Multiagent Systems
Multi-Agent Debate for Explainable Trading: Reasoning, Consensus, and Performance in Simulated Markets
Juli Huang, Alanood Alrassan, Deveen Harischandra et al. (+3 more)
Large
language models (LLMs) are increasingly used for financial decision-making, yet it remains unclear whether improvements in
reasoning quality translate into better economic outcomes. We investigate this question using a multi-
agent debate framework for portfolio allocation in historical
market simulations, where specialized
agents propose, critique, and revise investment decisions.
Reasoning quality is evaluated across four dimensions: logical validity, evidential support, alternative consideration, and causal
alignment, and compared with downstream financial performance. Across 210 controlled runs, aggregate
reasoning quality shows no meaningful relationship with Sharpe ratio (r = 0.07, p = 0.29) or total return (r = 0.03, p = 0.70). Structured prompting increases measured
reasoning quality from about 0.72 to 0.84 (+17.7%, Cohen's d about 2.0), but these gains do not consistently translate into higher returns. We identify sycophantic convergence as a central failure mode, where
agents abandon independent positions during critique-revision cycles and converge toward similar allocations. A Jensen-Shannon divergence intervention that preserves disagreement improves Sharpe by +0.14 (p = 0.028) and Sortino by +0.25 (p = 0.026), while interventions enforcing stronger causal
reasoning do not improve financial performance. Our results suggest that multi-
agent debate is most valuable when it preserves independent informational signals rather than simply improving measured
reasoning quality.
Read the full abstract ▾
All authors Juli Huang, Alanood Alrassan, Deveen Harischandra, Theodore Wu, Veljko Skarich, Matthew Hayes
Cryptography and Security
Understanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning
Chuanchao Zang, Jianing Wang, Wenyu Chen et al. (+6 more)
Feedback-based planning improves
agent reliability by incorporating tool observations and corrective feedback. However, its protection may not be distributed uniformly across planning stages. We conduct a round-wise analysis of four representative feedback mechanisms and uncover an initialization anchoring weakness: the first feedback round corrects 46% of
adversarial directions, whereas the rates fall to 13% and 7% among directions surviving into the next two rounds. Our analysis attributes this weakness to three interacting factors: a contextually plausible shift in the initial plan, insufficient counterevidence, and the persistence of accepted directions in the accumulated trajectory. Based on these findings, we propose InitAnchor, a black-box framework for exploiting this weakness through attacker-controlled external materials. It operationalizes the three factors as directional-shift, contextual-plausibility, and counterevidence-resilience signals under either limited target access or no target access. Across 112 tasks from 16 domains, six
agent architectures, and five backbone LLMs, InitAnchor achieves average ASRs of 76.1% and 72.0% under the two settings while reducing first-round mitigation rates to 21.0% and 25.0%, respectively. It also remains effective against six defenses and across six real-world
agent systems. These findings show that feedback-based
agents can retain early biases even when later correction is available.
Read the full abstract ▾
All authors Chuanchao Zang, Jianing Wang, Wenyu Chen, Xiangtao Meng, Li Wang, Xinyu Gao, Peng Zhan, Zheng Li, Shanqing Guo
Machine Learning
An Agnostic Sample Compression Scheme for Squared Loss of Near-Linear Size in the Fat-Shattering Dimension
Guangjian Zhang, Zhengyi Yang and Xiaoyang Wang
We study the squared-loss sample compression question posed by Attias, Hanneke, Kontorovich, and Sadigurschi in their ICML 2024 paper. For every nonempty class $\mathcal{F}\subseteq[0,1]^{\mathcal{X}}$ and accuracy $0<\alpha\le1$ with $d=\operatorname{fat}(\mathcal{F},c'\alpha)<\infty$, where $c'>0$ is universal, we prove the existence of a deterministic agnostic scheme of total size $O(d\log^3(2/\alpha))$. Its code contains original labeled observations and auxiliary bits, and its reconstruction has empirical loss at most $\alpha$ above the infimum over $\mathcal{F}$ on every finite sample. This establishes the polylogarithmic formulation in Section 5 of arXiv:1810.01864v2. The construction approximates a near-optimal internal target by a fixed-step boosting ensemble and takes its equal-weight median. Average loss permits an accuracy-dependent number of rounds, so the entire ensemble can be retained without dual-dimension sparsification. Quantized target constraints and round-membership bits determine the reconstructed function exactly. We also prove that, when retained observations must come from the sample, a fixed class of fat-shattering dimension one requires total size $\Omega(\log(1/\alpha))$. With observations and auxiliary bits charged together, this rules out the proceedings version's log-free formulation under its original-example restriction. The framework extends to average power loss at scale $\alpha/p$.
Read the full abstract ▾
Information Retrieval
EvLink: Source-Grounded Evidence Linking for Graph RAG
Linyao Zheng, Xuhang Shi, Zhifang Mao et al. (+3 more)
Graph-based
Retrieval-Augmented Generation (GraphRAG) supports multi-hop
reasoning by organizing corpora into structured graphs. However, graph reachability often captures semantic association rather than evidence support, so a reachable passage may still fail to justify a required cross-passage transition. We propose EvLink, an evidence-linking retriever that preserves passages as retrievable evidence units and builds evidence-supported transitions between them. EvLink constructs two types of reliable links: relation-grounded evidence links justified by explicit source relations, and endpoint-
alignment links serving as sourcebounded fallbacks. For
retrieval, we introduce a two-stage
retrieval strategy. First, bounded breadth-first search over source-grounded evidence links recovers bridge passages missed by similarity-based methods. Then, evidenceneed mining with noisy-OR coverage refinement selects a compact, non-redundant evidence set satisfying distinct question facets. Experiments on three multi-hop and two simple QA
benchmarks show EvLink consistently outperforms leading GraphRAG baselines with average gains of 2.4 R@5, 1.9 EM, and 2.4 F1
Read the full abstract ▾
All authors Linyao Zheng, Xuhang Shi, Zhifang Mao, Sai Zhou, Shuaixian An, Xiuquan Hou
Machine Learning
Bandit Multiclass PAC Learning: Structural Baselines and a Confidence Direct Sum
Guangjian Zhang, Zhengyi Yang and Xiaoyang Wang
How much does high confidence cost when a multiclass learner sees only whether its prediction is correct? We separate two behaviors in realizable bandit PAC learning. An anchored dimension gives a general lower bound that is attained, up to universal constants, by a family of product-block classes. In contrast, for $n\ge16$ divisible by four, an affine multiplexer with bandit DS dimension $2n-1$ has sample complexity $\Theta((n\min\{n,\ln(1/\delta)\}+\ln(1/\delta))/\varepsilon)$ in the standard accuracy and confidence regime. Its lower bound applies to adaptive randomized learners with improper outputs. The obstruction is that evidence collected against one candidate group cannot be reused against the others. The better of two
algorithms matches this cost. One finds the correct group through a positive response. The other exhausts the rank of successive groups. The resulting confidence profile rules out a universal additive-confidence bound linear in the bandit DS dimension. Moreover, classes with identical anchored dimension, bandit DS dimension, and pointwise label width can have polynomially different sample complexities. We also sharpen the confidence accounting in ListCascade and show how one positive response replaces the bandit DS dimension by the anchored dimension in a general upper bound.
Read the full abstract ▾
Artificial Intelligence
Fair Like Us? Auditing LLM Alignment in Resource Allocation
Qishen Han, Hadi Hosseini, Joshua Kavner et al. (+3 more)
Fair allocation of scarce, indivisible resources is an important challenge in many societal problems. While there are several formal theories of
fairness, no single definition can always be satisfied. As large
language models (LLMs) are increasingly used to support decisions and act as
agents, they raise new concerns about distributional justice: their judgments are not directly tied to any specific
fairness framework and may violate key normative principles. In this work, we introduce a general method for evaluating
fairness reasoning in LLMs. We study first-person
fairness judgments across a broad set of models and compare them directly with human responses on matched scenarios and elicitation conditions. We find that LLMs tend to prefer stricter
fairness constraints than humans, show more self-interested behavior, are sensitive to how information is framed, and are difficult to align with human judgments using fine-tuning with current
datasets.
Read the full abstract ▾
All authors Qishen Han, Hadi Hosseini, Joshua Kavner, Samarth Khanna, Sujoy Sikdar, Lirong Xia
Game Theory
Online House Allocation with Subsidy
Nicholas Teh, Saar Cohen, Karen Frilya Celine et al. (+2 more)
House allocation is a fundamental problem in which each
agent is assigned exactly one house. While the classical model assumes that all houses are available before the allocation is computed, many practical settings require decisions to be made as houses become available over time. We introduce the online house allocation problem, where houses arrive sequentially and the
algorithm must maintain an allocation without knowledge of future arrivals. Unlike online fair division, the one-house-per-
agent constraint makes recourse an inherent part of the problem, as accepting a newly arrived house may require reassigning previously allocated houses. We study online house allocation under subsidy-based
fairness, where monetary subsidies eliminate envy among
agents. We show that envy-freeability can always be maintained online using bounded recourse and that reassignment chains of length linear in the number of
agents are unavoidable in the worst case. In contrast, minimizing the total subsidy is fundamentally harder: no deterministic online
algorithm against an adaptive adversary, and no randomized online
algorithm against a non-adaptive adversary, admits a bounded competitive ratio, even for two
agents and four houses. We complement these impossibilities by showing that exact online subsidy minimization is possible whenever there is at most one extra house beyond the number of
agents, and that this guarantee is best possible with respect to the number of extra houses. Finally, we develop learning-augmented
algorithms that recover the offline optimum under accurate predictions while providing explicit robustness guarantees when predictions are inaccurate.
Read the full abstract ▾
All authors Nicholas Teh, Saar Cohen, Karen Frilya Celine, Benjamin Yu, Michael J. Wooldridge
Machine Learning
Predicting Symptoms of Amotivation and Anhedonia among University Students with a Novel Oversampling Method
Dang Nguyen, Bao Duong, Arun Kumar et al. (+12 more)
University students experience disproportionately high rates of common mental health conditions, such as depression, which can impair learning, social functioning, and overall well-being. Within this context, symptoms of amotivation (i.e. loss of motivational drive) and anhedonia (i.e. diminished interest or pleasure) are particularly debilitating, yet they frequently go undetected. Developing new approaches to identify students with prominent amotivation and anhedonia could enable earlier and more targeted intervention. Machine learning (ML) methods have increasingly been used to classify individuals according to symptom severity. However, these ML models often suffer from class imbalance, where the majority of cases fall in the low-symptom group and relatively few in the high-symptom group. This imbalance can reduce model accuracy and bias predictions. To address this, studies commonly employ the popular oversampling strategy SMOTE. However, SMOTE has a notable limitation: it may generate invalid values for nominal variables. In this paper, we introduce a novel and effective oversampling method that addresses this shortcoming. Our approach leverages a predictive model to generate nominal variables, rather than interpolating them. We validate our method on a large-scale GPS location
dataset collected from university students and demonstrate that it is significantly better than existing oversampling approaches in predicting elevated symptoms of amotivation and anhedonia.
Read the full abstract ▾
All authors Dang Nguyen, Bao Duong, Arun Kumar, Dat Phan-Trong, Julian Berk, Taylor Braund, Kien Do, Debopriyo Bal, Wu Yi Zheng, Leonard Hoon, Jill Newby, Helen Christensen, Svetha Venkatesh, Alexis Whitton, Sunil Gupta
Computation and Language
DP-IPI: A Hybrid Differential Privacy Text Rewriting Mechanism for Indirect Personal Identifiers in Clinical Texts
Ibrahim Baroud, Stephen Meisenbacher, Sebastian Möller et al. (+2 more)
Despite the strengths of modern anonymization and de-identification techniques, the risk of re-identification remains significant due to the indirect identifiers remaining in texts. To address this problem, recent works have applied text rewriting under Differential
Privacy (DP) to prevent data linkage by perturbing texts via noise addition. Such methods privatize all
tokens in a text indiscriminately, diminishing text quality and usability in critical domains such as in clinical settings. Focusing on indirect personal identifiers (IPIs), we introduce a utility-preserving DP text rewriting method that only privatizes spans containing IPIs. We show that our method effectively reduces re-identification risks in clinical texts while being producing more coherent and usable output texts, leading to higher
privacy-utility trade-offs. In this, we demonstrate the effectiveness of hybrid text privatization, which leverages the promise of DP in an efficient, usable manner.
Read the full abstract ▾
All authors Ibrahim Baroud, Stephen Meisenbacher, Sebastian Möller, Florian Matthes, Roland Roller
Artificial Intelligence
Sequential knowledge editing breaks a model's ability to tell good evidence from bad, without costing it accuracy
Atul Anand
Knowledge editing is evaluated on whether the edited fact changed, whether paraphrases follow, and whether unrelated answers stayed put. A model can pass all three and still lose something none of them measures: the ability to decide, on facts that were never edited, which retrieved documents to believe. We score the log odds a model assigns to its remembered answer against the answer an injected passage asserts, before and after editing, holding the query, the passage and both candidate strings fixed. Our cleanest arm is a conservatively tuned LoRA: after 1,000 sequential edits on Qwen2.5-7B-Instruct it leaves MMLU unchanged to four decimal places, yet the spread of the arbitration quantity across untouched facts falls by 36%. Selective prediction degrades with it. Area under the risk-coverage curve rises by 0.107, against 0.005 for a norm-matched perturbation at the same MMLU, and error on the model's most confident quarter of arbitration decisions goes from 0.217 to 0.342. This is not capability loss. Sweeping random perturbation over five severities, damage bad enough to cut MMLU from 0.6275 to 0.3725 produces less harm (0.088) than MEMIT does at 0.6050 (0.102). The effect holds across three seeds, two model families, two
datasets, two probe-disjointness criteria, three
prompt templates and paraphrased queries. Layer ablation on saved weight deltas shows it is distributed: no single layer reproduces it, and removing any one recovers about half. Under
retrieval with a frozen retriever, accuracy falls from 0.592 to 0.46. A secondary finding may matter more in practice. Three of five model and method pairings we ran collapse to chance MMLU at 1,000 sequential edits under published hyperparameters, while edit success stays at 1.00 and locality reads clean. Sequential-editing evaluations that never measure capability cannot see this.
Read the full abstract ▾
Computation and Language
PII-TRACE: A Benchmark for Context-Aware PII Detection in Multi-Turn LLM Conversations
Kaiyuan Zhang, Chuan Wang, Joey Zhong et al. (+4 more)
LLM assistants and agentic systems log long multi-turn conversations. AI providers often scan these conversations for Personally Identifiable Information (PII) and mask the PII before storing or processing conversation data. Yet most PII detectors and
benchmarks target self-contained records rather than cross-turn evaluation. To evaluate PII detection across turns in multi-turn conversations, we introduce PII-TRACE (Tracing Recurring PII Across Conversational Exchanges), to our knowledge the first PII
benchmark to assess whether detectors identify PII in conversational contexts and cover every mention of a recurring identifier across turns. PII-TRACE contains 13,148 synthetic multi-turn dialogues in 13
languages with character-level spans and identifier clusters. Across eleven baselines, including frontier LLMs, no detector achieves full entity-level coverage without substantial false positives on PII-free conversations, and single-pass reading loses a third of the gold characters on long dialogues. To close this gap, we introduce PII-Tracer, a compact 0.6B-parameter detector trained with conversation-level supervision. PII-Tracer attains the highest entity-level coverage of any system we evaluate and also performs strongly on standard single-record
benchmarks.
Read the full abstract ▾
All authors Kaiyuan Zhang, Chuan Wang, Joey Zhong, Paul Fryzel, Kyle Polley, Jerry Ma, Ninghui Li
Machine Learning
Improving Parameter Utilization by Sharing Neural Experts Across Layers in Transformers
Dian Jiao, Jiaxin Duan, Shuai Zhao et al. (+3 more)
Transformer-based large
language models often suffer from inter-layer parameter redundancy, where functional transformations are redundantly learned across network depths. We propose CS-MoE, a novel
Transformer architecture featuring cross-layer expert sharing to address this inefficiency. Deviating from the widely used Mixture-of-Experts (MoE) architecture that terminates each
Transformer block with layer-isolated experts, CS-MoE combines layer-independent experts with concurrent access to a centralized, globally shared expert pool. This Global Experts Sharing mechanism enables elastic control over
token-level parameter activation and computational consumption (FLOPs). Experiments demonstrate that CS-MoE achieves lower perplexity than equal-scale dense
Transformers while activating only 55% of parameters. Furthermore, its performance scales monotonically with an increased number of activated experts and approaches MoE counterparts that consume more FLOPs by expanding the shared pool with a fixed FLOPs budget. CS-MoE also establishes a flexible Pareto frontier between computational cost and model capacity, offering an efficient alternative for computation-constrained environments.
Read the full abstract ▾
All authors Dian Jiao, Jiaxin Duan, Shuai Zhao, Jiabing Leng, Yiran Zhang, Feng Huang
Machine Learning · Cross-listed from physics.med-ph
Reconstruction of 4D Mitral Regurgitation Hemodynamics from Sparse Planar Data using Deep Operator Networks with Test-Time Adaptation
Jakob Marcel Hoffmann, Yosuke Hasegawa and Alexander Stroh
Quantifying mitral regurgitation severity remains limited by the assumptions of clinical flow convergence methods, while high-fidelity simulation and volumetric velocimetry are too slow for routine use. We investigate whether a learned solution operator can reconstruct transient three-dimensional transvalvular hemodynamics from the sparse observation an in-vitro experiment actually provides: a single planar velocity slice and two boundary pressure traces. A Deep Operator Network is pretrained on an experimentally benchmarked URANS database spanning eleven mitral regurgitation orifice phantoms, learning a mapping from a masked two-component planar velocity snapshot to the surrounding volumetric field, and is subsequently adapted to unseen target cases by fine-tuning on their sparse measurements. Adaptation reliably corrects the flow
topology within the supervised plane, reorienting a strongly eccentric jet that the pretrained operator predicts as straight, and yields full-field predictions in minutes rather than the days required by the underlying simulations. Its influence decays sharply with distance from that plane, however: measured against phase-resolved particle image velocimetry, the reconstruction error rises from 24.6% at 2mm to 52.6% at 6mm, and the resulting mismatch between corrected and uncorrected layers degrades physical consistency. Single-plane supervision thus constrains the observed plane far more effectively than the surrounding volume, which we identify as the principal obstacle to coherent 4D reconstruction from sparse planar data.
Read the full abstract ▾
Computation and Language
ViCo: Visual-oriented Coding with Self-Reflection for Chart Replication
Jiaxin Duan, Dian Jiao Shuai Zhao, Jiabing Leng et al. (+2 more)
This paper addresses the challenge of generating high-quality academic charts that match the visual standards of human-authored papers. While existing AI
agents can produce well-structured text and code, their generated visualizations often lack the stylistic and semantic fidelity of human designs. Advanced coding
agents that employ self-reflection mechanisms exhibit poor visual
reasoning and limited reflection following, resulting in sparse reward signals that severely undermine their reinforcement learning (RL). We propose ViCo, a training framework for visual-oriented coding that employs iterative reflections to align generated chart images progressively with the reference. We first introduce a self-supervised warm-up stage, which augments Monte Carlo Tree Search with consistency-based
pruning to synthesize high-quality reflection trajectories, ensuring that each coding step strictly follows the outcomes of prior reflections. A multi-step RL
algorithm is then developed, using counterfactual baselines to estimate advantage for reflection and action steps within each refinement cycle, thereby addressing the reward sparsity. To enable efficient reward in massive training, we propose an automatic, multifaceted evaluation framework that assesses charts' style, layout, and semantic consistency via a hierarchical heterogeneous layout graph structure. Experiments on three public
benchmarks demonstrate that ViCo, trained on an 8B model, achieves performance close to proprietary LLMs with adequate reflection capabilities.
Read the full abstract ▾
All authors Jiaxin Duan, Dian Jiao Shuai Zhao, Jiabing Leng, Yiran Zhang, Feng Huang
Robotics
Seeing What the Vehicle Sees: Video-Augmented Virtual Reality for Physical Autonomous Vehicles
Md Tanjemul Islam, Mohammad Shafin and Md Rafiul Kabir
Autonomous vehicles are expected to improve road safety and efficiency, but passengers often remain uncertain about what the vehicle perceives and why it acts as it does. Virtual reality (VR) offers a safe and repeatable medium for presenting this information, yet most passenger-facing VR studies rely on fully simulated vehicles or pre-scripted scenarios, so the motion and perception shown to the user do not originate from a physically operating autonomous system. This paper presents a
video-augmented VR framework that couples a physical ROS 2 autonomous
robot vehicle to a Unity 6 application deployed on a Meta Quest 3S headset. The vehicle state and live onboard camera stream are transmitted over two independent communication channels, allowing the virtual vehicle to mirror the physical
robot's motion while the passenger simultaneously views the vehicle's first-person camera feed and its
navigation decisions through an in-vehicle dashboard interface. We evaluate the framework over 20 repeated closed-loop
navigation trials. The system achieves a mean state-update latency of 29.63 ms, a mean relative route-progress error of 2.28% between the physical and virtual vehicles, and
video delivery at 10.006 frames per second with 0.25% frame loss. All monitored
navigation decisions were correctly reflected in the VR interface with no missed or incorrect notifications. The results indicate that the framework can support temporally synchronized, semantically consistent, and accurate route-progress representation for immersive observation of physical autonomous-vehicle behavior.
Read the full abstract ▾
Digital Libraries
Benchmarking locally hosted language models for journal editorial work on a compact desktop workstation
Haruka Ozaki
Journals are beginning to consider
language models for manuscript handling, but submitted manuscripts are unpublished, and where policy forbids sending them to an external service the model must run on hardware the journal controls. The capability of locally hosted models on editorial work has not been measured. Here we constructed a
benchmark of eight editorial tasks from a journal's Instructions for Authors, from manuscripts carrying defects we seeded and verified independently, and from published reviews of a preprint, and evaluated twenty open-weight models spanning a twenty-five-fold range of weight size on a compact desktop workstation of the kind a laboratory or small editorial office can adopt. The strongest model detected 36 of 40 seeded guideline violations and occupied 81 GB; a 17 GB model detected 33. Across the best configurations tested, we observed no consistent monotonic association between weight size and score: rank correlations were negligible on every task (Spearman |rho| <= 0.19), and within one model family the larger member scored below its smaller sibling. A deterministic checker of regular expressions and arithmetic, using no model, detected 31 of the same violations in a fraction of a second, and the union of its detections with those of the strongest model covered all 40. On the single peer-review case, the best model recovered 6 of 12 points from three published reviews.
Prompt structure substantially altered scores within individual models. This level of performance is therefore within reach of a workstation of this class, once the deterministic checks are written.
Read the full abstract ▾
Computer Vision
Lensless Gaze Is Not Private by Default: Auditing Identity Leakage Across Disclosure Surfaces
Rahul Vimalkanth and Kaushik Mitra
Lensless near-eye sensing is often described as
privacy-friendly because its coded measurements are visually unintelligible. Yet visual unintelligibility reflects human interpretation, not what a learned adversary can recover. We therefore treat identity
privacy as a systems property of disclosure surfaces: representations crossing sensing, storage, computation, and output boundaries. We audit a simulated lensless gaze pipeline under a 36-subject known-gallery closed-set identification protocol with a fixed, known PSF;
privacy from an unknown or varying optical key is outside our scope. Reported accuracies are empirical attack success rates under matched linear and MLP probes and do not upper-bound stronger adversaries. Simulated lensless measurements yield 96.7% top-1 identification versus 97.7% for matched original eye crops, while an MAE
embedding retains 94.3%. Compression alone offers little protection: 8-D PCA and a matched 8-D bottleneck retain 93.2% and 91.8%, whereas separately trained 8-D GSPL bottlenecks yield 77.5% mean recovery across three seeds. A released 128-way gaze
token lowers single-frame recovery to 38.1%, while its residual and continuous gaze output expose 62.1% and 72.6%, respectively. Under a source-frame-disjoint tiled protocol,
token summaries reach 39.9% at T=25, showing that repeated-output risk depends on representation and aggregation. These rates reflect all subject-correlated information in the evaluated
dataset, including acquisition and behavioral cues, rather than isolating intrinsic ocular biometrics. Ordinary least squares residualization against a six-dimensional crop geometry and intensity summary still leaves lensless recovery at 95.1%. Our results show that
privacy claims for lensless sensing must be tested at disclosure boundaries rather than inferred from appearance.
Read the full abstract ▾
Computer Vision
AgenticGen: Reward-Guided Agentic Video Generation for Advertising
Xingyuan Bu, Chengru Song, Hao Zhou et al. (+9 more)
Advertising
video generation is not only a
video synthesis task, but also a product-conditioned
reasoning problem whose success is measured by online business metrics. Recent
video foundation models can generate realistic clips from
multimodal conditions, yet they do not optimize how a product should be transformed into an effective advertisement or how future generation should be improved from online business feedback. To close this loop, we propose AgenticGen, a reward-guided agentic framework that decomposes advertising
video generation into two trainable
reasoning stages, strategy selection and draft generation, thereby exposing optimization targets that online business feedback can supervise. AgenticGen learns a performance-based reward from accumulated online feedback and a complementary rubric-based reward aligned with human quality standards, then uses them to supervise policy optimization. DPO first moves the agentic policies toward online preferences, and GRPO further refines both stages with process and outcome rewards. Offline experiments validate the reward models and successive policy optimization. Online A/B experiments in the TikTok advertising system show that AgenticGen after DPO and GRPO improves CTR by 2.72%, CVR by 2.63%, and Advv by 9.61% over the SFT baseline.
Read the full abstract ▾
All authors Xingyuan Bu, Chengru Song, Hao Zhou, Tao Zhou, Dong Li, Wei Li, Shilong Li, Hao Shi, Yongxin Guo, Donghao Zhou, Qiangpeng Yang, Shilei Wen
Computer Vision
M2LG-DG: A Multi-modal Local-Global Domain Generalization Framework for Cross-site Major Depressive Disorder Classification
Muhammad Asif Hasan, Yanming Zhu, Xuefei Yin et al. (+1 more)
Classification models based on resting-state functional
magnetic resonance imaging (rs-fMRI) often show lower performance at imaging sites not included during model development, which can limit their use in clinical settings. Domain generalization (DG) addresses this issue by learning representations from source sites that remain effective for unseen target sites. However, existing DG approaches for psychiatric disorder classification commonly rely on a single imaging modality and may not fully account for site-specific acquisition effects on the learned representation space. Subjects scanned at the same site share scanner hardware, acquisition settings, and preprocessing characteristics, which can cause representations to reflect acquisition conditions rather than diagnostic information. In this work, we present M2LG-DG, a source-only
multimodal local-global framework for cross-site major depressive disorder (MDD) classification. The framework employs a dual-stream rs-fMRI encoder, where the global pathway models inter-regional dependencies through self-
attention and the local pathway performs graph-constrained aggregation over functional connectivity-derived
brain graphs. Imaging and non-imaging representations are decomposed into shared and private components and integrated through bidirectional cross-
attention with a learned modality gate. A cross-site supervised contrastive objective forms positive pairs from same-class subjects acquired at different source sites, encouraging the fused representation to preserve diagnostic information across acquisition domains. On four held-out REST-meta-MDD sites, M2LG-DG achieves an AUC of 69.48% and exceeds the closest comparison method by 2.18 percentage points. Experiments on the Autism
Brain Imaging Data Exchange (ABIDE)
dataset further support its applicability to other psychiatric neuroimaging classification tasks.
Read the full abstract ▾
All authors Muhammad Asif Hasan, Yanming Zhu, Xuefei Yin, Alan Wee-Chung Liew
Computer Vision
Integrating Unimodal and Vision-Language Representations in Latent Space for Multi-Label Chest X-Ray Classification
Quang-Huy Tran, Duc-Tuan Ngo, Minh-Khoi Nguyen-Bui et al. (+4 more)
Multi-label chest X-ray classification has attracted considerable
attention in recent years, with the effective use of visual representations and clinical semantic knowledge playing an important role. This study proposes a framework that combines unimodal representations from RAD-DINO with
vision–
language representations from BioViL-T for the classification of 14 labels in the MIMIC-CXR-JPG
dataset. The RAD-DINO and BioViL-T
embeddings and their combined representation are refined separately in latent space before being normalized and fused across the three branches. In addition to improving classification performance, the study aims to clarify the role of each
embedding source and the degree to which they complement one another. Experiments show that RAD-DINO outperforms BioViL-T when used independently, whereas early fusion further improves the results, indicating that the two
embedding sources contain complementary information. The best-performing model achieves a mean AUROC of 0.840 and an mAP of 0.467. Ablation analysis shows that hybrid fusion provides consistent and statistically significant improvements over early fusion when each
embedding source is refined in latent space, suggesting that fusion effectiveness depends on the quality of the representation supplied by each branch. However, the study has only been evaluated internally on MIMIC-CXR-JPG; its generalizability to data from other healthcare institutions therefore remains to be validated. The source code is available at: https://anonymous.4open.science/r/mimic-report-C210/.
Read the full abstract ▾
All authors Quang-Huy Tran, Duc-Tuan Ngo, Minh-Khoi Nguyen-Bui, Dang-Khoa Bui, Thanh-Trong Tran, Tuan-Khoi Nguyen, Hoang-Anh Ngo
Robotics
Robots Influencing Humans to Reveal their Goals during Collaboration and Competition
Debasmita Ghose, Oz Gitelson, Michal Lewkowicz et al. (+3 more)
We propose a unified strategy for fast goal inference in human-
robot interaction. The core idea is to drive the human toward Critical Decision Points (CDPs)-states where competing human strategies prescribe different next actions and thus maximally reveal the goal. We formalise CDPs using a goal-conditioned policy divergence measure and incorporate them into a Receding-Horizon Planner that explores future action sequences while optimizing a cost function balancing task progress and information gain. We evaluate this approach in both a collaborative, fully observable cooking task and a competitive, partially observable hide-and-seek game, each in simulation and on real
robots. In both scenarios, our method infers human goals more accurately and earlier than baseline strategies.
Read the full abstract ▾
All authors Debasmita Ghose, Oz Gitelson, Michal Lewkowicz, Jake Brawer, Marynel Vazquez, Brian Scassellati
Computer Vision
CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation
Jiacheng Cai, Zijin Hong, Zheng Yuan et al. (+3 more)
Despite the strong capabilities of
multimodal large
language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, motivating
multimodal retrieval-augmented generation (RAG) to ground responses in external text and images. However, existing
benchmarks face two major limitations: (i) they typically emphasize single-hop
retrieval or
reasoning over a small set of provided contexts rather than open-domain evidence discovery; and (ii) they provide fragmented coverage of cross-modal
reasoning paths, leaving complex multi-hop and multi-image
reasoning underexplored. In this paper, we introduce CrossModalQA, an open-domain
benchmark for evaluating
multimodal retrieval and
reasoning over heterogeneous corpora. CrossModalQA contains 1,863 question-answer pairs constructed from 4,987 Wikipedia articles and 4,431 Wikimedia Commons images. It covers five complementary
reasoning paths:
vision-to-text, text-to-
vision,
vision-to-text-to-
vision, multi-image intersection, and image-set
reasoning. Every question requires retrieving and composing distributed textual and visual evidence, with an average
reasoning depth of 3.50 hops. We construct the
benchmark through
multimodal knowledge graph-guided subgraph sampling and apply rule-based consistency checking and LLM verification to ensure
multimodal dependence and traceable evidence. Extensive experiments demonstrate that existing
multimodal RAG systems struggle to recover complete evidence chains and can underperform closed-book models when incomplete
retrieval introduces distracting context. Further analysis reveals that complete cross-modal
retrieval contributes more to answer accuracy than generator scaling, while multi-image
retrieval and
reasoning remain the primary bottlenecks limiting end-to-end performance.
Read the full abstract ▾
All authors Jiacheng Cai, Zijin Hong, Zheng Yuan, Huachi Zhou, Qinggang Zhang, Xiao Huang
Computer Vision
Han Zhang
Human observers prioritize visual information according to task goals. Most computational models of naturalistic viewing are gaze-trained for free viewing, leaving open whether goal-directed
attention can emerge in systems without gaze supervision. We tested two off-the-shelf
vision-
language models (VLMs), Qwen3-VL-32B-Thinking and Gemma-4-26B-A4B-it, on 4,887 naturalistic scenes under visual-search and free-viewing instructions. Model predictions were compared with human fixations on the same images under corresponding tasks. Both models aligned more closely with human fixations under matching goals than under mismatched goals. This crossover persisted in target-absent scenes, where
alignment could not be explained by simple visual grounding, and appeared in decoder-layer readouts. Furthermore, model-thinking traces were grounded in target semantics during search and in visual prominence during free viewing. These findings show that general-purpose VLMs can generate human-aligned, goal-directed spatial priorities without gaze-specific training, informing theories of goal-directed
attention and offering scalable tools for predicting where people look across tasks.
Read the full abstract ▾
Computer Vision
An Exploratory Study of Frequency-Aware Task Weighting for YOLOv8-Based Unified Driving Perception
Zhiyuan Nie, Zixi Zhou and Xianbin Gu
Unified perception enables autonomous driving systems to perform object detection, drivable-area
segmentation, and lane
segmentation within a single network, improving efficiency and reducing deployment complexity. Jointly optimizing multiple perception tasks remains challenging because tasks exhibit different convergence rates, loss scales, and optimization stability. Existing task-weighting methods use loss magnitude, learned uncertainty, short-term loss changes, or gradient statistics; here, we explore the frequency structure of a recent loss-history window as a complementary signal. We implement and examine Frequency-aware Task Weighting (FTW), a dynamic task-balancing rule that estimates a loss-trajectory stability proxy from the low-frequency energy ratio of recent loss histories. FTW assigns larger weights to tasks whose mean-centered loss trajectories contain a larger proportion of low-frequency power. We document FTW and two baselines under full-network static training and progressive freezing using a unified YOLOv8-based perception framework with three task-specific heads. Experiments on Mapillary Vistas compare FTW with fixed and uncertainty-based weighting under both configurations. Final holdout metrics are reported for the checkpoint with the lowest per-epoch validation loss in each run. Across six single-run configurations, static FTW has the largest derived overall score and lane mIoU, progressive FTW has the largest detection mAP, and static uncertainty weighting has the largest drivable-area mIoU. Without repeated-seed estimates, single-task baselines, or FTW ablations, these rankings are descriptive. The evidence supports the feasibility of loss-frequency-based weighting in this pipeline, but does not establish improvement over the baselines or generalization beyond the reported runs.
Read the full abstract ▾
Robotics
Multi-robot Learning-based Informative Path Planning Using Spatio-Temporal Gaussian Process Kalman Filter
Muqing Cao, Yunwoo Lee, Junbin Yuan et al. (+2 more)
Multi-
robot informative path planning (IPP) for persistent target monitoring requires
robots to reason about spatial uncertainty, temporal
evolution, and practical sensing and communication constraints. Recent learning-based multi-
robot IPP methods use Gaussian Processes (GPs) for target uncertainty, but often rely on simplified sensing models and centralized belief updates. We propose a grid-based spatio-temporal GP-Kalman filtering framework for learning-based multi-
robot IPP. Instead of maintaining one GP per target, we represent anonymous target presence as a single latent field over a discrete workspace grid. The proposed recursive update assimilates footprint-level camera measurements and supports arbitrary fields of view and range-dependent noise. A GP-derived temporal process update inflates uncertainty over time to account for moving targets. For decentralized deployment, each
robot maintains its own mapper and exchanges fixed-size belief summaries rather than raw measurements. Received beliefs are fused using diagonal covariance intersection to remain conservative under unknown inter-
robot correlations. We integrate the mapper with a reinforcement-learning policy for graph-based neighbor selection. In simulation, the centralized deployment improves target visitation and attains about 20% lower posterior target uncertainty than learning-based and classical auction/coverage baselines, a large share of which stems from the belief representation itself. A real-world two-
UAV experiment demonstrates transfer to outdoor multi-
robot search over a large field (>7000 m^2). Code is available at https://github.com/caomuqing/multirobot-ipp.
Read the full abstract ▾
All authors Muqing Cao, Yunwoo Lee, Junbin Yuan, Lorenzo Schenk, Sebastian Scherer
Artificial Intelligence
The Failure Happens Before the Drift: The Social Dynamics of Values in LLM Agent Societies
Farah Atif, Sougata Saha and Monojit Choudhury
Large
Language Model (LLM)-based
agents are increasingly used as proxies for human participants in social science research, yet it remains unclear whether they can faithfully simulate diverse and conflicting human value systems. We present a World Values Survey (WVS)-grounded simulation framework where culturally diverse
agents with different communication styles engage in longitudinal, value-laden discussions. Across approximately 4,000 conversations involving 1,200 personas, 15 topics, and three models (GPT-4o, Gemini-2.5-Flash, and Gemma-4-E4B), we evaluate value faithfulness, value drift, and conversational realism. We find that more than 50% of personas fail to express their assigned WVS profiles from the outset, while 2-7% drift after repeated conversations. Ablations removing demographic details improve faithfulness for some models but do not change the broader trend: simulated value distributions still systematically deviate from the assigned WVS profiles. Compared to human discussions, simulated dialogues show a different trade-off between stylistic consistency and semantic diversity, often producing content-wise varied but stylistically repetitive exchanges. These findings suggest that current LLM
agents can generate plausible conversations, but remain limited proxies for representing and preserving diverse human value profiles over time.
Read the full abstract ▾
Artificial Intelligence
When and What to Teach: Budget-Aware Online Adaptation for Web Agents
Jianwei Zhang, Sihan Cao, Pengcheng Zheng et al. (+7 more)
Web
agents have achieved significant success in automating complex internet tasks but deploying them in real-world environments requires continuous online adaptation. Given that deploying powerful proprietary models remains commercially cost-prohibitive, practitioners must rely on lightweight local models that evolve post-deployment via online teaching from a stronger teacher. However, standard interactive feedback imposes prohibitive costs. We show that conventional trajectory-level preference optimization wastes budget on both unresolvable episodes and redundant execution turns. To resolve these inefficiencies, we propose Score-Guided Online Teaching with Budgeted Trajectory Trimming, a budget-aware framework that systematically orchestrates when and what to teach. Specifically, our framework integrates a solvability-aware teacher gate to dictate when to query the teacher model and a score-guided turn selection mechanism to decide what informative turns to retain. Extensive experiments on MiniWoB and TimeWarp demonstrate that our method achieves comparable first-pass success while reducing teacher calls by 22.6% and student training compute by 52.1% on average. Our code is available at https://github.com/zjw131f1fc/budgeted-online-teaching.
Read the full abstract ▾
All authors Jianwei Zhang, Sihan Cao, Pengcheng Zheng, Ya Wen, Pei Ke, Kuien Liu, Shen Gao, Wei Dong, Yang Yang, Chaoning Zhang
Artificial Intelligence
Reasoning-Aware Compression: Identifying and Protecting Vulnerable Reasoning Circuits for Energy-Efficient LLM Deployment
Leonard Twagirayezu and Prasenjit Mitra
Large
Reasoning Models (LRMs) impose substantial energy costs during deployment, yet current compression methods apply uniform quantization across all components, risking damage to critical
reasoning circuits. We present a
reasoning-aware compression framework that
benchmarks quantization conditions across five
reasoning benchmarks, GSM8K, FOLIO, MATH-500, ProofWriter, and MuSiQue, with hardware-level GPU energy measurement; profiles per-module INT4 vulnerability across all 196-224 (layer, projection) pairs via a perturbation sweep on a held-out calibration split, then selectively restores the most sensitive
circuits to FP16. Three findings emerge. First, INT4 quantization can increase energy by extending
reasoning chains; a 25% power reduction becomes a net energy increase on GSM8K. Second, vulnerability is task-dependent:
attention projections are more critical for mathematical
reasoning, and sensitivity patterns differ by architecture in logical inference. Third, selective compression achieves Pareto-optimal points inaccessible to uniform methods: R1-Qwen-7B Top-10% on ProofWriter gains +12 pp over FP16 at -9.7% energy, validated on held-out data across five
reasoning benchmarks.
Read the full abstract ▾
Artificial Intelligence
SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction
Bowei He, Xiaokun Zhang, Meng Ding et al. (+1 more)
Web
agents need to navigate visually rich, long-horizon interfaces that change across sites, yet most previous
agents still learn each task in isolation and discard the procedural knowledge they accumulate. Recent skill-augmented frameworks take an important first step, but they treat the skill library as a flat or two-tier
prompt-side cache and offer no principled mechanism for compressing redundancy or composing skills recursively. We introduce Scaffold, a self-improving framework for visual web
agents that (i) induces parametric, executable skills from successful trajectories under a multi-instance abstraction constraint, (ii) maintains a recursively composed hierarchy in which higher-level skills invoke lower-level ones, (iii) compacts the library via a minimum-description-length (MDL) criterion and behavioral equivalence checking, and (iv) periodically distills skill-augmented trajectories back into model weights to internalize the abstractions. Across WebArena, VisualWebArena, and a held-out split of Online-Mind2Web, Scaffold improves success rate by $11.1$–$17.2$ absolute points over the strongest skill-augmented baseline and shows monotonic gains across five self-improvement iterations without library collapse. We release the code and documents in the Github \href{https://github.com/BokwaiHo/SCAFFOLD}{repository}.
Read the full abstract ▾
All authors Bowei He, Xiaokun Zhang, Meng Ding, Xue Liu
Software Engineering
Memory as Infrastructure: Reliability Engineering for Persistent Agent Memory in Months-Long LLM-Assisted Development
Mike Helwig
LLM coding
agents are crossing from task-scale to project-scale: single assisted efforts that run for months, across repeated context compactions, on codebases far larger than any context window. We report operational experience from one such effort (a research project under a single continuous Claude Code session line since January 2026, driving a 633,000-line codebase, with its
memory subsystem continuously instrumented since July 2026) and describe SIx Harness, the open-source
memory and continuity infrastructure that emerged from keeping it coherent. The harness combines per-project long-term
memory (hybrid lexical-vector
retrieval over SQLite, fully local), precision-gated context injection, anti-recurrence stores for decisions and dead-ends, conventions engineered to survive compaction, and, the part we argue is missing from operational practice, reliability engineering for the
memory subsystem itself: a session-start health gate with discriminated failure modes, heartbeat telemetry designed so that no enumerated failure mode can pass unrecorded, and alert-fatigue budgeting borrowed from SRE practice. We present what we believe is the first months-scale instrumented operational record of a persistent
agent-
memory subsystem in production development use: 78,933 hook invocations; 85 recorded failures, none silent: 84 in the subsystem's first three weeks, one since, none in the final 20 days; an injection layer whose ten-day precision instrument shows zero false fires against an intact denominator; and three production incidents traced from instrument reading to structural fix. From the record we distill seven design principles, state our limitations plainly (N=1, no control arm, self-reported), and publish a tagged pre-registered ablation protocol that any team can run with the released MIT-licensed kit.
Read the full abstract ▾