Peer Revenue Equity in science

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Wednesday 23 September

Software Engineering

FairTest: Search-Based Fairness Testing for Multi-Agent Reinforcement Learning Systems

Xiaotong Wang and Xuan Xie

Multi-agent Reinforcement Learning (MARL) trains a team of agents that share one environment and learn their policies together. Training maximizes the team return, and a high return does not imply that the rewards are shared fairly among the agents in every episode. Testing is an established way to discover the failures of deep reinforcement learning, yet few methods address the fairness of MARL. In this work, we propose FairTest, a search-based testing approach that seeks the unfair executions of a MARL policy. The design combines search guidance with test prioritization. The guidance scores each candidate with three fitness functions. One measures the fairness of the runs already performed, another predicts the fairness from abstract states and fairness features, and the third reads the decision uncertainty from the policy. Crossover and mutation derive further candidates from the observed executions. The prioritization ranks the candidates by the predicted fairness and the decision uncertainty, so that the runs reach the candidates where failures are expected. FairTest is evaluated on three environments and two MARL algorithms, and four baselines are given the same budget. It detects the most fairness failures compared to three baselines with statistical significance and large effect sizes. The failure count exceeds that of the strongest baseline by 221% on average and coverage improves by an average of 23%.
Read the full abstract

Robotics

EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics

Zeyu Shen, Haoxiang You, Yilang Liu et al. (+16 more)

We study coding agents for long-horizon, dexterous robotics and ask whether their solutions can provide scalable supervision for learning general robot policies. To test this, we develop EMBODIEDSWE-BENCH, a simulation benchmark for coding agents spanning contact-rich manipulation, deformable objects, and long-horizon tasks requiring up to half an hour of continuous interaction. We find that frontier coding agents can solve complex long-horizon tasks and transfer prior solutions across both tasks and embodiments. We also design supporting tools that help agents more effectively solve these tasks. However, the resulting solutions require substantial iterative interaction and are typically specialized to individual task instances. We therefore introduce EMBODIEDSWE-GEN, which expands a single solution from coding agent into large diverse trajectories for training a VLA. VLA performance improves with more generated demonstrations, and agent-aided diversification improves generalization to held-out task variations. We also show that a VLA finetuned solely on coding-agent-generated simulation demonstrations completes a long-horizon task on real robot. Together, our framework uses coding agents to solve complex robotics tasks and turn verified solutions into scalable supervision for robot policies.
Read the full abstract

All authors Zeyu Shen, Haoxiang You, Yilang Liu, Zhicheng Zheng, Lihan Zha, Kashu Yamazaki, Mingtong Zhang, Suning Huang, Jiankai Sun, Qianzhong Chen, Lucy He, Kaiyuan Liu, Haoran Chang, Katerina Fragkiadaki, Dhruv Shah, Mac Schwager, Peter Henderson, Ian Abraham, Canwen Xu

Artificial Intelligence

Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents

Yan Zhang, Daiqing Wu, Huawen Shen et al. (+7 more)

Graphical User Interface (GUI) agents enable the fulfillment of complex user instructions through multi-turn interactions with software environments, requiring step-wise reasoning and long-horizon memory to guide actions and retain task-relevant information, respectively. Recent on-policy self-distillation (OPSD) methods have achieved strong performance on GUI grounding, a foundational subtask for GUI agents, owing to dense token-level supervision from privilege-conditioned self-teachers. However, extending existing OPSD methods to multi-turn GUI agents is hindered by self-teachers' limited privilege-following ability and insufficient privileged guidance. In this paper, we introduce GUI-SD-v2, the next version of GUI-SD, which extends OPSD from GUI grounding to multi-turn GUI interaction and addresses key limitations through a two-stage training framework. Specifically, GUI-SD-v2 first strengthens privilege following by jointly optimizing rollouts with and without privileged guidance from the same GUI states. Furthermore, it selectively distills step-specific reasoning and memory guidance through a privilege-conditioned self-teacher, supporting action decisions and the retention of task-relevant information for subsequent interactions. Extensive experiments on two representative GUI agent benchmarks, AndroidWorld and MobileWorld, show that GUI-SD-v2 compares favorably with existing OPSD baselines while consistently outperforming the evaluated state-of-the-art methods in both Pass@1 and Pass@3 success rates. Code and training data will be publicly released.
Read the full abstract

All authors Yan Zhang, Daiqing Wu, Huawen Shen, Liang Li, Gang Cao, Zhi Gong, Wei Dai, Xiaode Zhang, Can Ma, Yu Zhou

Machine Learning

Discrete Diffusion Models via Evolving Variational Autoregressive Networks

Kewen Pan and Ying Tang

Conventional score-based diffusion models learn scores without representing normalized densities, whereas tractable normalized models support both sampling and direct likelihood evaluation. A recent tensor-network approach provides such a representation but is largely restricted to low-dimensional lattices. Here we introduce a discrete diffusion model that parameterizes normalized probability distributions using variational autoregressive networks. Explicit Markov jump operators govern the forward noising and reverse denoising dynamics, extending discrete diffusion models with normalized distributions to spin systems on higher-dimensional lattices. We apply this framework to the two- and three-dimensional Ising models across ordered, critical, and disordered regimes, accurately computing thermodynamic quantities including free energy, energy, and magnetization. We further integrate the framework with Monte Carlo sampling, using adaptive diffusion steps to maintain high acceptance rates even at low temperatures while enhancing sample diversity. These results establish a neural-network framework for the discrete diffusion model with normalized probability distributions.
Read the full abstract

Game Theory

The Power of Recruiting the Smaller Side: Two Additional Traders Suffice in Two-Sided Markets

Yang Cai, Vineet Gupta, Yanchen Jiang et al. (+5 more)

We study Bulow-Klemperer-style competition complexity in two-sided double auctions with $m$ unit-demand buyers drawn i.i.d. from $F_B$ and $n$ unit-supply sellers drawn i.i.d. from $F_S$. When $m \ge n$ and buyer valuations first-order stochastically dominate seller costs ($F_B \succeq_{\mathrm{FSD}} F_S$), we prove that recruiting just two additional sellers enables Seller Trade Reduction (STR), a prior-independent mechanism, to achieve expected Gains From Trade (GFT) at least the first-best GFT of the original market; symmetrically, when $m \le n$, Buyer Trade Reduction suffices with two additional buyers. This resolves open questions of Babaioff, Goldner, and Gonczarowski (SODA 2020) and Cai, Liaw, Mehta, and Zhao (STOC 2024). Moreover, this uniform bound is optimal: already for $m = n = 1$, no prior-independent mechanism (deterministic or randomized) that is dominant-strategy incentive-compatible (DSIC), individually rational (IR), and weakly budget-balanced (WBB) matches the first-best GFT with one additional seller. We further extend our characterization to $r$-dominance ($F_B \succeq_r F_S$), where $r \in (0, 1]$ and $1 - F_B(x) \ge r(1 - F_S(x))$ for all $x \in \mathbb{R}$ (recovering $F_B \succeq_{\mathrm{FSD}} F_S$ at $r = 1$). When $m \ge n \ge 1$, $c = \lceil 1/r \rceil + 1$ additional sellers suffice for STR to match or exceed the first-best GFT, while every prior-independent DSIC, IR, and WBB mechanism requires at least $\max(2, \lceil 1/r \rceil - 1)$ additional sellers even for $m = n = 1$, pinning down the optimal bound to within two traders. Finally, this $\Theta(1/r)$ bound cannot be asymptotically improved even by recruiting on both sides: for $r < 1/64$ and $m = n = \lceil 2/(5r) \rceil$, every prior-independent DSIC, IR, and WBB mechanism requires $c \ge \lceil 1/(64r) \rceil = \Omega(1/r)$ additional traders per side.
Read the full abstract

All authors Yang Cai, Vineet Gupta, Yanchen Jiang, Christopher Liaw, Aranyak Mehta, Grigoris Velegkas, Di Wang, Mingfei Zhao

Machine Learning

Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams

Shujian Gao, Jiamei Yan, Yuchen Yang et al. (+6 more)

Livestreams are long-lasting interactive environments where audiovisual content, viewer activity, host behavior, and platform signals evolve together, creating assistance needs that emerge from the stream itself. We introduce \liveassistant, a framework for mixed-initiative, role-conditioned assistance that formulates livestream interaction as four coupled decisions: whether to act, when to act, whom to address, and what to communicate. At each 10-second interval, one autoregressive policy consumes native audio and video with synchronized comments, gifts, viewer dynamics, and room metadata, then selects OBS, MEM, or ANS. OBS remains silent, MEM records a private semantic update, and ANS specifies a recipient, task, and grounded message. To support this task, we build a trajectory engine that reconstructs real livestream sessions into structured causal supervision, yielding over 320 hours of optimization trajectories and a human-reviewed benchmark of 275 clips and 13,812 decision intervals. We train the policy with Marker-Aware Multiturn Supervised Fine-Tuning (MA-MSFT), which strengthens sparse structured decisions, followed by Streaming Multiturn GSPO (SM-GSPO), which optimizes self-generated trajectories with turn- and trajectory-level credit. On the held-out benchmark, \liveassistant reaches 71.14 state accuracy, 72.67 recipient accuracy, and 58.41 task accuracy, with consistent gains over representative streaming and general multimodal baselines. Together, the formulation, benchmark, and training framework establish livestream assistance as selective participation in a shared social stream.
Read the full abstract

All authors Shujian Gao, Jiamei Yan, Yuchen Yang, Penghao Zhou, Qinglei Wang, Tiehan Fan, Yuan Wang, Zuxuan Wu, Yu-gang Jiang

Cryptography and Security

SoK: You Find What You Seek: Rethinking Oracles, Guidance, and Input Generation in Hardware Fuzzing

G Abarajithan, Zhenghua Ma, Cristian Tirelli et al. (+4 more)

Hardware fuzzing is an active area in security verification research, yet its industrial adoption remains in its early stages. This SoK examines which lessons from software fuzzing carry over to hardware and where unique approaches are needed. By analyzing 52 fuzzers across RTL/IP, CPU, NoC, and SoC designs, we introduce an analytical framework that frames verification as a bounded search. This search is defined by its objective, oracle, guidance, input generation, target abstraction, and budget. Consequently, a campaign only uncovers failures it can effectively reach, recognize, and prioritize before exhausting its resources. We distinguish two roles for hardware fuzzing: (1) augmenting constrained-random verification (CRV) via feedback-guided coverage and (2) directed adversarial testing based on threat models and security specifications. Through our framework, we identify what each campaign can observe and generate, providing a basis for assessing the evidence behind reported results. Our analysis suggests that mainstream adoption of hardware fuzzing will require reusable interfaces, target-specific verification assets, reproducible evaluations, and transparent reporting of cost and user effort.
Read the full abstract

All authors G Abarajithan, Zhenghua Ma, Cristian Tirelli, Andres Meza, Francesco Restuccia, Cynthia Sturton, Ryan Kastner

Artificial Intelligence · Cross-listed from stat.ME

Beyond the Illusion of Power: Calibrating Quasi-Experiments in Observational IS

Spandan Ghose Chowdhury

Information systems (IS) researchers increasingly use quasi-experimental methods such as difference-in-differences (DiD) and instrumental variables (IV) to recover causal effects from observational panel data. Power calculations that justify these designs assume i.i.d. errors, but the deeper problem is what even a cluster-robust calculator cannot see. We report a Monte Carlo study over 9837 parameter conditions (approx 9.8 million datasets) and decompose the planned-versus-achieved power gap. The serial-correlation component is recoverable by an AR(1)-aware calculator when rho is known, and partially when rho must be estimated from short pre-periods, but panel attrition, staggered-adoption bias, and parallel-trends pretesting are captured by no closed-form formula; exogenous attrition alone costs approx 8 to 11 percentage points at the few-hundred-to-thousand sample sizes IS studies use. Treatment-correlated, outcome-dependent attrition instead induces bias, not just power loss. For IV, holding first-stage F fixed, larger N neither raises power nor curbs exclusion bias, though with a fixed instrument more data does sharpen the first stage, so identification rests on instrument strength, not sample size.
Read the full abstract

Artificial Intelligence

StateComp: Learning When to Compress History in Long Horizon Agents

Mingxuan Wang, Hongyue Chen, Yinglong Guo et al. (+6 more)

Long-horizon agents continuously accumulate interaction history during task execution, yet the importance of past interactions changes as the agent state evolves. Existing context management methods largely compress history based on fixed windows, periodic schedules, or current relevance, overlooking a more fundamental question: when has a past interaction become safe to replace? Premature compression may remove information still needed for future actions, while overly conservative retention leads to substantial context overhead. To address this, we propose State Conditioned Compression (StateComp), a framework that determines when historical interactions can be safely compressed according to the current agent state. StateComp constructs KEEP and READY supervision through a two-stage annotation procedure and trains an imbalance-aware router on hidden representations from a frozen language model. A bounded state representation further reduces the cost of evaluating long histories, while adjacent READY interactions are grouped into continuous spans and replaced with compact summaries during execution. Experiments on WorkBuddyBench show that StateComp reduces total agent and summarization tokens by 52.27% while maintaining task performance, and achieves a 12.67-fold speedup in representation extraction.
Read the full abstract

All authors Mingxuan Wang, Hongyue Chen, Yinglong Guo, Fei Luo, Chao Ning, Bo Wang, Guorun Yao, Yanbiao Ma, Jungong Han

Artificial Intelligence

Large Knowledge Model: A Knowledge Foundation for Agentic Science at Scale

Yuan Huang, Sihan Hu, Hongyu Gu et al. (+18 more)

Agentic science envisions many autonomous agents investigating concurrently while building on a shared, evolving body of scientific knowledge. This requires a knowledge foundation that supports high-concurrency access, preserves traceable and reusable reasoning, and grows incrementally. We propose the Large Knowledge Model (LKM), a growing, agent-native knowledge foundation that provides a general representation of scientific knowledge across disciplines. LKM organizes the scientific literature into reasoning graphs, with claims as the core nodes and associated reasoning chains that make explicit how premises and evidence support conclusions. These source-grounded objects are persistent and addressable; cross-paper links organize them into aligned question, workflow, and evidence views. Newly extracted papers extend the foundation incrementally while preserving existing object identities. Building on this foundation, we develop an agent-native, reasoning-aware scientific retrieval system that retrieves claims together with their reasoning chains and sources, enabling agents to inspect and reuse the evidence underlying scientific conclusions. Across benchmarks, agents using LKM retrieve more evidence, cite more faithfully, and answer scientific questions more accurately: LKM nearly doubles the known supporting and contradicting evidence retrieved on SciFact-Open (818 versus 443 claim-paper pairs), reasoning graphs raise citation F1 on ScholarQABench by more than 5 points over the same retrieved papers, and LKM retrieval improves a fixed answering model by 9.3, 4.2, and 14.7 points over no retrieval on ChemBench, PubMedQA, and SciBench. LKM lays the foundation for a scientific ecosystem in which AI scientists not only recall accumulated knowledge but also extend it, returning new questions, workflows, and evidence to a memory that every subsequent investigation can build on.
Read the full abstract

All authors Yuan Huang, Sihan Hu, Hongyu Gu, Chao Ma, Jiaxing Zhang, Zhiyong Zou, Caiyu Fan, Yan Xiao, Mingjun Xu, Chenyu Xie, Mingzhen Ju, Zhehao Ma, Qi Zhang, Baozong Wang, Yu Li, Zhiyuan Yao, Ruoxue Liao, Xinyu Li, Linfeng Zhang, Kun Chen, Weinan E

Software Engineering

Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation

Zaid Ghazal, Khouloud Gaaloul and Bruce Maxim

Validating Autonomous Driving Systems (ADS) in simulation requires testing architectures that can discover rare, safety-critical failures while generating scenarios that are executable, diverse, and useful for downstream failure analysis. We introduce Teach-to-Crash, a closed-loop testing framework that combines a constrained ego-centric scenario representation, stagnation-aware search control, and a dual-LLM architecture for adaptive failure discovery. A high-reasoning Teacher LLM acts as an adaptive search controller, while a low-reasoning Student LLM emits simulator-executable scenarios in a strict JSON schema. The Teacher intervenes only when rolling collision rate and time-to-collision metrics stagnate, providing strategic guidance to redirect the search. In a CARLA case study with two experimental setups that vary the ego vehicle's speed policy, Teach-to-Crash achieves the highest Collision Hit Rate (90.79%), the shortest mean Time-to-Collision (18.31 s), and a competitive Collision Discovery Rate (136.21). PAFOT attains a higher mean CDR (179.44), but with substantially larger variance. Teach-to-Crash also yields the highest diversity (0.547) and, averaged across both setups on the CARLA Traffic Manager controller, the highest avoidability-based usefulness proxy (60.04%) among the compared methods. These results, within the evaluated CARLA scope, provide evidence that closed-loop dual-LLM reasoning can steer adversarial simulation-based testing over a constrained executable program space, generating failures that are frequent, structurally diverse, and assessed as more frequently avoidable.
Read the full abstract

Machine Learning

KITE: KV-Invariant Transformer Expansion for Efficient Agentic LLM Scaling

Zhiheng Hu, Yixun Wei, Jian Zhou et al. (+8 more)

Scaling a language model is not only a question of final quality: the architectural choice determines how much computation is spent during training, prompt processing, and autoregressive decoding to achieve certain model quality. An ideal model architecture should lower all above computation costs to facilitate scaling to a larger model, while ensure the larger model indeed outperforms smaller baselines. We introduce KV-Invariant Transformer Expansion (KITE), a scaling paradigm that achieves this goal. It trains the model from a smaller size to a larger size (i.e., saving training costs via upcycling), while places newly added parameters in regions that do not affect attention KV. Consequently, during inference, prefilling KV only relies on the smaller part of the model, so the inference costs are saved. As a concrete instantiation, we present Step Scale Transformer (SST), a two-tower decoder in which one tower produces KV and the other reads them. At comparable cumulative training compute, SST, a 67B MoE model with 2.15B active body parameters per decode token, achieves lower training loss than 47B and 63B MoE Transformers with 1.48B and 2.02B active body parameters, respectively, while reducing estimated inference cost by 6.7% and 31.6%.
Read the full abstract

All authors Zhiheng Hu, Yixun Wei, Jian Zhou, Yizhuang Zhou, Ji Li, Xing Chen, Yang Li, Bojun Wang, Yibo Zhu, Xiangyu Zhang, Daxin Jiang

Game Theory · Cross-listed from econ.TH

Singleton-Attainability and Transparent Access in Matching

Szilvia Pápai

Matching mechanisms differ in how much of an agent's preference ranking must be determined and reported to obtain a particular object. A mechanism is singleton-attainable (SA) if every object that an agent can obtain through some report can also be obtained by reporting only that object as acceptable. With an SA mechanism, once an attainable object has been identified, the agent need not rank or report any other object. Singleton-attainability identifies a distinct dimension in matching theory and market design: transparent access to attainable outcomes, separate from incentives, stability, welfare or equity. We establish general conditions for SA and derive its strategic implications. Top-lift invariance and truncation invariance together imply SA, while strategyproofness and stability each imply SA. By contrast, no Pareto improvement over a strategyproof, individually rational, and non-wasteful mechanism is SA. In particular, every Pareto improvement over Deferred Acceptance violates SA. We introduce report width, which measures how many acceptable objects may have to be reported to obtain an object. SA mechanisms have report width one. Report width is unbounded for a large class of efficient mechanisms that Pareto-improve Deferred Acceptance. Stable selection with report-induced priorities has width one when priorities are monotone and maximal width under reverse priority dominance. Rank-welfare maximization has width one when the outside-option rank is fixed and maximal width when it is report-dependent. These results reveal a structural divide, which we call the width dichotomy: across all mechanisms and families in our classification and all structural classes we study, report width is either one or unbounded.
Read the full abstract

Machine Learning

NGN: Learning Neural Network Size as a Differentiable Count

Lixing Li

Neural network size is usually chosen before training, separating architecture selection from weight optimization. We introduce the Neurogenesis Network (NGN), a differentiable parameterization for learning how many ordered structural components a model should use. For each ordered component group, one learnable boundary selects an active prefix while the model parameters are trained. The boundary can grow from a compact initialization and can be deployed by discarding components beyond the learned boundary. Controlled experiments examine convergence of the learned boundary, the performance of deployed prefixes, and comparisons with fixed-size models and alternative approaches to learning capacity. We then apply the same mechanism to MLPs, convolutional and graph networks, Transformers, state-space models, LoRA, and adapters. Across these settings, deploying only the learned prefix usually changes performance little, and the selected architectures perform similarly to fixed models trained at the same size. These results show that structural capacity can be optimized directly as a count.
Read the full abstract

Artificial Intelligence

Sparse-Observation Atmospheric Thermal Forecasting with Physics-Informed Neural Networks for Climate-Aware Digital Twins

Tannaz Goodarzvand Chegini, Elyas Shivanian, Behzad Karimi et al. (+1 more)

Short-horizon forecasts of atmospheric temperature are needed to support climate-aware digital-twin systems, but such forecasts must be produced where thermal observations are incomplete. This study evaluates a physics-informed neural network for potential-temperature forecasting, constrained by a pressure-coordinate thermodynamic advection-source equation and a diabatic-source closure fit from the preceding 12-hour period and frozen before future-time training. Using hourly ERA5 reanalysis at three pressure levels, the model is evaluated as a conditional hindcast at lead times of one, two and three hours against persistence, local-trend, and two matched neural-network baselines, one of which receives the same future meteorological forcing as the PINN, helping distinguish the physical constraint from access to future forcing. In an Oklahoma development case, mean RMSE improvement over the strongest baseline grew from 8.1% at one hour to 23.8% at three hours; under an observation-density sweep down to 5% of candidate locations, this 3-hour advantage remained 14.6–16.9%, with no evidence that lower density improves performance. Under a fixed protocol transferred to an Alabama heat event with three virtual-observation layouts, three-hour improvement ranged 19.7-24.4% with consistent origin-level wins. A parallel Montana stress test, in which fixed pressure levels intersected complex terrain, produced a three-hour degradation of roughly 17.5%, identifying a terrain-related applicability limit of the formulation. Together, these results indicate that the physics constraint's benefit grows with forecast horizon, persists under severe observation sparsity, and transfers across regions, but is bounded by the validity of a fixed vertical-coordinate representation over complex terrain, evidence relevant to physics-constrained components of climate-aware forecasting and digital-twin systems.
Read the full abstract

All authors Tannaz Goodarzvand Chegini, Elyas Shivanian, Behzad Karimi, Faraz Dadgostari

Computation and Language

Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition

Hao Shi, Yun Liu, Xuehao Yang et al. (+6 more)

Conventional Japanese automatic speech recognition (ASR) is supervised by an orthographic transcript, although the same written form can correspond to different lexical readings realized in speech. Such utterances receive an identical target, so their reading distinction is absent from the supervision interface and cannot be recovered reliably by post-hoc text-only grapheme-to-phoneme conversion. We present Ruby-ASR, which refines the conventional target into a span-bound orthographic–lexical-reading sequence. Unlike separate full-sentence orthographic and phonological outputs, the ruby representation locally binds each written span to its realized reading and permits deterministic recovery of both views. We instantiate the target under subtitle-style and verbatim-style transcription conventions using a Qwen3-ASR backbone; a mora-level CTC objective provides auxiliary monotonic reading supervision. The experimental results across five Japanese benchmarks show that refining the recognition target can improve lexical-reading recovery without sacrificing readable orthographic transcription. We release the checkpoints and inference code.
Read the full abstract

All authors Hao Shi, Yun Liu, Xuehao Yang, Jun Liu, Chuanbo Hua, Xuanjun Chen, Lianbo Liu, Shiao Zhu, Zixiong Su

Artificial Intelligence

PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks

Claas Beger, Ryan Yi and Melanie Mitchell

The Abstraction and Reasoning Corpus (ARC) has become a prominent benchmark for evaluating general abstract reasoning and fluid intelligence in AI models. Yet standard ARC evaluation considers only a single capability: producing the correct output grid for a test input. We argue that this narrow format fails to evaluate the diversity of abilities that genuine abstract skill acquisition should enable. We introduce PotARCin, a benchmark that extends ARC by assessing understanding of a task's underlying abstract rule across five dimensions: Definition, Classification, Constrained Generation, Editing, and Inversion. PotARCin employs programmatic methods to generate new task instances and transform given inputs for a given ARC task, enabling dynamic generative sampling beyond fixed input-output pairs. Across five state-of-the-art models evaluated on the ARC-AGI-1 training set, we observe a 25-52 percentage-point performance gap between standard ARC evaluation and evaluation on PotARCin, and find that multi-dimensional evaluation reorders models that standard accuracy ranks alike. We further investigate effects of generative sampling, difficulty of corruption types, and questions of self-consistency, showing that models frequently contradict their own formalized rule even where they have stated it correctly. We also introduce P-ARC, a held-out hand-crafted test set, on which models achieve 1-8% accuracy across all five dimensions, underscoring the importance of more holistic evaluations of abstract reasoning capabilities.
Read the full abstract

Machine Learning

SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection

Xuwei Tan, Yao Ma and Xueru Zhang

Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized burst attacks can cause losses before retraining. Production systems typically rely on tabular classifiers and rules, which can struggle to capture these emerging sequential patterns before periodic retraining occurs. We present SR-Fraud, an outcome-supervised reflective LLM framework that decouples request-time decisions from offline adaptation. A frozen, stateless agent scores each transaction from a Hybrid Episodic Window to track behavioral shifts, while an offline reflection agent proposes boundary hypotheses from matured errors. A deterministic verifier then admits only supported hypotheses into an executable knowledge state. On a production payment-fraud benchmark, SR-Fraud improves all detection metrics over its frozen decision agent, obtains higher point estimates than static and periodically retrained CatBoost, and detects an emerging fraud burst.
Read the full abstract

Artificial Intelligence

Memory Control Signals Emerge Before Action in Long Horizon Agents

Mingxuan Wang, Guorun Yao, Fei Luo et al. (+6 more)

Long horizon language model agents continuously accumulate interaction history, increasing computational cost while making relevant information harder to preserve and reuse. Existing context management methods mainly focus on how to compress or retrieve history, but largely leave open whether the model itself already represents the need for these memory operations before they occur. We study the hidden state immediately before each agent action and find that compression and recall needs are already encoded in the model's internal representations. These signals cannot be explained by simple context length or interaction progress, and they exhibit distinct formation patterns across model depth. We further show that most memory decision information is preserved in a compact recent context, while selectively restored historical evidence complements the long range dependencies that recent context misses. Based on these findings, we propose Preaction Memory with Evidence Retrieval (PaMER), which combines state guided compression with external evidence retrieval. PaMER+ further introduces step level evidence selection to recover only the historical information required by the current task. Experiments on WorkBuddyBench, across multiple context management baselines and model backbones, show that our framework substantially reduces context consumption while maintaining competitive task performance.
Read the full abstract

All authors Mingxuan Wang, Guorun Yao, Fei Luo, Yinglong Guo, Chao Ning, Bo Wang, Hongyue Chen, Yanbiao Ma, Jungong Han

Game Theory

Pacing Equilibria in Abstract Mechanisms

Salam Afiouni and Christian Kroer

Digital platforms increasingly rely on automated budget-management systems to regulate participation across allocation opportunities. A common tool is multiplicative pacing, which scales buyers' bids so that campaign-level budgets are spent gradually. Although pacing is operationally simple, its aggregate behavior depends on the underlying mechanism. In first-price single-item auction markets, pacing enjoys strong structural and computational properties that often fail in second-price auctions. It is unclear whether these properties extend to richer platform mechanisms. We develop a unified theory of pacing equilibria across a hierarchy of mechanisms. We first show that, even in first-price position auctions, the market-equilibrium interpretation of the single-item benchmark can fail. We then identify bid-maximizing pay-your-bid mechanisms as a broad class in which pacing equilibria exist, are unique, and admit an Eisenberg-Gale-type convex-program characterization. This implies efficient computation, Pareto-efficiency, and liquid-welfare guarantees, enabling pacing integration into large-scale optimization-based allocation routines. Finally, for abstract mechanisms satisfying a payment monotonicity condition, we prove equilibrium existence by smoothing discontinuities. With additional conditions and appropriate tie-breaking, we obtain uniqueness, revenue maximality among budget-feasible pacing vectors, and shill-proof implementability, and provide convergent budget-adjustment dynamics for approximate equilibria. Overall, many favorable properties of first-price pacing extend beyond single-item auctions under appropriate mechanism-level conditions.
Read the full abstract

Artificial Intelligence

Hunyuan-A13B Technical Report

Tencent Hunyuan Team, Ao Liu, Botong Zhou et al. (+72 more)

We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but activates only 13 billion during inference, balancing model capability, computational efficiency, and deployment cost. The model is pretrained on a rigorously filtered 20T-token corpus with enhanced STEM data curation, improving factual reliability and reasoning ability. High-quality supervised fine-tuning and large-scale reinforcement learning further enhance its overall performance. Hunyuan-A13B also introduces a dual-mode Chain-of-Thought framework that adapts reasoning depth to task complexity: fast thinking for routine queries and slow thinking for complex, multi-step problems. Evaluations show competitive performance across mathematics, science, programming, general language understanding, and agent tasks, often approaching that of much larger models. Its high inference throughput makes it suitable for latency-sensitive applications. We release Hunyuan-A13B to support open research and practical LLM deployment.
Read the full abstract

All authors Tencent Hunyuan Team, Ao Liu, Botong Zhou, Can Xu, Chayse Zhou, ChenChen Zhang, Chengcheng Xu, Chenhao Wang, Decheng Wu, Dengpeng Wu, Dian Jiao, Dong Du, Dong Wang, Feng Zhang, Fengzong Lian, Guanghui Xu, Guanwei Zhang, Hai Wang, Haipeng Luo, Han Hu, Huilin Xu, Jiajia Wu, Jianchen Zhu, Jianfeng Yan, Jiaqi Zhu, Jihong Zhang, Jinbao Xue, Jun Xia, Junqiang Zheng, Kai Liu, Kai Zhang, Kai Zheng, Kejiao Li, Keyao Wang, Lan Jiang, Lixin Liu, Lulu Wu, Mengyuan Huang, Peijie Yu, Peiqi Wang, Qian Wang, Qianbiao Xiang, Qibin Liu, Qingfeng Sun, Richard Guo, Ruobing Xie, Saiyong Yang, Shaohua Chen, Shihui Hu, Shuai Li, Shuaipeng Li, Shuang Chen, Suncong Zheng, Tao Yang, Tian Zhang, Tinghao Yu, Weidong Han, Weijie Liu, Weijin Zhou, Weikang Wang, Wesleye Chen, Xiao Feng, Xiaoqin Ren, Xingwu Sun, Xiong Kuang, Xuemeng Huang, Xun Cao, Yanfeng Chen, Yang Du, Zhen Yang, Yangyu Tao, Yaping Deng, Yi Shen, Yigeng Hong, Yiqi Chen

Machine Learning · Cross-listed from stat.ML

Multitask Regression with Pairwise Fusion

Xiaodong Li and Zhentao Li

We study multitask regression when coefficient sharing can differ by predictor. For a given predictor, many tasks may have the same coefficient while a few differ, and the exceptional tasks need not be the same for another predictor. We describe this structure by two quantities: the number of active predictors and the total number of task coefficients that differ from the most common value for their predictor. We estimate the coefficient matrix by penalizing all pairwise coefficient differences across tasks, with an additional group penalty when predictor selection is needed. The resulting upper and lower bounds have the same dependence on these two quantities. We also consider the stronger setting in which a large set of tasks shares one entire coefficient vector. Under explicit sample-size conditions, the same pairwise estimator pools those tasks exactly, while allowing the remaining tasks to differ. Simulations and household energy data illustrate the transition between broad sharing and task-specific coefficients.
Read the full abstract

Artificial Intelligence

EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory

Xuanyu Meng, Xing Fan, Xinyi Fan et al. (+3 more)

An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history. Existing memory systems often compress interactions into generic summaries or retrieve anonymous text chunks, making it difficult for an agent to identify the correct entity, property, and supporting evidence. We present EnSIMem, an entity-structured long-term memory architecture for an agent. During offline construction, the system organizes interactions into theme-coherent episodes and builds dialogue-grounded index entries of the form [entity][entity_type][property: value]. Each entry preserves its source turns, temporal information, and available multimodal fields. During online interaction, the agent's request is decomposed into evidence requirements whose properties are aligned with the memory index. Entity-property lookup and adaptive retrieval then collect the evidence needed for point, temporal, compositional, and aggregation reasoning. The agent generates its response from the preserved source evidence rather than from lossy memory summaries. On long-term agent-memory benchmarks, EnSIMem achieves high answer accuracy while maintaining compact, evidence-focused contexts. These results show that entity-structured indexing and episode-level provenance provide a reliable foundation for long-term memory in agents. The code of our model is available at https://github.com/RamonMeng/EnSIMem.
Read the full abstract

All authors Xuanyu Meng, Xing Fan, Xinyi Fan, Chenlei Guo, Yixuan Xie, Jiawei Han

Machine Learning

Graph Learning with Spectral Connectivity Priors for Scarce Data

Mingxiao Liu, Bahar Oveisgharan, Bingyan Zou et al. (+3 more)

Learning a sparse graph from scarce data is practically important but challenging. Motivated by the desirable combination of local sparsity and strong global connectivity exhibited by expander-like graphs, we propose spectral connectivity-regularized graph learning (SCoGL), a framework that incorporates a family of Laplacian spectral priors to explicitly promote global connectivity. Specifically, SCoGL augments a combinatorial-Laplacian-constrained graphical lasso (GLASSO) objective over a target adjacency matrix $\mathbf{W}$ with a general connectivity prior computed from Laplacian eigenvalues. We derive gradients for several representative connectivity priors and develop a projected gradient descent (PGD) algorithm with Armijo backtracking to efficiently optimize $\mathbf{W}$. Experiments show that the proposed SCoGL variants improve graph recovery and enhance downstream tasks such as graph signal denoising when signal observations are scarce.
Read the full abstract

All authors Mingxiao Liu, Bahar Oveisgharan, Bingyan Zou, Gene Cheung, H. Vicky Zhao, Feifei Gao

Artificial Intelligence

TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent

Jie Yang, Yan Zheng, Jiarui Sun et al. (+8 more)

Time series agents answer analytical questions by calling external tools, and which tools they carry is decided by people before the agent runs. However, we identify two failures in this setup. Human-Agent Tool Misalignment: a library of 21 expert-curated tools helps on some tasks and hurts on others, dropping anomaly accuracy under every backbone we test. Silent Harm: one round of generic self-revision changes 147 answers and breaks 56 of them, while the final score moves by less than a point. Both follow from the same gap: whether a tool helps is decided question by question at runtime, while tools are supplied in advance and judged by a single average. To address this, we propose TimeEvo, which clusters an agent's diagnosed failures into capability gaps, plans a measurement for each, synthesizes evidence-only tools that fill them, and admits the candidate library only through a paired admission gate. Experiments on ten time series QA tasks and three backbones show that TimeEvo, starting from an empty library, improves accuracy on every task and every backbone, and that a library grown on a cheap model still gains when it is installed into stronger ones. Code is available at https://github.com/Muyiiiii/TimeEvo.
Read the full abstract

All authors Jie Yang, Yan Zheng, Jiarui Sun, Xiran Fan, Junpeng Wang, Liang Wang, Zelin Xu, Qinghua Liu, Zhengyu Fang, Yiwei Cai, Philip S. Yu

Artificial Intelligence

DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents

Mingxuan Wang, Bo Wang, Fei Luo et al. (+6 more)

Long-horizon language-model agents accumulate reasoning traces, tool exchanges, and observations whose relevance changes with the current decision. Existing compression strategies often score historical units independently, but the safety of deleting several units is generally not determined by their singleton scores: redundant evidence, accumulated small effects, and the information that remains after deletion all matter. We introduce Direct Relational Set-Risk Pruning (DRSR), which formulates agent-history compression as risk-constrained selection over deletion sets. Offline, DRSR constructs exact counterfactual supervision by jointly deleting protocol-valid history Blocks and measuring the change in teacher-forced likelihood of the same recorded next output. A lightweight scorer then predicts set-level harm from online-visible relations between candidate history and the current pre-action state, together with deleted-retained and pairwise set structure. At deployment, DRSR evaluates a small set of structurally valid deletion candidates with the lightweight scorer and removes the largest feasible set under recency, protocol, budget, and learned-risk constraints, abstaining when no set is sufficiently safe. On WorkBuddyBench Full260, DRSR increases mean reward from 0.699 to 0.802 while reducing total model tokens by 20.820%. On the fixed Eval40 comparison, it obtains 0.794 reward at 1.211M tokens per task, using 35.850% fewer tokens than the uncompressed agent. Mechanistic analyses and ablations further show that decision-conditioned relations, retained-context information, pair interactions, and abstention each contribute to reliable pruning.
Read the full abstract

All authors Mingxuan Wang, Bo Wang, Fei Luo, Guorun Yao, Chao Ning, Yinglong Guo, Hongyue Chen, Yanbiao Ma, Jungong Han

Robotics

BranchDrive: A Branch-Structured Dataset for Action-Conditioned Driving Prediction

Feeza Khan Khanzada, Sudarshan Sridhar and Jaerock Kwon

Most autonomous-driving datasets record only the action executed by a behavior policy and the single future that followed, providing limited supervision for comparing alternative ego decisions. We introduce BranchDrive, a branch-structured CARLA dataset and benchmark that pairs one canonical pre-decision history with one nominal expert future and twelve physically executed intervention futures spanning acceleration, braking, and left- and right-steering policies at three magnitudes. Each intervention lasts 2.5 s and is followed by expert recovery. Following control-compliance, modality-completeness, replay-fidelity, and action-leakage audits, the frozen benchmark contains 606 independent branch groups and 7,878 associated trajectories. We evaluate prediction of six continuous short-horizon outcomes and a ten-step ego trajectory using action-only, history-only, structured, visual, multimodal, and privileged bird's-eye-view models. On the held-out test split, the structured history-and-action model achieves a macro normalized mean absolute error of 0.5036 and an average displacement error of 2.2042 m, significantly outperforming both restricted baselines. In full-information offline evaluation, its outcome-derived selector increases balanced policy value from 0.5364 to 0.5704 and reduces normalized regret from 0.2674 to 0.1495 relative to the frozen action prior. However, a validation-calibrated minimum-separation guard rejects every intervention, showing that conservative execution remains unresolved. BranchDrive therefore supports action-conditioned short-horizon prediction and fixed-bank offline decision evaluation, but does not establish exact causal effects, binary safety prediction, or closed-loop safety improvement.
Read the full abstract

Computer Vision

High Dynamic Range Video Reconstruction from Single-Exposure Raw Sequences

Tao Zhang, Peixian Su, Xingyu Gao et al. (+6 more)

Due to the limited dynamic range of conventional image sensors, captured low dynamic range (LDR) video often suffers from highlight clipping and shadow detail loss, making high-quality high dynamic range (HDR) reconstruction from single-exposure sequences highly challenging without alternating exposures or extra hardware. Alternating-exposure HDR methods sacrifice frame rate and struggle with motion alignment, making them impractical for real-world capture. To address this, we propose RawHDRV, an end-to-end framework for single-exposure Raw video HDR reconstruction, that fundamentally exploits the linear response and channel-specific characteristics of Bayer data. Specifically, it features a channel-decomposition temporal alignment and fusion strategy that processes Bayer channels separately to exploit their distinct exposure characteristics, together with exposure-aware weighted fusion. It further incorporates an exposure complementarity mask-guided restoration module that leverages inter-frame exposure redundancy to adaptively fuse reliable information and suppress saturation artifacts, and introduces a mask-guided color loss that combines normalized error constraints with gradient smoothing to enhance highlight recovery. Furthermore, we construct a large-scale mobile Raw-HDR video dataset with per-frame HDR annotations. Experiments show that our method achieves the state-of-the-art results in all metrics, demonstrating superior spatial quality and temporal stability under extreme exposure conditions. The code is available at https://github.com/supeixian/RawHDRV.
Read the full abstract

All authors Tao Zhang, Peixian Su, Xingyu Gao, Yunhao Zou, Yu Lu, Zunjie Zhu, Bolun Zheng, Ying Fu, Chenggang Yan

Artificial Intelligence

CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments

Yuxuan Li, Will Epperson, Wesley Deng et al. (+1 more)

Computer-use agents (CUAs) increasingly act on behalf of users online. What happens when the environments they operate in have incentives of their own? Online marketplaces, for example, may favor some products over others, steering agents away from the user's objective. Existing CUA benchmarks cover cooperative settings or explicit attacks, but do not test whether agents preserve user objectives when the environment itself has a stake in the outcome. We introduce CAVEAT, a controlled benchmark spanning nine marketplace environments and a taxonomy of eight common steering mechanisms. Across five model families, agents purchase the user-optimal product in 78.6% of matched-control episodes but only 17.3% when steering mechanisms are enabled. Larger models and more reasoning improve robustness, but substantial failures persist. Trajectory analysis and targeted ablations identify three weaknesses in how agents decide: they (1) prematurely narrow the set of alternatives they consider, (2) impose priorities the user never stated, and (3) commit before resolving decision-relevant evidence. Guided by this diagnosis, we develop CAVEAT-Harness, which targets these failures and raises the optimal purchase rate by up to 80.0 percentage points, and show that targeted post-training further improves a smaller open model. These results establish incentive robustness as a distinct challenge for delegated agents, diagnose failure modes, and show how targeted interventions can substantially improve robustness.
Read the full abstract

All authors Yuxuan Li, Will Epperson, Wesley Deng, Zezhou Huang

Numerical Analysis

Layer-wise discrete certificates in multicomponent reacting-flow discretizations

Jingchao Zhang

Multicomponent reacting-flow discretizations must conserve total species mass, preserve positive mass fractions, and dissipate a convex mixing potential. These properties are controlled at different stages of a solver, however, and a certificate established at one stage need not survive the next. We study this compatibility problem for mixture-averaged diffusion, non-orthogonal finite-volume reconstruction, and positivity-preserving Patankar time integration. The analysis is isothermal, uses prescribed density, and uses synthetic detailed-balance reaction networks for the chemistry tests. At the face level, the entropy-variable jump is shown to equal a log-mean Gibbs Hessian applied exactly to the mass-fraction jump. Requiring conservation and entropy neutrality of the mass-correction term on the simplex tangent space then yields a unique componentwise-positive face composition and an exact two-point entropy certificate. The arithmetic-weight face criterion is also satisfied by production neutral-air/carbon data and a quasi-neutral ambipolar-air control, but a face-level certificate does not automatically extend to subsequent discretization layers. A weighted least-squares non-orthogonal correction can, in the tested prototype, convert a dissipative two-point operator into an anti-dissipative multipoint operator. Likewise, Patankar rescaling can preserve positivity and conservation while increasing the free energy; an explicit finite-step rational counterexample establishes this failure independently of ensemble statistics. A fully discrete two-cell example further shows that a positive face entropy margin does not guarantee positivity of the fully discrete update. Thus conservation, positivity, and free-energy dissipation are layer-specific properties and require distinct discrete certificates.
Read the full abstract