measure the value of narratives to recover incident details only from the unstructured text and build temporal graphs with time cues and domain axioms. We achieve this by redacting personal identifiers, semantic parsing, predicate mapping to ontology, and reasoning. We evaluate the symbolic approach on 450 property crime reports and a short human review. Of the extracted events from the system, 54.1% had a confidence score of at least 0.80 and 93.7% were mapped through the PropBank--VerbNet--WordNet semantic path. 100% agreement was reached on incident initiation, stolen items, and temporal cues and lower agreement for forced entry interpretation.
arXiv:2511.18127v2 Announce Type: replace
Abstract: Real-time 3D hand forecasting is a critical component for fluid human-computer interaction in applications like AR and assistive robotics. However, existing methods are ill-suited for these scenarios, as they typically require offline access to accumulated video sequences and cannot incorporate language guidance that conveys task intent. To overcome these limitations, we introduce SFHand, the first streaming framework for language-guided 3D hand forecasting. SFHand autoregressively predicts a comprehensive set of future 3D hand states, including hand type, 2D bounding box, 3D pose, and trajectory, from a continuous stream of video and language instructions. Our framework combines a streaming autoregressive architecture with an ROI-enhanced memory layer, capturing temporal context while focusing on salient hand-centric regions. To enable this research, we also introduce EgoHaFL, the first large-scale dataset featuring synchronized 3D hand poses and language instructions. We demonstrate that SFHand achieves new state-of-the-art results in 3D hand forecasting, outperforming prior work by a significant margin of up to 35.8%. Furthermore, we show the practical utility of our learned representations by transferring them to downstream embodied manipulation tasks, improving task success rates by up to 13.4% on multiple benchmarks. Dataset page: https://huggingface.co/datasets/ut-vision/EgoHaFL, project page: https://github.com/ut-vision/SFHand.
arXiv:2605.16071v1 Announce Type: new
Abstract: Designing the objective function in Model Predictive Control (MPC) is challenging when performance assessment criteria are available only from human judgment. We adopt a preference-based learning (PbL) approach to learn the MPC objective function from preferences over trajectory pairs. However, the real-world application of PbL is often restricted by the significant cost or limited availability of human preference queries. To address this, Active Learning (AL) strategies seek to improve sampling efficiency, reducing the labeling effort required to obtain a well-performing classifier. We present two AL strategies for learning the MPC objective function from human preferences over pairwise system trajectories: a pool-based strategy that selects trajectory pairs that are both uncertain under the current surrogate and diverse relative to previously labeled comparisons, and a query-synthesis strategy that incorporates new trajectories using the current surrogate-driven MPC. Numerical results show that the proposed strategies yield closed-loop behaviors that align more with the expressed preference using fewer number of queries compared to a random sampling approach.
arXiv:2605.16114v1 Announce Type: new
Abstract: We propose a scalable neuromorphic architecture based on spiking dynamics emerging from the autonomous time-continuous evolution of clockless (asynchronous) digital circuits. Implemented on commercially available field-programmable gate arrays (FPGAs), our system implements networks of interacting Boolean spiking neurons with configurable excitatory and inhibitory synaptic weights. A complete processing pipeline enables efficient handling of spike-encoded data for solving machine-learning tasks. We demonstrate competitive performance for an audio classification task with spike-based encoding and high-speed processing. Power consumption is significantly lower than traditional digital implementations; this makes our approach an efficient alternative that bridges the gap to dedicated analog neuromorphic systems without the need for specialized hardware design. More generally, our approach establishes clockless digital hardware as a viable platform for neuromorphic computing. It paves the way for reconfigurable chips to be turned into energy-efficient quasi-analog neuromorphic processors.
arXiv:2605.16115v1 Announce Type: new
Abstract: As mobile service robots increasingly coexist with pedestrians, ensuring passively safe behaviour during confined emergency evacuations is critical. Existing multi-robot yielding strategies often focus solely on collision avoidance and macroscopic flow optimisation, overlooking environmental affordances and human spatial expectations. To bridge the gap between macroscopic theory and micro-level perception, we conducted a game-based virtual evacuation experiment (N=56). We investigated individual psychological responses to four multi-robot yielding strategies (Hide, LineEscape, Freeze, ShortestPath) across confined corridors with and without refuge niches. Our results establish a robust preference hierarchy (Hide > LineEscape > Freeze > ShortestPath), demonstrating that proactive space-yielding significantly outperforms freezing and efficiency-first approaches. Crucially, we found that environmental affordances heavily shape cognitive expectations. Actively utilising available niches amplifies the psychological comfort of proactive yielding (Hide). Conversely, failing to use an obvious niche (e.g., executing LineEscape) may trigger Expectation Violation. This is reflected in a drastically increased perceived cognitive delay, despite objectively unimpeded trajectories. Furthermore, prior robot interaction experience helps users decode complex social intents. Ultimately, this research demonstrates that safe human-robot interaction during emergencies must evolve from pure trajectory optimisation to semantically aware navigation. Future work will extend this framework to investigate complex interactions between robot swarms and pedestrian crowds.
arXiv:2510.02278v2 Announce Type: replace
Abstract: Modeling traffic dynamics is a critical challenge for urban computing, with applications from real-time traffic management to infrastructure planning. However, progress in this area is fundamentally constrained by a lack of large-scale public datasets that capture the subtle properties of real city road networks. Existing benchmarks are often limited by their small scale, reliance on sparse highway traffic sensors, absence of true road connectivity information, and lack of information about road properties. To address this issue, we introduce datasets representing fine-grained road networks of two major cities, which are unique in their scale (up to 100,000 road segments), use of real road connectivity, presence of time series measurements for both traffic speed and volume at a 5-minute resolution, and inclusion of rich static road attributes. These datasets enable in-depth analysis of spatiotemporal traffic patterns and can serve as benchmarks for various ML applications. As a practical demonstration of the utility of our datasets and the challenges they present, we use them for the task of traffic forecasting. The size of the real-world road networks in our datasets reveals significant scalability issues in current traffic forecasting models. To address them, we propose a simple and efficient baseline that not only scales to large road graphs but also achieves forecasting performance competitive with other established spatiotemporal models. We hope that the proposed datasets will serve as a foundational resource for a broad range of research in traffic modeling, urban computing, and smart city development.
arXiv:2509.21465v3 Announce Type: replace
Abstract: Tabular foundation models are becoming increasingly popular for low-resource tabular problems. These models make up for small training datasets by pretraining on large volumes of synthetic data. The prior knowledge obtained via pretraining provides the exceptional performance, but the resulting model becomes a black box that is difficult to interpret and costly for inference. In this work, we explore an alternative strategy: using reasoning-capable LLMs to induce decision trees for small tabular datasets in an agentic setup. We design a minimal set of tools for constructing, analyzing, and manipulating decision trees. Equipped with these tools, the LLM combines its prior knowledge with learning from data to produce a lightweight decision tree that outperforms CART and recent non-greedy tree learners and remains competitive with tree ensembles on low-resource tabular problems. While a single agentic decision tree is competitive with state-of-the-art black box models, it also comes with a human-readable reasoning trace that can be checked for biases and data leaks. Furthermore, the reasoning-based LLM's creation process allows for additional human input to be incorporated into the tree without it being captured in data.
arXiv:2605.16116v1 Announce Type: new
Abstract: Developing and evaluating e-commerce web agents requires environments that preserve meaningful task structure while enabling controllable, reproducible, and scalable scientific comparison. Existing methodologies force a tradeoff: live storefronts provide realism but are non-stationary, difficult to inspect, and irreproducible, while hand-built sandbox benchmarks provide control but cover only a narrow range of layouts, catalogs, policies, and interaction patterns. We argue that the core bottleneck is methodological: the field lacks a scalable way to construct evaluation settings that are simultaneously realistic, diverse, controllable, inspectable, and reproducible. We introduce ShopGym, an integrated framework for realistic simulation and scalable benchmarking of e-commerce web agents. ShopGym is a framework for constructing e-commerce simulation environments and grounded benchmark tasks. Its simulation layer, ShopArena, converts live seed storefronts into self-contained sandbox shops through anonymized shop specifications and a staged, validated generation process. On top of these simulated storefronts, ShopGuru synthesizes benchmark tasks across seven skill categories, grounding each task in the shop's catalog, navigation structure, policies, and interaction affordances. Together, ShopArena and ShopGuru produce self-contained, resettable, inspectable, and stable evaluation artifacts that preserve structural properties and agent-evaluation signals relevant to shopping tasks. We validate the framework through graph-based structural analysis and agent-based behavioral evaluation with 224 generated tasks across six sandbox shops: three constructed with synthetic data and three with real data. Our results show that the synthetic shops preserve key structural properties of live storefronts, with agent performance on synthetic shops positively correlated with performance on live storefronts.
arXiv:2509.20349v3 Announce Type: replace
Abstract: Accurate time-series forecasting for complex physical systems is the backbone of modern industrial monitoring and control, yet deep learning models often lack the physical consistency required in regulated environments.To bridge this gap, we introduce Process-Informed Forecasting (PIF) models for temperature in pharmaceutical lyophilization, embedding deterministic production recipes as macro-structural priors. We investigate classical methods (e.g., Autoregressive Integrated Moving Average (ARIMA) model) and modern deep learning architectures, including Kolmogorov-Arnold Networks (KANs). We compare three different loss function formulations that integrate a process-informed trajectory prior: a fixed-weight loss, a dynamic uncertainty-based loss, and a Residual-Based Attention (RBA) mechanism. We evaluate all models not only for accuracy and physical consistency but also for robustness to sensor noise. Furthermore, we test the practical generalizability of the best model in a transfer-learning scenario to a new process. Our results show that PIF models outperform their data-driven counterparts in terms of accuracy, physical plausibility and noise resilience, offering a scalable framework for reliable and generalizable forecasting solutions in critical manufacturing.
arXiv:2507.20098v2 Announce Type: replace
Abstract: This paper compares data-driven predictive control strategies by examining their theoretical foundations, assumptions, and applications. The three most widely recognized and consequential methods, Data Enabled Predictive Control, Willems-Koopman Predictive Control, Model-Free Adaptive Predictive Control are employed. Each of these strategies is systematically reviewed, and the primary theories supporting it are outlined. Following analysis, a discussion is provided regarding their fundamental assumptions, emphasizing their influence on control effectiveness. A numerical example is presented as a benchmark for comparison to enable a rigorous performance evaluation.
arXiv:2605.16191v1 Announce Type: new
Abstract: We present a case study for how AI coding systems can be used to generate novel scientific hypotheses. We combine a generic coding agent (Google's AntiGravity) with an LLM-driven tree search algorithm (Empirical Research Assistance / ERA) to autonomously generate high-efficiency three-dimensional photovoltaic (3DPV) structures that overcome losses limiting flat solar panels at mid-latitudes. These structures operate by presenting favorable angles to the sun throughout the day, and for illustrative purposes we focus on optimizing performance for a single solar day. Our workflow begins by using AntiGravity to reproduce calculations \cite{bernardi2012solar} showing that 3DPV can have energy densities much higher than stationary flat PV panels. We use these initial designs as the starting point for large scale tree search, where we seek improved solutions and score them for their diurnal yield. The initial tree search leads to nominally more efficient solutions, yet they are caused by algorithmic reward hacking, arising from non-physical design features such as structurally levitating disconnected tiers and exploitations of the discretizations in the optics solver. To counteract this, we develop a workflow where the coding agent iteratively patches the physics engine with constraints to eliminate reward hacking. With reward-hacking eliminated, ERA discovers a series of designs with various constraints and improved performance, including optimal designs with different fixed collector areas, optimizing zenith tracking and avoiding self shadowing.
Combining coding agents with tree search (ERA) provides a powerful platform for scientific discovery, for problems whose solutions can be empirically evaluated with a score function.
arXiv:2605.15927v1 Announce Type: new
Abstract: Quantum chemistry calculations are often performed using atom-centered basis sets which are chosen to balance accuracy and cost. While they are systematically improvable, the total energy converges slowly with basis set size towards the complete basis set (CBS) limit. Common extrapolation methods require several intermediate-quality calculations to afford an estimate of the CBS energy. We propose combining a pairwise interaction model with a minimal complementary auxiliary basis set (CABS) baseline to estimate the CBS energy from a single quantum chemistry calculation in a minimal basis set via Kernel-Ridge-Regression (KRR), which is more efficient than both direct and $\Delta$-machine learning. We show that KRR on standard molecular representations can be improved by approximating atom-wise local kernels using Chebyshev polynomials which allows us to train KRR models efficiently on moderate compute resources, further enabling a data-driven approach towards CBS combining physical baselines capturing leading order effects with data-efficient machine learning models.
arXiv:2507.17572v3 Announce Type: replace
Abstract: Global optimization has gained attraction over the past decades, thanks to the development of both theoretical foundations and efficient numerical routines. Among recent advances, Kernel Sum of Squares (KernelSOS) provides a powerful theoretical framework, combining the expressivity of kernel methods with the guarantees of SOS optimization. In this paper, we take KernelSOS from theory to practice and demonstrate its use on challenging control and robotics problems. We identify and address the practical considerations required to make the method work in applied settings: restarting strategies, systematic calibration of hyperparameters, methods for recovering minimizers, and the combination with fast local solvers. As a proof of concept, the application of KernelSOS to robot localization highlights its competitiveness with existing SOS approaches that rely on heuristics and handcrafted reformulations to render the problem polynomial. Even in the high-dimensional, non-parametric setting of trajectory optimization with simulators treated as black boxes, we demonstrate how KernelSOS can be combined with fast local solvers to uncover higher-quality solutions without compromising overall runtimes.
arXiv:2605.16178v1 Announce Type: new
Abstract: Accurate seasonal runoff forecasts are critical for managing California's reservoirs and water supply for millions of its residents. Winter snow accumulation provides a strong source of predictability of snowmelt-based runoff in the spring and summer months, but progressive hydroclimatic changes in the Sierra Nevada are altering its timing and volume. These changes reduce the skill of statistical forecasts trained on historical data, highlighting the need for improved forecasting systems that can capture the changing dynamics of snowmelt. Here we demonstrate that a collaborative workflow between an agentic AI assistant and an automated code-mutation system, both powered by large language models, can accelerate the development of competitive seasonal runoff forecasting systems. In our framework, the AI agent discovers relevant datasets, synthesizes domain knowledge from prior forecasting competitions and the scientific literature, and explores the space of model architectures, while the code-mutation system refines each of the solutions explored by the agent through Monte Carlo Tree Search over the code space. The resulting system forecasts monthly Full Natural Flow (FNF) at 1- to 6-month lead times across 23 Sierra Nevada watersheds using an adaptive ensemble of three XGBoost quantile regression sub-models with physics-informed feature engineering. Evaluated against California's operational Bulletin 120 forecasts over 2021-2025, the agent-evolved model achieves superior skill for early-season cumulative April-July runoff predictions, reducing watershed-averaged quantile forecast error by up to 29%, and offering a new paradigm for AI-driven scientific model development in the geosciences.
arXiv:2507.16806v2 Announce Type: replace
Abstract: When language models (LMs) are trained via reinforcement learning (RL) to generate natural language "reasoning chains", their performance improves on a variety of difficult question answering tasks. Today, almost all successful applications of RL for reasoning use binary reward functions that evaluate the correctness of LM outputs. Because such reward functions do not penalize guessing or low-confidence outputs, they often have the unintended side-effect of degrading calibration and increasing the rate at which LMs generate incorrect responses (or "hallucinate") in other problem domains. This paper describes RLCR (Reinforcement Learning with Calibration Rewards), an approach to training reasoning models that jointly improves accuracy and calibrated confidence estimation. During RLCR, LMs generate both predictions and numerical confidence estimates after reasoning. They are trained to optimize a reward function that augments a binary correctness score with a Brier score -- a scoring rule for confidence estimates that incentivizes calibrated prediction. We first prove that this reward function (or any reward function that uses a bounded, proper scoring rule) yields models whose predictions are both accurate and well-calibrated. We next show that across diverse datasets, RLCR substantially improves calibration with no loss in accuracy, on both in-domain and out-of-domain evaluations -- outperforming both ordinary RL training and classifiers trained to assign post-hoc confidence scores. While ordinary RL hurts calibration, RLCR improves it. Finally, we demonstrate that verbalized confidence can be leveraged at test time to improve accuracy and calibration via confidence-weighted scaling methods. Our results show that explicitly optimizing for calibration can produce more generally reliable reasoning models. Code, models, and further info is available at https://rl-calibration.github.io/.