Artificial Intelligence
EvoWeave: Composing Reusable Agent Experience through Operation Level Graphs
Guanhua Zhu, Bo Shen, Lei Zhang et al. (+4 more)
Different tasks often require interactive
agents to perform similar operations at intermediate steps. Retrieving an entire past workflow can introduce irrelevant steps, whereas retrieving isolated operations can discard the dependencies needed to reuse them. We introduce EvoWeave, a framework for experience
memory that represents abstract states as nodes and reusable operations as directed edges with input and output contracts, provenance, and capability references. A planner decomposes the current task into a dependency graph; operation
retrieval and bounded directed search then assemble relevant experience fragments. An execution
agent can inspect these fragments and their referenced capabilities, while reflection separates concrete execution evidence from reusable abstractions. We study the framework across four
benchmarks, five evaluation settings, and three
language model backbones. Across backbones, AppWorld Normal and Challenge task goal completion average 51.91 and 27.99, respectively, exceeding the baseline without
memory by 6.99 and 4.99 percentage points. An AppWorld ablation associates directed connections with an additional improvement of 2.08 points over independent operation cards. The results motivate composition of reusable operations while exposing tradeoffs in
retrieval overhead and conditions for valid reuse.
Read the full abstract ▾
All authors Guanhua Zhu, Bo Shen, Lei Zhang, Fadi Deek, Zhi Wei, Mengnan Du, Chenxi Yuan
Computation and Language
Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback
Li Wang, Chen Zhang, Yirong Yang et al. (+4 more)
User feedback enables LLMs to refine reusable personalized skills, but often mixes persistent preferences with request-specific corrections. Indiscriminately retaining both risks negative transfer, motivating selective retention at the level of individual requirements. We frame this challenge as selective transfer over atomic rules and propose SkillGrain, a framework for learning reusable personalized skills from user feedback. SkillGrain decomposes feedback into independently actionable rules, predicts their transferability, and retains only those suitable for future requests. To learn these decisions, we combine rubric-guided skill rewards with fine-grained credit assignment that separately evaluates rule content and retention decisions. We further jointly optimize skill induction and skill-conditioned generation through reinforcement learning, ensuring that learned skills support downstream personalization. We construct a
benchmark spanning five personalized writing tasks to evaluate cross-request generalization. Experiments across three base models in both in-domain and out-of-domain settings show that SkillGrain achieves the best overall average performance among competing methods.
Read the full abstract ▾
All authors Li Wang, Chen Zhang, Yirong Yang, Xingyu Chen, Jinkun Zhao, Tianhao Peng, Wenjun Wu
Astrophysics of Galaxies
Simulations of Dust Content and Attenuation in $z=5-15$ Galaxies
Dhruv T. Zimmerman, Jed McKinney, Desika Narayanan et al. (+10 more)
Correctly modeling the dust attenuation law in
galaxies is essential to properly inferring their growth and physical properties. With the rapid discovery of $z>6$
galaxies by JWST and lack of constraints on the properties of dust at these
redshifts, we must turn to theoretical models to predict the properties of dust at these
redshifts. In this paper, we develop a theoretical foundation for the nature of high-
redshift attenuation laws. We analyze $107$ cosmological zoom-in simulations of
galaxies run with the SMUGGLE
galaxy formation model. SMUGGLE includes an explicitly modeled multiphase interstellar medium and a state-of-the-art dust model with a self-consistently evolving dust grain size distribution. We forward model these simulations with the radiative transfer package POWDERDAY to produce synthetic spectra and attenuation curves for a set of $z=5-15$, $M_*\sim10^{6.5}-10^{10}\; \mathrm{M}_{\odot}$
galaxies. We find evidence for flatter attenuation curves than the commonly used locally-calibrated literature attenuation laws assumed when modeling high-
redshift galaxies. The vast majority of our attenuation curves also lack the 2175 Angstrom absorption feature. Our attenuation laws do not evolve strongly over $z=15-5$, which we attribute to relatively constant fractions of small grains up to $z=4$ in our simulations. We present a set of simulation-informed priors on dust attenuation law parameterization that could be implemented in SED fitting codes. There is an anti-correlation between
galaxy mass and attenuation curve slope and positive correlation between
galaxy mass and $A_V$, which we attribute to dust growth becoming efficient in our massive
galaxies with $\log{M_*/\mathrm{M}_{\odot}}\gtrsim9$ and with ISM conditions above a critical
metallicity threshold.
Read the full abstract ▾
All authors Dhruv T. Zimmerman, Jed McKinney, Desika Narayanan, Caitlin M. Casey, John Chisholm, Alex M. Garcia, Michelle C. Jecmen, Jessica Kelley-Derzon, Federico Marinacci, Julian B. Muñoz, Laura V. Sales, Ethan Savitch, Paul Torrey
Machine Learning
Robust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning
Vahid Jebraeeli, Hamid Krim and Keisuke Fujii
We seek a hierarchical resolution of residual error under a composite learning objective as a principled mechanism for identifying and exploiting additional information, particularly under distribution shift and perturbation. Inspired by the System 1/System 2 paradigm, we formulate this principle as a two-loop mechanism serving a common inference goal. A fast, System 1-like loop resolves the residual addressable by the available evidence; the remaining epistemic residual triggers a medium speed, System 2-like loop that actively acquires additional evidence and measures its informational value through residual reduction. Over nested solution spaces, the medium-loop optimum is provably no worse than the fast-loop optimum. Experiments show that the resulting two-loop model consistently improves upon the fast loop at approximately half the computation of the medium loop, including under unseen corruptions, and, when provided a cleaner observation, outperforms staged classifiers and learning-to-defer methods at equal computational cost.
Read the full abstract ▾
Earth and Planetary Astrophysics
Emission spectroscopy of KELT-2A b with Gemini-North/IGRINS-2: hints of a stellar C/O ratio and sub-stellar metallicity
Yuya Hayashi, Stevanus K. Nugroho, Shota Notsu et al. (+13 more)
We present the results of high-resolution emission spectroscopy of the hot Jupiter KELT-2A~b using IGRINS-2 on the Gemini-North
telescope, covering the $H$- and $K$-bands at a spectral resolution of $R \sim 45{,}000$. Observations were carried out over five nights, covering both pre- and post-eclipse orbital phases. Stellar and telluric contaminations are removed via singular value decomposition. We detect $\rm H_2O$ at a signal-to-noise ratio of {6.57}, confirming the previous result at a higher significance. While $\rm ^{12}CO$ is identified in the log-likelihood map near the expected planetary velocity, a definitive detection of $\rm ^{12}CO$ remains elusive given the current data quality. We perform atmospheric
retrieval both with IGRINS-2 data alone and jointly with archival Spitzer/IRAC photometric data points. The retrieved temperature–pressure profile is non-inverted, consistent with prior observations. {From the joint fit we constrain the water abundance to} $\rm log(H_2O) = {-3.78^{+0.27}_{-0.20}}$ {with the free chemistry model}. {The chemical
equilibrium model yields} $\rm C/O={ 0.19^{+0.12}_{-0.07}}$, $\rm [C/H]=-0.81^{+0.41}_{-0.34}$, and $\rm [O/H] = -0.37^{+0.27}_{-0.17}${: the C/O ratio agrees with the stellar value, while the carbon and oxygen abundances are moderately depleted relative to the host
star, though still consistent at the $\sim2\sigma$ level.} If confirmed, {this combination of a stellar C/O ratio with a sub-stellar
metallicity is difficult to reconcile with gas
accretion between the $\rm{H_2O}$ and CO snowlines, which predicts a super-stellar C/O. It instead points to the
accretion of metal-depleted gas outside the CO snowline with only limited planetesimal enrichment, and hence to a disk-free, high-eccentricity migration history.}
Read the full abstract ▾
All authors Yuya Hayashi, Stevanus K. Nugroho, Shota Notsu, Changeat Quentin, Peter C. B. Smith, Krishna Kanumalla, Michael R. Line, Jorge A. Sanchez, Tomohiro C. Yoshida, Kazumasa Ohno, Hideko Nomura, Taiki Kagetani, Norio Narita, Kiyoe Kawauchi, Akihiko Fukui, Enric Palle
Artificial Intelligence
DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents
Tianle Chen, Pushkar Singh, Ketan Todi et al. (+8 more)
Language-model
agents that run long tasks often redo work they have already done: they re-issue a tool call they made earlier and get back exactly the same observation, a step that adds no new information. We identify this failure as a loop. Loops appear natively in Qwen, Llama, and Gemini
agents and become far more common once the
agent's history is compressed to fit its context window. To reduce these loops, we propose DeLoop, a self-supervised training method. DeLoop builds on a simple observation: the
agent's own rollout can provide the supervision needed to learn from its loops. We use a looping action as a negative example and the first later non-looping action in the same rollout as a positive example. DeLoop learns from these pairs through direct preference optimization and does not require task rewards, gold answers, or LLM judges. On CodeGym under compression, DeLoop reduces the share of Qwen3-8B tasks containing loops from 57.3% to 6.1%. It also uses about one third as many steps per task, with similar task success. On Qwen3-32B, DeLoop reduces loops and steps while raising task success from 37.7% to 44.8%.
Read the full abstract ▾
All authors Tianle Chen, Pushkar Singh, Ketan Todi, Biswajit Paria, Qijia He, Wenqi Wang, Yuwen Tan, Jike Zhong, Sugato Basu, Deepti Ghadiyaram, Arjun Akula
Machine Learning
One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models
Joshua Cheung and Zhang He
Latent world models are routinely selected, checkpointed and ablated on one-step prediction loss, on the assumption that a model which predicts the next latent better is a better model. In model-based RL this assumption is known to be unreliable; we ask whether it also fails for latent world models, where the training target is the model's own
embedding and the loss is not expressed in interpretable units. We introduce a frozen-decoder protocol reporting one-step error in physical units, decomposed into the part already present in the encoder's representation and the part the predictor adds. Applying it to a recent end-to-end JEPA world model across three continuous-control environments, we move the metric by fine-tuning and measure goal-conditioned planning on the same checkpoints, with three training seeds and paired planning seeds throughout. Within one environment, a per-epoch ladder shows the relationship saturating after a single epoch: the first epoch improves fidelity by 32% and planning by 4.4 pp, but across the fifteen checkpoints that follow – a further 15% fidelity improvement, monotone in every training seed – the correlation between one-step error and planning success is r = -0.010. This is not a task-ceiling artifact: stratifying by a model-independent measure of training-data support, planning in the lowest-support stratum starts at 80%, leaving ample headroom, and is nonetheless flat from epoch 1 onward. Across environments the exchange rate is equally unstable: a 93% fidelity reduction on TwoRoom yields -0.7 pp of planning, while a 40% reduction on PushT yields +4.9 pp [+1.1, +8.9]. All results replicate under a decoder-free measure, latent drift. We also show that a matched continued-training control absorbs the entire fidelity gain we had attributed to an auxiliary objective.
Read the full abstract ▾
Systems and Control
A Critical Review of Grid Integration Challenges and Flexibility Opportunities for Large-Scale Data Centers
Bibek Dhakal, Manohar Chamana, Biswambhar Gayen et al. (+8 more)
The rapid proliferation of cloud computing and artificial intelligence workloads is fundamentally reshaping the magnitude, spatial concentration, and electrical characteristics of data center power demand. Data centers differ from conventional commercial loads because they combine high rack densities, converter-dominated interfaces, thermally coupled cooling, uninterruptible power supplies, programmable workloads, and increasingly complex behind-the-meter generation and storage within a single facility. This review examines their grid integration from utility and sustainable-energy perspectives across resource planning, large-load interconnection, distribution feeders,
market operation, real-time dynamics, power quality, and asset management. Particular
attention is given to distribution-level issues that receive limited treatment in broader energy reviews: bidirectional operation on renewable-rich feeders, harmonic propagation and resonance, ride-through and reconnection,
transformer derating, cable ampacity, neutral-conductor heating, protection, and measurement. Static, composite, physics-based dynamic, calibrated, impedance, electromagnetic transient, and hybrid load models are compared according to study purpose and data requirements, and utility coordination platforms, uninterruptible power supply and battery control, workload flexibility, renewable co-location, cogeneration, fuel
cells, thermal storage, and clean firm supply are assessed. The central finding is that requested peak demand and annual energy matching alone cannot establish reliable or sustainable integration. Credible assessment must consider hourly and locational supply, network deliverability, marginal emissions, lifecycle and water impacts, backup obligations, rebound, asset health, and verified operating capability.
Read the full abstract ▾
All authors Bibek Dhakal, Manohar Chamana, Biswambhar Gayen, Jatendar Kumar, S M Shams Rahman, Aaqib Peerzada, Ki Yeob Lee, Olatunji M. Adeyanju, Bhaskar Mitra, Soumya Kundu, Stephen Bayne
Computation and Language
Evaluating Compressed Memory: Dependence, Utility, and Content Benefit
Minsu Oh, Seunghui Jwa, Chanjun Park et al. (+1 more)
Does a
language model answer better because its compressed
memory contains useful document information? Replacing
memory vectors with zeros can lower a trained model's score without showing that it outperforms a model trained without
memory. We combine zeroing with separately trained models that cannot access stored text or receive the same constant input for every document. Across nine systems, some models rely on
memory yet perform worse than the trained alternative. For example, in experiments that predict states in generated stories, zeroing
memory worsens a model's prediction loss, yet a model trained without
memory achieves lower loss than the original model with intact
memory. On TriviaQA, giving xRAG
memory from another question's passage raises F1, which measures word overlap with accepted answers, from 19.38 without a document to 24.78. Its effect on how often outputs contain an accepted answer is statistically uncertain. The question's retrieved passage scores higher still (29.88 F1). Thus a gain over no document alone does not establish that the gain requires the question's passage. Evaluations must therefore specify the comparison model, absolute performance, and generation and scoring conditions.
Read the full abstract ▾
All authors Minsu Oh, Seunghui Jwa, Chanjun Park, Yeo-Chan Yoon
Machine Learning
Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards
Min-Young Yu
Runtime policy verifiers can prevent
agents from executing disallowed actions, but their decisions are typically used only for enforcement and discarded afterward. We ask whether these decisions can instead become verifiable policy rewards for training the
agents they guard. We introduce Policy-Verified Self-Training (PVST), a post-training paradigm in which an
agent generates its own interaction trajectories and an executable policy verifier, here a deterministic gate compiled from a written policy, evaluates whether each action complies. Compliant trajectories are reinforced, and violations become negatives for preference optimization; beyond the gate and the
benchmark's task-success signal, PVST needs no stronger teacher model, no human preference labels and no attack-specific supervision, although rollouts are collected in the
benchmark's attacked environment. On held-out AgentDojo tasks under
prompt injection, policy-verified preference training of Qwen3-8B reduces violating trajectories from 37.2% to 10.3 $\pm$ 0.9% (three seeds) and successful attacks from 12.4% to 0.5% at equal or higher pooled task utility, although utility falls on travel, compared with 22.0% when negatives are selected by an attack oracle and 31.9 $\pm$ 0.9% with negatives that contain no violation. The learned behavior holds under an attack template never used in training (37.7% to 11.0%) and on a suite excluded from training (34.8% to 16.7%), and the retained verifier's intervention rate falls from 39.2% to 8.8% (seed 0). Our analysis identifies two conditions under which the verdict is most informative: success must not already imply compliance, and guarded actions must appear in both permitted and forbidden contexts.
Read the full abstract ▾
Statistical Computation
Analytically Optimal Sample Allocations for Nested Multivariate Multifidelity Control Variate Estimators
Atticus Rex and Elizabeth Qian
Monte Carlo estimation, an essential tool for quantifying uncertainty in complex scientific and engineering applications, often has unacceptably large errors when computing resources are limited and each sample requires evaluating an expensive high-fidelity model. Multifidelity control variate methods seek to increase the accuracy of Monte Carlo estimation by combining a limited number of expensive high-fidelity samples with a larger number of cheaper lower-fidelity samples. Many different multifidelity
estimators have been proposed, including multilevel Monte Carlo (MLMC), multifidelity Monte Carlo (MFMC), approximate control variates (ACVs), and multilevel best linear unbiased
estimators (MLBLUEs). An important design choice in multifidelity estimation is the allocation of a limited computational budget among the available models to minimize
estimator error. The state of the art in solving this budget allocation problem relies on numerical optimization; to date, closed form solutions have only been derived for
estimator forms known to be suboptimal. In this work, we provide closed form expressions for optimal fractional sample allocations for a large class of nested multifidelity control variate
estimators, in which higher-fidelity models are evaluated on a subset of the inputs that lower-fidelity models are evaluated on. Our analysis is based on reformulating nested MLBLUEs as an extended version of the MFMC
estimator, and is applicable to general multivariate Monte Carlo estimation. We additionally propose a new approach for integer-valued budget allocation based on a greedy strategy used in combinatorial optimization, as well as a method for robust approximation of control variate coefficients from limited pilot samples. Two numerical examples illustrate our theoretical results and demonstrate the increased accuracy of our extended MFMC formulation relative to existing
estimators.
Read the full abstract ▾
Strongly Correlated Electrons
Odd-to-Even-Layer Switch of Spontaneous Excitonic State in $\rm{TiSe_{2}}$ Thin Films
Kaili Wang, Zhuowei Liu, Yuyang Mu et al. (+8 more)
$\rm{TiSe_{2}}$ is a candidate of high temperature excitonic condensates with spontaneous
exciton formation in addition to its charge density wave (CDW). However, direct observation and manipulation of this electron-hole paring state formation is still lacking. Here, using varying-temperature angle-resolved photoemission spectroscopy (VT-ARPES), we observe a distinct odd-to-even-layer switch of spontaneous
exciton state formation with the evident correlated band structure in $\rm{TiSe_{2}}$ thin films. While the odd-layer $\rm{TiSe_{2}}$ films show a sharp band structure in single-particle picture superimposed by CDW renormalization, in the even-layer $\rm{TiSe_{2}}$ films, the full-filling valence band (VB) opens a distinct notch at the top, and the conductive band (CB) shows a significant extra signal extending above Fermi level with spectra broadening. These features indicate that the extra holes (notched VB) and electrons (broadening CB above Fermi level) form spontaneous
excitons in even-layer $\rm{TiSe_{2}}$. Based on a correlated electron-hole model extracted from the tight-binding description, we reproduce the characterized band structures with spontaneous
exciton formation, where the interlayer inter-band coupling in $\rm{TiSe_{2}}$ plays a key role, which leads to an odd-to-even-layer switch of the excitonic state formation. Our results provide direct evidences of the spontaneous
exciton formation, promising an excitonic condensate as versatile platform for realizing Bose-Einstein condensate (BEC) and investigating novel correlated phenomena.
Read the full abstract ▾
All authors Kaili Wang, Zhuowei Liu, Yuyang Mu, Zhujuan Li, Zhenjie Fan, Yu Gui, Xiaodong Qiu, Baigeng Wang, Rui Wang, Yi Zhang, Qi-Kun Xue
Computer Vision
The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking
Pedro Manoel Herminio Alves, Dalton Cézane Gomes Valadares and Cláudio de Souza Baptista
Pedestrian tracking in
video is important for applications such as surveillance and scene analysis, but it becomes more challenging in crowded scenarios with frequent occlusions and rapid motion. This paper analyzes how detector architecture, model scale, scene density, and inference regime affect the tracking of multiple pedestrians. We compare the YOLO11, RT-DETR, and YOLO26 detector families with the ByteTrack and BoT-SORT trackers on sequences from the MOT17, MOT20, and SOMPT22
benchmarks. For YOLO26, we also compare traditional overlap filtering via Non-Maximum Suppression (NMS) with end-to-end inference. The RT-DETR family achieved the highest mean scores on the HOTA tracking quality metric across all three
benchmarks with both trackers, with a more pronounced advantage on MOT20, albeit at a higher computational cost. On MOT17 and SOMPT22, YOLO26 variants, especially YOLO26-L with NMS, offered favorable combinations of quality and speed compared with RT-DETR. In the YOLO26 inference comparison, the end-to-end mode did not yield consistent tracking gains over the NMS-based regime. Taken together, these results provide a practical guide for selecting detectors and trackers for this task based on application priorities.
Read the full abstract ▾
Software Engineering
OS-Bench: Evaluating SWE Agents on Cross-OS Code Migration
Qirui Jin, Kenan Li, Liao Zhu et al. (+8 more)
Language-model (LM)
agents are increasingly evaluated on repository-level software engineering (SWE)
benchmarks derived from GitHub issues and pull requests. Although these
benchmarks cover a broad range of development tasks, they provide limited insight into a common yet technically distinct challenge: migrating an existing implementation from one operating system (OS) to another while preserving behavior on both. We introduce OS-Bench, an executable
benchmark for cross-OS code migration between Linux and Windows. Motivated by case studies showing that cross-platform features are frequently implemented on one OS before support is added for another, OS-Bench identifies migration opportunities by comparing execution coverage collected from the same repository on both systems. Platform-specific regions are then verified, organized into five migration scenarios, and transformed into repository-level tasks with target-platform tests and source-platform regression tests. The resulting
benchmark contains 140 validated tasks from 111 repositories across C, C++, C#, Go, and Rust, comprising 91 Windows-to-Linux and 49 Linux-to-Windows migrations. We evaluate six models with SWE-
agent, Claude Code, OpenHands, and Win-
agent. The best configurations achieve only 26.4% success on Linux-target tasks and 20.4% on Windows-target tasks while preserving correctness across both systems. These results indicate that cross-OS migration is a challenging and underexplored capability, and OS-Bench is a testbed for improving platform-aware SWE
agents.
Read the full abstract ▾
All authors Qirui Jin, Kenan Li, Liao Zhu, Lingching Tung, Yikai Zhang, Yijia Wu, Zijian Jin, Pengfei Gao, Yu Kang, Qingwei Lin, Wenke Lee
Computation and Language
Beyond Corrected Actions: Training LLM Agents on Textual Critiques
Thomas Zeng, Zelei Cheng, Mingyang Zhou et al. (+3 more)
Large
language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequences of actions. A common approach to improving LLM
agents is to use more capable expert models to provide training supervision, either by behavior cloning the expert's trajectories or by using the expert to correct the actions in trajectories generated by the weaker student model. However, expert LLMs can provide richer supervision than actions alone: they can directly generate textual critique that explain why specific actions are incorrect. We study whether training on such feedback benefits LLM
agents and propose Critique-Augmented Agentic Fine-Tuning (CAFT), a framework that elicits textual expert feedback on student-generated trajectories. For each incorrect action, the expert yields both a corrected action and a textual critique explaining the student's mistake–which we then use as the training target for fine-tuning. Across four student models from the Nemotron 3 and Gemma 4 families on the agentic domains $\tau^2$-Bench Airline+Retail and WebShop, adding critiques to action-level supervision improves performance by 8% on average over action-only
distillation. Additionally, CAFT checkpoints can also provide a better warm start for reinforcement learning than expert-trajectory
distillation. Our results demonstrate that textual critiques can strengthen supervision for multi-turn LLM
agents.
Read the full abstract ▾
All authors Thomas Zeng, Zelei Cheng, Mingyang Zhou, Sambit Sahu, William Campbell, Genta Indra Winata
Artificial Intelligence
Minghao Guo, Qingyue Jiao, Xiujin Liu et al. (+77 more)
Multimodal models and
agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities. However, enabling
multimodal agents to continually acquire useful information from complex, heterogeneous
multimodal data remains a significant challenge as they move toward long-horizon tasks and lifelong settings. Addressing this challenge requires effective
memory mechanisms that can maintain continuity across sessions, adapt to changing users and environments, and refine
memory-management policies through accumulated experience. We introduce a two-axis analytical framework for
multimodal agent memory structured around two key questions: how
multimodal information is formed and represented (Axis I, Formation and Representation), and how its management adapts with accumulated experience (Axis II,
Memory Management). Axis I, Formation and Representation, characterizes what information is retained and how it is encoded (e.g., modality-specific
embeddings, textual and structured records, latent and parametric representations) to support subsequent
reasoning and action. Axis II,
Memory Management, distinguishes three tiers: T1 Static
Memory reuses fixed
memory; T2 Dynamic
Memory updates
memory through a stable policy; and T3 Self-Evolving
Memory updates
memory through an evolving policy. Based on this framework, we synthesize recurring design patterns and derive principles for balancing source fidelity with abstraction, maintaining temporal validity and provenance, grounding
memory use in recoverable evidence, and evolving
memory policies over time. Furthermore, we discuss the challenges and potential future directions for the
memory mechanism of
multimodal agents.
Read the full abstract ▾
All authors Minghao Guo, Qingyue Jiao, Xiujin Liu, Jianhong Pang, Ruimeng Yang, Naihao Xu, Liwei Che, Haochen Xue, Ziqi Wang, Xinying Cai, Jiaxuan Luo, Jiaxin Deng, Xuesong Ye, Jintao Qu, Wenyao Gao, Jingwen Gu, Chenyang Zhao, Shichun Liu, Guibin Zhang, Zefang Liu, Siyin Wang, Wujiang Xu, Danrui Li, Zeru Shi, Woongyeong Yeo, Shuang Liu, Wei-Chieh Huang, Weizhi Zhang, Tianyu Yang, Kangsan Kim, Yebowen Hu, Bowen Wen, Bowen Jiang, Haohao Su, Ming Yin, Sheldon Yu, Mian Zhang, Yuyan Chen, Hanrong Zhang, Kai Mei, Zihao Zhang, Mingyu Jin, Xi Zhu, Hengyi Wang, Tianxin Wei, Linyong Nan, Zhenwen Liang, Zhendong Chu, Ziqi Huang, Yongye Su, Sixun Dong, Shujian Liu, Kaiqu Liang, Jiaojiao Han, Zhaoye Fei, Kun Wang, Shihan Dou, Zhichun Guo, Xingjian Diao, Zeqi Gu, Heng Wang, Tao Feng, Cheng Qian, Hamid Palangi, Silei Xu, Xi Yun, Yi Zhu, Shilong Liu, Qingsong Wen, Sung Ju Hwang, Zuxuan Wu, Yu-Gang Jiang, Yiyu Shi, Dimitris N. Metaxas, Jiaxuan You, Julian McAuley, Mengdi Wang, Jiawei Han, Philip S. Yu, Ziyi Ye
Artificial Intelligence
DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment
Tianzhuo Yang, Shaoheng Yan, Lin Lu et al. (+5 more)
Safety
alignment teaches
language models to refuse harmful requests, yet the internal accessibility of hazardous concepts can retain traces of earlier training. Can checkpoints with equally safe behavior differ in what remains accessible behind their refusals? In this work, we investigate this question through paired training histories and a direct audit of intermediate representations. We introduce DANGERLENS, a probe that maps hidden states into vocabulary space and uses blinded semantic judgments to distinguish harmful goals and operational means from hazard recognition and safety control. Experiments on three Qwen1.5 scales show that checkpoints with prior harmful exposure generally retain greater hazardous concept accessibility after the same safety
alignment, with the strongest separation in intermediate and later layers. The same harmful update also produces different behavioral trajectories from closely matched starting points. Human relevance validation and readout ablations reinforce the measured accessibility contrast. Our findings show that training history remains visible inside behaviorally matched models and motivate internal accessibility audits alongside output safety evaluations.
Read the full abstract ▾
All authors Tianzhuo Yang, Shaoheng Yan, Lin Lu, Jiawei Chen, Kaile Wang, Fanyu Meng, Minglu Liu, Yaodong Yang
Machine Learning
Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context
Bo Li, Yue Yang, Yujin Huang et al. (+6 more)
Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do not fully address dynamic graph world modelling, which requires learning transitions from temporal context to future latent graph states. This is difficult for three reasons: nodes and relations rely on different historical evidence, structural
evolution is path-dependent, and future snapshots provide sparse and realization-specific targets. We propose Dynamic Graph World Modelling (DyG-WM), the first framework to jointly predict future node and relation representations from temporal context by answering three questions: what has evolved, how it evolved, and what will evolve next. To capture what has evolved, a historical node-relation context encoder summarizes node-neighborhood trajectories and pair-specific histories. To characterize how it evolved, a node-relation path-signature encoder captures ordered structural changes. To predict what will evolve next, a dual-level joint-
embedding objective predicts target-snapshot node and relation representations without reconstructing the raw graph. Experiments on 12 link-prediction and two node-classification
datasets demonstrate the effectiveness of DyG-WM across both tasks.
Read the full abstract ▾
All authors Bo Li, Yue Yang, Yujin Huang, Siao Liu, David Lemphers, Sara E Rodriguez Gomez, Luke Borgnolo, Can Wang, Xin Zheng
Combinatorics
Bicolored Eulerian quasisymmetric functions, affine lengths, and Theta operators
Hsin-Chieh Liao and Hai Zhu
We introduce a $q$-analogue of the bicolored Eulerian quasisymmetric functions by incorporating an additional grading arising from affine length, obtained by interpreting bicolored permutations as affine permutations. We also provide an intrinsic description of this refinement in terms of bicolored permutations by introducing notions of
alignments and crossings, together with an explicit bijection identifying these statistics with the
alignments and crossings in the existing literature. Finally, we prove that our refinement is symmetric by expressing it in terms of the Theta operators appearing in the Theta coinvariant
Conjecture and the modified Macdonald symmetric functions. Assuming the Theta coinvariant
conjecture implies the Schur-positivity of our refinement.
Read the full abstract ▾
Computation and Language
Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems
Taro Yano, Yoichi Ishibashi and Masafumi Oyamada
Best-of-N sampling is a simple inference-time scaling strategy for large
language models, yet its behavior under incomplete reward models remains poorly understood. We study Best-of-N as a competition between the extreme reward tails of correct and incorrect responses. This view shows that success depends not only on the probability of sampling a correct response, but also on whether correct responses dominate incorrect ones in the upper tail. Using extreme value theory, we characterize three asymptotic regimes: correct-tail-dominant, incorrect-tail-dominant, and critical explaining both monotonic gains and reward-hacking-induced degradation. We further derive finite-sample scaling laws for representative reward distributions, showing that, under Gaussian rewards, incorrect responses with sufficiently large variance can dominate selection even when their mean reward is lower. Unlike oracle selection, convergence with an incomplete selector can be
polynomial rather than exponential. Finally, we propose a lightweight tail-tension criterion to estimate when additional sampling may become harmful. Experiments on synthetic data and real reward model scores are consistent with the theoretically predicted regimes, scaling laws, and diagnostic behavior, suggesting that tail competition provides a unified lens on Best-of-N sampling for verifiable problems.
Read the full abstract ▾
Computer Vision
VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement
Kyusong Lee, Heting Ying and Tiancheng Zhao
Embodied visual tracking requires a
robot to identify a designated target from visual observations and control its own motion to follow that target through an environment. Following an isolated person is a comparatively simple demonstration of embodied visual tracking, but following the intended person among distractors remains challenging. Existing methods exhibit a substantial drop in success from single-target to distractor tracking, motivating a focus on the shared spaces that person-following
robots must navigate. We present \method{}, a
vision–
language waypoint policy built around the hypothesis that visual and
language representations should be aligned before tracking-specific motion is learned. The policy combines complementary frozen visual encoders, multiscale temporal context, a
transformer backbone, and a lightweight head for
robot-centric waypoint prediction. Its training progresses through
vision–
language alignment,
multimodal reasoning mid-training, and tracking specialization on 19,532 oracle episodes. Compared with 41.54% distractor-tracking success for our earlier OmTrackVLA model, the complete multi-stage recipe achieves 55.80%. We then explore on-policy refinement using filtered oracle labels for states visited by the policy. This preliminary study adds 2.42 percentage points of distractor-tracking success, reaching 58.22%, while reducing collision rate by 1.99 pts. The final policy records the highest distractor- and ambiguous-tracking success rates among the compared methods. These results support staged
multimodal learning as a promising direction for tracking among distractors and motivate further study of on-policy refinement for person following in shared spaces.
Read the full abstract ▾
Dynamical Systems
Poincaré compactifications of pullbacks of parallel vector fields under counterexamples to the real Jacobian conjecture
Francisco Braun and Paulo Machado
Let $F: \mathbb{R}^2 \to \mathbb{R}^2$ be a
polynomial map with nowhere zero Jacobian determinant. It is known that the global invertibility of $F$ is equivalent to the pullback of a parallel vector field being parallel. In this paper, we construct the phase portraits on the Poincaré disc of the pullbacks of the canonical annular, radial, and strip vector fields under non-injective maps $F$ that have recently appeared in the literature. Our arguments use local and global properties of vector fields as well as local and global properties of functions, thereby connecting techniques from dynamical systems and singularity theory.
Read the full abstract ▾
Artificial Intelligence
Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering
Weilun Xu and Zipeng Sun
Activation steering adds a vector to a model's hidden states to control a named behaviour. A gain on that behaviour, however, does not show that the vector controls it directly: it may act through a component shared with neighbouring behaviours, which unsteered and random baselines cannot separate. We introduce the competing-target test: a vector is compared with the vector built the same way for a competing target, and an equivalence test states when their difference is below a useful margin. We apply it in open-weight models to vectors for Kantian deontology, which judges an act by the rule it follows, and act utilitarianism, which judges it by the welfare it produces. On held-out situations, prompting a framework raises its score and lowers the other's, whereas vectors for either framework move both scores alike, and none reaches the margin. The two vectors share most of their direction, a request to apply some framework; the same construction separates an optimistic from a pessimistic tone, whose vectors share much less. What a vector shares with its competitors therefore sets what it controls: steering a perspective can deliver a mixture, and measuring a disposition can measure its neighbours, unless tested against the competing target.
Read the full abstract ▾
Machine Learning
Katy Blumer, Da-Cheng Juan, Jon Kleinberg et al. (+3 more)
In this paper we study the behavior of
transformer networks generating text over long periods of time. We show that even a three-
token, single-layer
attention-only
transformer can fail to converge. We then study a rich class of
transformers with arbitrary finite depth, layer normalization, MLPs, RoPE encodings, and an arbitrary mix of local and global layers. Every
transformer in this class has a softmax temperature threshold above which its empirical cache distribution converges to a unique limit, independent of initial conditions. We show further that, while each
transformer has a temperature threshold, the supremum of this set is infinite, so there is no global minimal temperature that forces all
transformers to converge.
Read the full abstract ▾
All authors Katy Blumer, Da-Cheng Juan, Jon Kleinberg, Ravi Kumar, Cyrus Rashtchian, Andrew Tomkins
Algebraic Geometry
On the Arnold corank, the Zariski multiplicity, and the tangent Milnor fiber problems
José Edson Sampaio
In this article, we approach the Arnold corank problem posed by Arnold himself in 1975, which asks whether the corank of a holomorphic function is a topological invariant. Here, the corank of a holomorphic function is the corank of its Hessian
matrix at 0, which is one of the most basic and fundamental invariants of a holomorphic function. Here, we prove the topological invariance of the corank mod 2. Consequently, we obtain another proof of the Arnold corank problem in dimension 3, which was recently proved by Fernandes, Jelonek, and the author of this article. We also prove that the corank is constant in a continuous family of holomorphic functions with isolated singularities and constant Milnor number. We also approach a
conjecture recently posed by Budur, Fernández de Bobadilla, Lê, and Nguyen (2022), which states that if two germs of holomorphic functions are right topologically equivalent, then the Milnor fibers of their initial forms are homotopy equivalent. We prove that a (much) weaker version of this
conjecture, which states that if two holomorphic functions are right topologically equivalent, then the Milnor fibers of their initial forms have the same Euler characteristic, is equivalent to the Zariski multiplicity
conjecture for right topological equivalence. Some other results are also presented here. For instance, the multiplicity $> 2$ of generalized semi-Bireskorn-Pham hypersurfaces is an invariant for the right topological equivalence.
Read the full abstract ▾
Probability
Fluctuations in the Potts spin glass model at high temperature
Partha S. Dey and Taegu Kang
We study the fluctuations of the free energy of the Potts
spin glass with $\kappa$ colors at high temperature. The disorder is symmetric with unit variance and finite fourth moment. For configurations with a balanced, or nearly balanced, color profile, the log-partition function satisfies a central limit
theorem whenever $\beta^2<\alpha_c(\kappa)$. Here $\kappa\alpha_c(\kappa)$ is the critical inverse temperature of the Curie-Weiss-Potts model. A comparison of color profiles transfers this limit to the unconstrained model for $\beta<\beta_{\max}(\kappa)$, an explicit threshold. In the same range, the magnetizations of two replicas and their overlap
matrix satisfy a joint quenched central limit
theorem with independent Gaussian limits. The fourth cumulant of the disorder enters the limiting mean and variance explicitly.
Read the full abstract ▾
Geometric Topology
Two non-semisimple quantum invariants of lens spaces
Rhea Palak Bakshi, Mitchell Jubeir and Quinn T. Kolt
We calculate the chromatic spherical invariant $\mathscr{K}_{\mathrm{Rep}(H)}(L(p,q))$ of lens spaces $L(p, q)$ for arbitrary finite-dimensional unibalanced, unimodular Hopf
algebras $H$. In the case of the index-2 Nichols Hopf
algebra $\mathcal{K}_2$ and $q=1$, we find that the invariant of $L(p, 1)$ depends only on the parity of $p$ for $p\geq 1$. We also describe the duals $\mathcal{S_I}(M)^*$ of the admissible skein modules of handlebodies $M=H_g$ and of $M=L(p, q)$ for arbitrary tensor ideals $\mathcal{I}$ of a ribbon tensor category. In particular, $\mathcal{S_I}(L(p, q))^*$ corresponds with cyclic traces on $\mathcal{I}$ satisfying a property reminiscent of the modified trace condition.
Read the full abstract ▾
Numerical Analysis
Discrete Edge Multiscale Space based Hybrid Schwarz Preconditioner for High-Frequency Helmholtz Problems
Shubin Fu, Shihua Gong, Guanglian Li et al. (+1 more)
In this work, we develop a novel hybrid Schwarz method, termed as edge multiscale space based hybrid Schwarz (EMs-HS), for solving the Helmholtz problem with large wavenumbers. The problem is discretized using $H^1$-conforming nodal finite element methods on meshes of size $h$ decreasing faster than $k^{-3/2}$ such that the discretization error can be bounded by the data uniformly with respect to $k$. EMs-HS consists of a one-level Schwarz preconditioner (RAS-imp) and a coarse solver in a multiplicative way. The RAS-imp preconditioner solves local problems on overlapping subdomains with impedance boundary conditions in parallel, and combines the local solutions using partition of unity. On the PDE level, this coarse space corresponds to an edge multiscale space proposed in {[S. Fu, G. Li, R. Craster, and S. Guenneau, Multiscale Model. Simul., 19(4):1684-1709, 2021]}. The approximation properties of this coarse space to the discrete solutions from the primal and adjoint problems are derived by a novel conforming Galerkin finite element method based upon a nonstandard variational formulation. This work represents the first theoretical analysis of an edge multiscale space at the discrete level. We prove that the EMs-HS preconditioner leads to a convergent fixed-point iteration uniformly for large wavenumbers, by rigorously analyzing the approximation properties of the coarse space to the global Helmholtz harmonic extension part and to the solution of the adjoint problem. We provide extensive numerical results on the sharpness of the theoretical findings and also demonstrate the method on challenging heterogeneous models.
Read the full abstract ▾
All authors Shubin Fu, Shihua Gong, Guanglian Li, Yueqi Wang
Statistical Methodology
Longitudinal Brain Aging in Covariance Space: Temporally Calibrated Bayesian Inference for Adaptive Covariance Operators
Montserrat Fuentes and Yi Zhao
Functional
brain aging is often characterized by differences between people of different ages, although aging unfolds within individuals. This distinction is especially important for functional connectivity, where the direction of covariance change may evolve across adulthood. We introduce a
Bayesian longitudinal covariance-operator framework that models each visit covariance as a latent positive-definite state informed by repeated resting-state fMRI runs. The approach calibrates run-level information for temporal dependence and replicate variability, separates within-person aging from between-person age differences, and uses an adaptive tangent representation to learn the low-dimensional structure of longitudinal change without relying on pooled covariance variation. The longitudinal operator varies smoothly in magnitude and orientation with age, while exact Fréchet derivatives translate the fitted trajectory to the covariance scale. This framework allows us to examine how
brain covariance organization changes within individuals, whether longitudinal aging follows the population age gradient, and which functional systems contribute to their divergence. In the Dallas Lifespan
Brain Study, within-person covariance aging differs substantially from the cross-sectional age gradient through early and middle adulthood, with the discrepancy diminishing later in life. Covariance reorganization is strongest around midlife, and the longitudinal signal is concentrated in a few coordinated directions, with most off-diagonal change occurring between functional systems. These findings demonstrate that population-level signatures of
brain aging do not necessarily reflect individual aging trajectories and highlight the importance of modeling longitudinal covariance change directly.
Read the full abstract ▾
Machine Learning
BFHD: Bidirectional Feature Harmonization Decomposition for Heterogeneous Clinical Assessments
Yuanhao Zhuo, Zixi Qin, Ling Qin et al. (+1 more)
Clinical assessments are often collected using heterogeneous assessment systems across centers and time, leading to records that mix different but related sets of measurements. This motivates harmonization beyond total-score linking. We formulate clinical harmonization at the measurement level as a bidirectional recoverability problem: given paired observations from two assessment systems, the goal is to identify which measurements can be reliably translated in both directions within an application-defined tolerance, while separating non-translatable components. We propose Bidirectional Feature Harmonization Decomposition (BFHD), a feasibility-driven framework that enforces bidirectionally coupled translation and uses feature-wise output gating to produce an explicit decomposition in the original measurement space. Experiments on synthetic data and real clinical assessment pairs show that BFHD achieves broader feasible harmonization coverage and improved subset stability compared to baselines.
Read the full abstract ▾
All authors Yuanhao Zhuo, Zixi Qin, Ling Qin, Wanqing Li