Artificial Intelligence
SR-Agent: An Experience-Driven Agentic Framework for Post-Ranking Strategy Refinement in E-Commerce Recommendation
Hanchen Yang, Kaiwen Yang, Junpeng Zhuang et al. (+7 more)
User experience is a first-class objective in industrial e-commerce recommender systems (RS). Post-ranking strategies, which govern diversity, similarity, and exposure over a ranked list, are widely deployed in industrial RS for their simplicity and low serving cost. However, as the online recommendation environment evolves continuously, these statically configured strategies gradually become stale, thereby degrading the user experience. Refining them typically relies on manual inspection, diagnosis, and updates, making it slow, costly, and difficult to scale or reuse. Although recent LLM-based
agents (e.g., RecUserSim, SimUSER, and Self-EvolveRec) offer promising directions, none of them close the full loop of automated, self-evolving strategy refinement. To bridge this gap, we introduce SR-
Agent, which, to the best of our knowledge, is the first agentic framework deployed to refine post-ranking strategies in industrial RS. SR-
Agent unifies three components: (i) a UserSim
agent that applies inspection skills to surface user-perceived bad cases; (ii) an Analysis
agent that consolidates recurring bad cases into structured, reusable diagnoses; and (iii) a constrained Strategy Refinement Harness that maps diagnoses to typed and bounded actions, gated by a four-stage reward pipeline with reversible rollback. Deployed on the Kuaishou e-commerce platform, SR-
Agent continuously runs this refinement loop and, in a one-month online A/B test, increases order volume by 0.71%, browsing depth by 0.34%, and clicked-category diversity by 0.48%, while markedly shortening the refinement cycle and lowering operational cost.
Read the full abstract ▾
All authors Hanchen Yang, Kaiwen Yang, Junpeng Zhuang, Yang He, Keting Cen, Bochao Liu, Zhongbo Sun, An Liu, Zhongteng Han, Chenyi Lei
Artificial Intelligence
Learning to Detect Cross-Modal Negation: An Analysis of Latent Representations and an Attention-Based Solution
Ali AbuSaleh, Leon Hammerla and Alexander Mehler
Detecting high-level semantic concepts like negation across modalities remains a challenge for current
multimodal systems. We analyze this as a fundamental representation learning problem, providing the first evidence that negation does not form a linearly or non-linearly separable class in the latent spaces of standard
vision-
language models (VLMs). We demonstrate that pretrained
embeddings primarily encode modality-specific features, lacking a generalizable negation signal. To overcome this, we propose a novel cross-modal
attention architecture that explicitly models inter-modal dependencies, achieving performance gains of up to +7.03% F1 over unimodal baselines. Our analysis reveals a key asymmetry: while textual negation often appears independently, visual negation is semantically dependent on linguistic context, a finding validated through our statistical analysis of 3,222 political
video-text pairs automatically annotated via Qwen2.5-VL. By combining this analysis with self-supervised
video representations (JEPA2), we advance the modeling of temporal negation. This work provides new methods and insights for learning robust, semantically-aligned representations in
multimodal systems.
Read the full abstract ▾
Artificial Intelligence
LaT: LLM-as-Trainer for Multi-Task Vehicle Routing Solvers
Yang Wang, Ya-Hui Jia, Wei-Neng Chen et al. (+3 more)
Multi-task neural solvers aim to handle multiple Vehicle Routing Problem (VRP) variants within a unified model, avoiding separate training for each constraint combination. However, VRP variants differ in optimization difficulty, while existing methods lack stage-wise feedback on their training status, making the model biased to some specific variants. Although meta-learning can support adaptive training, it typically requires bi-level optimization and additional gradient updates, increasing computational cost. To address this limitation, we propose LLM-as-Trainer (LaT), a plug-and-play training paradigm that uses a pretrained large
language model as an external trainer. LaT periodically analyzes cross-task validation metrics to generate a stage-wise guidance vector. This vector is combined with the current task's constraint vector and injected into each encoder layer, providing the neural solver with additional training information during subsequent policy optimization. Experiments on 16 VRP variants show that LaT improves the solution quality of several state-of-the-art multi-task neural solvers on both trained and unseen variants, supporting the effectiveness and generality of the proposed training paradigm.
Read the full abstract ▾
All authors Yang Wang, Ya-Hui Jia, Wei-Neng Chen, Yi Mei, Wen Song, Zhiguang Cao
Artificial Intelligence
ProEvent: An Event-centric Benchmark for Proactive Agents
Guanzhen Li, Liangming Pan and Leye Wang
Proactive
agents are expected to anticipate user needs and provide autonomous assistance by perceiving environmental context without explicit instructions. A fundamental capability of such
agents is to identify and track users' upcoming events, enabling continuous and event-specific assistance. For example, by recording the time and location of a planned hike, an
agent can deliver weather reminders in advance or provide
navigation support before departure. However, existing works on proactive
agents largely overlook event-centric assistance, and the open-ended nature of proactive assistance poses challenges for reliable evaluation. To bridge these gaps, we introduce ProEvent, the first event-centric
benchmark designed to assess an
agent's ability to proactively maintain a user's timetable based on ongoing instant messaging chats. ProEvent provides synthesized yet realistic chats that consider the dynamic interaction among users, concurrent chat threads, and noise in the real world, and evaluates proactive
agents on response timing, single-step response correctness, and multi-step response correctness. Experiments on eight LLMs and pipelines reveal that current
agents frequently overact and struggle with event cancellation. Notably, even GPT-5.1 only reacts correctly in 26.7% of scenarios. Further qualitative analysis reveals fundamental limitations of current LLMs as proactive
agents, particularly in detecting implicit events and
reasoning from the user's first-person perspective.
Read the full abstract ▾
Artificial Intelligence
Artificial Intelligence for Understanding and Managing Transportation Behavior in Sustainable Smart Cities
Junbiao Pang, Muhammad Ayub Sabir and Fatima Ashraf
Urban transportation systems generate heterogeneous data, yet these data do not automatically become actionable management intelligence. This chapter adopts a behavior-centered perspective on artificial intelligence (AI), treating mobility records and passenger-generated text as behavioral evidence rather than behavioral truth. It examines four directions: bus arrival prediction for service reliability, taxi mobility pattern discovery for demand analysis and planning, abnormal behavior detection for accountable regulatory support, and passenger-perceived risk mining for service improvement. These directions are integrated through a closed-loop framework linking data input, behavior representation, AI inference, decision support, public value, and governance feedback. The chapter identifies data quality,
privacy,
fairness, interpretability, uncertainty, transferability, and human accountability as essential conditions for deployment. It thereby establishes a unified pathway from behavioral evidence to operational, planning, regulatory, and passenger-service decisions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Integrating High-Level Requirements to Low-Level Tests with Machine-Readable V&V Specifications
Mansur Arief, Nur Ahmad Khatim, Ali Akarma et al. (+1 more)
Modern software teams have mature tools for low-level testing, such as pytest, JUnit, and Jest, which make it inexpensive to write unit tests and run them on every commit. Systems engineering, in parallel, has developed rigorous principles for design verification and validation (V&V), which has worked very well across engineering discipline to align user expecations and requirements with developers' deliverables. In practice, however, the two rarely connect, and the link between users' high-level requirements and the low-level tests that machines actually run is maintained by hand, if at all. This gap is increasingly costly for AI-enabled and cyber-physical systems, for which regulators now ask for traceable evidence that high-level requirements are met, while raw test results provide little of the structure such evidence requires. We introduce VNVSpec, an open-source framework that makes V&V specifications machine-readable and executable. With this framework, users state high-level requirements directly or import them from catalogs derived from published standards. Then, the framework checks requirement quality, supports decomposition into module-level requirements with explicit metrics and acceptance criteria, links these requirements to test results through a traceability graph, and compiles the collected evidence into verdicts and audit-ready reports. We evaluate the framework by self-application, in which it is continuously assessed in CI against its own specification of 36 requirements verified by 449 tests, completed within limited time which scales linearly and thus can handle up to 10,000 requirements. We also discuss how the framework extends to testing black-box AI models and AI coding
agents. The framework, its full test suite, the catalogs, and the
benchmark scripts are available at https://github.com/ai-vnv/vnvspec.
Read the full abstract ▾
All authors Mansur Arief, Nur Ahmad Khatim, Ali Akarma, Ahmad Alfan Alfian Irfan
Artificial Intelligence · Cross-listed from cs.LG
Uncovering Latent Reasoning Strategies in Language Models
Awni Altabaa and John Lafferty
A
language model $p_\theta(y \mid x)$ trained on
reasoning tasks learns to solve problems via multiple distinct strategies, yet these strategies are implicit and entangled within the model's response distribution. We study the problem of decomposing the response distribution of a given pretrained
language model into a structured, strategy-conditioned representation. Specifically, we learn a latent-variable factorization $p_\theta(y \mid x) \leadsto (r_\phi(z \mid x), g_\phi(y \mid x,z))$, where a router $r$ maps each input to a distribution over latent strategies $z$ and a generator $g$ produces the response conditioned on that strategy. A key challenge is that the generator, initialized from the base model, already represents $p_\theta(y \mid x)$ without using $z$. Standard variational inference therefore gives the model no incentive to route information through $z$ and can yield a severe form of posterior collapse. To address this, we propose a variational objective that measures fractional information gain relative to the base model's response loss and concentrates reconstruction pressure on
tokens with high base model surprisal, encouraging $z$ to encode strategy-relevant response variation. We introduce a
benchmark of multi-strategy algorithmic tasks and show that this objective recovers latent codes aligned with distinct reference strategies while preserving the base model's response distribution.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning
Tillmann Rheude, Roland Eils and Benjamin Wild
Contrastive learning is increasingly moving toward settings with three or more modalities instead of image-text pairs. Yet, extending models from pairwise to higher-order
multimodal alignment can introduce optimization and representation challenges. We identify encoder Jacobian conditioning as a key factor in trimodal contrastive learning: poorly conditioned encoders exhibit collapsing or amplified singular-value spectra, leading to exploding Jacobian condition numbers and degraded
multimodal alignment. We introduce geometry-preserving encoders (GPEs) by directly conditioning the Jacobian through regularization and demonstrating that simple modifications like LeakyReLU activations and residual paths recover these
geometric benefits. Across a synthetic
benchmark and four real-world
datasets including missing modalities, improving Jacobian conditioning boosts
retrieval and linear probe performance across multiple contrastive objectives, whereas expressive objectives yield little benefit in linear probes. More broadly, our results show that
multimodal contrastive learning depends not only on objective expressivity, but also on the
geometric and optimization properties of the underlying encoders.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Selectivity Matters: Source Node Influence Pruning for Unsupervised Graph Domain Adaptation
Ridong Han, Yawen Shen, Zhongnian Li et al. (+3 more)
Unsupervised Graph Domain Adaptation (UGDA) aims to facilitate knowledge transfer from a labeled source graph to an unlabeled target graph by mitigating cross-domain distribution shifts. Existing methods primarily focus on node-level feature
alignment in latent spaces, relying on the implicit assumption that all source nodes contribute positively to the
alignment. However, this assumption often fails because a node's semantic information is intrinsically coupled with its topological graph structure. Due to structural shifts, source nodes with severe structural deviations (e.g., structural outliers) lack semantic counterparts in the target graph, and forcing
alignment on them introduces severe noise and causes negative transfer. To bridge this gap, we argue that selective source node utilization is superior to full-graph training, thereby shifting the research paradigm from feature-level
alignment to data-level refinement. To this end, we propose Source Node Influence
Pruning (SNIP), a novel model-agnostic, data-centric refinement framework. Specifically, SNIP quantifies the structural discrepancy between individual source nodes and the target domain by integrating multiple centrality measures, assigning each source node an influence score. A rank-based normalization mechanism is further employed to eliminate scale variations across different measures, allowing SNIP to effectively identify and filter out structurally incompatible nodes with low influence scores. As a plug-and-play method, SNIP constructs a refined "sub-source" graph that is inherently more beneficial for subsequent
alignment. Comprehensive experiments across eight transfer scenarios on five real-world
datasets demonstrate that SNIP consistently outperforms competitive baselines and significantly enhances adaptation performance, validating the superiority of selective node utilization over full-graph training.
Read the full abstract ▾
All authors Ridong Han, Yawen Shen, Zhongnian Li, Tongfeng Sun, Xinzheng Xu, Abdulmotaleb El Saddik
Artificial Intelligence
OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment
Wenxiao Fan, Hang Yin and Kan Li
Multimodal large
language models (MLLMs) still struggle with spatial
reasoning that requires perspective transformation. In particular, they often rely on camera-centric cues rather than
reasoning from the reference object's viewpoint, leading to systematic errors in non-camera reference settings. In this paper, we first analyze this failure mode and show that object orientation is a key factor underlying such camera-centric shortcut behavior. To address this issue, we propose OrientSAM, an orientation-aware spatial
alignment framework for
multimodal models. OrientSAM injects explicit orientation information into
multimodal representations through orientation-aware
tokens and
Fourier-based angle encoding, and further adopts a curriculum learning strategy to progressively improve perspective-aware
reasoning. In addition, we build a spatial data construction pipeline to generate orientation-aware spatial supervision from large-scale images. Experiments on Spatial-MM, ViewSpatial, and 3DSRBench show that OrientSAM consistently outperforms strong baselines, especially on non-camera-view, person-centric, and orientation-sensitive tasks. The results further demonstrate that explicit orientation modeling is important for mitigating camera-centric shortcut behavior and enabling more robust allocentric spatial
reasoning in
multimodal models.
Read the full abstract ▾
Artificial Intelligence
FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models
Bing Tian, Haikun Liu, Xiaocheng Zhong et al. (+5 more)
Block-wise
diffusion large
language models (dLLMs) decode sequentially at the block level, enabling effective KV-cache reuse across blocks but making inter-block decoding strictly serial. Prior work has attempted to unlock inter-block parallelism through post-training methods, but achieves only modest speedups and often degrades accuracy. We observe that self-correcting dLLMs offer a training-free alternative:
token-to-
token (T2T) editing can repair
tokens drafted with a slightly stale upstream context, so a downstream block requires only an informative draft rather than a finalized predecessor. This turns block finality from a hard dependency into a scheduling resource. We propose \textbf{\flowblock{}}, a training-free parallel decoding framework built on two mechanisms. (i) Gated Wavefront Decoding admits blocks into a bounded wavefront only when a readiness gate is satisfied, jointly refines active blocks via T2T editing, and commits blocks in order under a windowed block-causal mask that preserves exact frozen-prefix KV caches reuse. (ii) Heterogeneous Wavefront Packing assigns each request an independent wavefront while packing asynchronous windows into dense, shape-stable batched forwards. Across different
benchmarks, \flowblock{} improves
tokens per second (TPS) over LLaDA-2.1 and LLaDA-2.0, two serial block-wise dLLMs, by up to 2.95$\times$ and 4.01$\times$, while reducing latency by up to 53.6% and 77.1%, respectively. It also improves average accuracy by 1.3 points. Compared with D2F, a training-based inter-block-parallel baseline, \flowblock{} achieves higher accuracy and up to 16$\times$ higher batched serving throughput.
Read the full abstract ▾
All authors Bing Tian, Haikun Liu, Xiaocheng Zhong, Zhuohui Duan, Zhaokai Luo, Huayi Jin, Zhiyong Wang, Xiaofei Liao
Artificial Intelligence
Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents
Yitao Wu, Si Shen, Rui Yang et al. (+2 more)
Verify-repair loops are a standard means for large
language model (LLM)
agents to correct faulty plans in code generation, mathematical
reasoning, and tool use. When both the verifier and the repairer are noisy, repair can damage already-correct plans, and reported acceptance keeps rising while true validity falls, so existing methods lack a principled basis for deciding when repair should stop. We propose VRR-Stop, a robust stopping framework for noisy verify-repair-repeat (VRR) loops. A four-parameter noise model separates verifier false acceptance and false rejection from the repair and damage behavior of the repairer. Belief filtering turns repeated verification votes into an estimate of committed validity, and the loop commits or repairs according to the sign of the true marginal gain, which requires only sign identifiability rather than accurate recovery of all parameters. When verifier discrimination approaches zero, calibration itself fails and estimation error can flip the stopping sign, so we pair VRR-Stop with VRR-Guard, an estimation-free fallback that replaces the incumbent candidate only under a sufficient verification margin. On a GSM8K stress setting, VRR-Stop improves final true validity by 60.6 percentage points over fixed five-round repair at an average cost of 0.72 repair rounds. Across settings, stopping reliability is governed jointly by verifier discrimination and the decision margin rather than by the absolute size of estimation error.
Read the full abstract ▾
All authors Yitao Wu, Si Shen, Rui Yang, Hong Peng, Bin Hu
Artificial Intelligence · Cross-listed from cs.LG
TypiCore: A Hybrid Active Query Strategy for Class-Incremental Learning on Time Series
Gabor Szucs, Samuel Jacsev, Marcell Nemeth et al. (+2 more)
Time series data play a pivotal role across numerous domains, including healthcare and manufacturing. In real-world environments, models must cope with distribution shifts over time, a challenge commonly addressed through Continual Learning (CL) techniques. However, existing CL methods face a critical limitation: real-world data streams are rarely fully labeled, making annotation cost a major practical constraint. This paper investigates Active Class-Incremental Learning (ACIL) for multivariate time series, where a model must sequentially learn new classes while selectively querying labels under a fixed annotation budget. We present a systematic evaluation of a wide range of query strategies combined with multiple rehearsal-based approaches, assessing their impact on plasticity, stability, and label efficiency across four
benchmark datasets. Our analysis reveals the limitations of uncertainty-based and distribution-aware methods in achieving strong performance under constrained labeling budgets. To address these shortcomings, we propose TypiCore, a novel hybrid query strategy that alternates between typicality-based and diversity-based sample selection across active learning cycles, enabling the construction of
memory buffers that are both representative and diverse. Evaluated on the TSCIL
benchmark, TypiCore delivers significant improvements over all baselines and matches or surpasses fully supervised continual learning performance on multiple
datasets while requiring a fraction of the available labels.
Read the full abstract ▾
All authors Gabor Szucs, Samuel Jacsev, Marcell Nemeth, Davide Dalle Pezze, Gian Antonio Susto
Artificial Intelligence
Yechao Hong, Haiquan Qiu, Yaqing Wang et al. (+1 more)
Existing self-evolving
memory systems mainly improve
agent memory based on textual outputs, such as task trajectories and reflections. However, this text-based paradigm rarely incorporates internal mechanistic signals, leaving how retrieved
memory is actually utilized during task execution underexplored. This limitation can lead to unreliable error attribution and hallucinated
memory modifications. In this work, we show that
retrieval-head
attention provides a mechanistic signal for revealing segment-level
memory utilization. By aggregating
attention over
memory segments and decision steps, we construct a context utilization
matrix that exposes recurring
memory-use patterns and indicates corresponding refinement strategies. Building on this observation, we propose
Attention-Guided
Memory Refinement (AGMR), a framework that uses utilization patterns revealed by
attention to guide targeted segment-level
memory updates. AGMR corrects or enhances
memory for failed executions, simplifies
memory for successful executions, and verifies each update through re-execution. Experiments on interactive decision-making
benchmarks show that AGMR improves both task performance and
memory efficiency over text-only
memory refinement baselines. Code is available at https://anonymous.4open.science/r/AGMR_code-3262/
Read the full abstract ▾
All authors Yechao Hong, Haiquan Qiu, Yaqing Wang, Quanming Yao
Artificial Intelligence · Cross-listed from cs.SD
Re-Sonance: A Dysarthric Asynchronous Real-Time Speech Conversion System Based on a Three-Stage Cascaded ASR-LLM-TTS Architecture
Yuxuan Wu, Yifan Xu, Junkun Wang et al. (+3 more)
Individuals with dysarthria face significant challenges in professional speaking scenarios such as conferences, presentations, and meetings, where real-time communication is crucial. While existing Augmentative and Alternative Communication (AAC) systems provide basic support, they often fail to meet the demands of professional speaking environments due to high latency and unnatural
speech patterns. This paper presents Re-Sonance, a novel LLM-enhanced
speech-driven AAC system designed for real-time professional speaking scenarios. By integrating Whisper ASR, Qwen LLM, and CosyVoice TTS, Re-Sonance achieves improved
speech intelligibility and naturalness while maintaining real-time performance. Both subjective and objective evaluations using a Mandarin dysarthric
speech dataset demonstrate that our
speech reconstruction approach significantly improved intelligibility while preserving semantic coherence for speakers with mild to moderate dysarthria. Although performance remains limited for severe dysarthria cases, our findings validate the potential of LLM-based methods for enhancing
speech-driven AAC systems, paving the way for more effective and accessible communication technologies.
Read the full abstract ▾
All authors Yuxuan Wu, Yifan Xu, Junkun Wang, Jiayong Jiang, Xin Zhao, Zhaojie Luo
Artificial Intelligence · Cross-listed from cs.CV
Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation
Sangmin Han, Jinho Kim, Jinwoo Kim et al. (+2 more)
Multi-exposure fusion (MEF) expands the luminance range beyond what a single exposure can capture. Combining images taken at different exposure levels requires handling
geometric differences while naturally merging their complementary brightness information. It often demands generative completion where details are missing.
Diffusion-based generative methods address these challenges, however, they are computationally expensive and struggle to preserve fine structures in saturated regions. We propose LIIFusion, a coarse-to-fine framework that balances fusion quality and efficiency in generative MEF. The coarse stage performs low resolution generative fusion, enhanced by an adaptive exposure correction that recovers structure lost in saturated over-exposed areas. The fine stage adapts a local implicit image function into a multi-exposure fusion function: conditioned on the HR OE/UE sources and the coarse output, it queries arbitrary target coordinates and fuses source evidence regardless of the HR input resolution. LIIFusion achieves up to 3.5$\times$ speed-up over existing generative methods while maintaining or improving structural fidelity and perceptual quality. We believe this framework provides an effective pathway toward making generative MEF more practical in real-world applications.
Read the full abstract ▾
All authors Sangmin Han, Jinho Kim, Jinwoo Kim, Dongyoung Kim, Seon Joo Kim
Artificial Intelligence · Cross-listed from cs.LG
Trustworthy Protein-Ligand Binding Affinity Prediction via Reliability-Aware Multi-Engine Fusion
Yongchan Hong, Defu Cao, Wenjin Liu et al. (+6 more)
Accurate
protein-ligand binding affinity prediction is central to computational drug discovery, yet modern docking engines frequently disagree without indicating which prediction to trust. Consensus scoring and ensemble methods improve mean accuracy but treat all predictions identically without interpretable confidence measures or uncertainty decomposition, ignoring the chemical context of each
protein-ligand pair. To address this limitation, we introduce RELIABLE-BA (RELIABiLity-aware Evidential fusion for Binding Affinity), an evidential framework for multi-engine binding affinity prediction. Our model comprises three steps: (1) modeling each engine as an evidential expert via Normal-Inverse-Gamma distributions, (2) scaling epistemic uncertainty through learned reliability from molecular context while preserving each expert's predictive mean, and (3) fusing experts through closed-form aggregation that captures both individual uncertainty and inter-engine disagreement. Experiments on the PDBBind and BDB2020+
benchmarks demonstrate competitive point prediction with substantially improved uncertainty calibration, and additional validation on the SARS-CoV-2 Mpro
dataset and 5HT2A receptor demonstrates applicability to clinically relevant drug targets. Crucially, these uncertainty estimates enable reliable filtering of
protein-ligand pairs, reducing prediction error by up to 25% when retaining only high-confidence pairs. To our knowledge, RELIABLE-BA is the first multi-engine binding affinity prediction framework to combine evidential fusion with context-dependent reliability, offering a principled path toward trustworthy AI-guided drug discovery. Our code is publicly available at https://github.com/yongchand/RELIABLE-BA.
Read the full abstract ▾
All authors Yongchan Hong, Defu Cao, Wenjin Liu, Thomas Ku, Jordy Homing Lam, Emily Nguyen, Willie Neiswanger, Vsevolod Katritch, Yan Liu
Artificial Intelligence
Is Progressive Disclosure All You Need for Long-Context Agents?
Yifeng He, Yinzhe Zhao, Jicheng Wang et al. (+1 more)
Long-document question answering usually forces a choice between loading the whole document into the context window and bolting on a separate retriever. Agentic AI suggests a broader option, giving the
agent the document path and letting it decide how and what to read.
Agent Skills, a standard for packaging expertise into folders an
agent loads on demand, supply a ready mechanism: progressive disclosure, which exposes only what a query needs, from a short description down to the specific passages. Practitioners rapidly adopted this pattern for book-length understanding tasks, but the evidence to support such choices has been anecdotal. We run the first controlled study of the pattern, comparing raw-document
navigation and several designs of
Agent Skills packs against a classical hybrid retriever across three
agent harnesses and three model families on InfiniteBench. On a single book, the gain depends on the harness, running large when the
agent navigates the raw document poorly but near zero when a strong
agent harness already divides and retrieves on its own. When scaling up to tasks that span many books, raw-document
navigation collapses while one-level progressive disclosure degrades more slowly and pulls ahead. A second, deeper routing level never helps and sometimes breaks accuracy outright, so one level is enough. Progressive disclosure buys context, not intelligence: it is redundant while a strong
agent can locate the right passages itself, and decisive once the corpus grows too large to navigate by reading.
Read the full abstract ▾
All authors Yifeng He, Yinzhe Zhao, Jicheng Wang, Hao Chen
Artificial Intelligence · Cross-listed from cs.CR
Detection, Attribution, Narration: An End-to-End Pipeline for Explainable Money Mule Identification
Yuge Zhang, Yuanxing Zhang, Yichao Jin et al. (+7 more)
Money mule accounts are critical facilitators of financial fraud, yet detecting them at scale remains challenging due to the heterogeneous nature of transactional and behavioural data. We present an end-to-end pipeline for customer-level mule detection comprising three stages: (1) a LightGBM classifier trained on 280 engineered features spanning transaction patterns, account demographics, network
topology, and temporal behaviour; (2) a TreeSHAP attribution layer that decomposes each prediction into feature contributions; and (3) a large
language model (LLM) module that converts SHAP attributions into analyst-facing natural-
language narratives. We evaluate across three open-weight LLM families and assess explanation quality through analyst feedback. In a live production deployment, the system achieves a yield rate of 89%, up from 61% under the incumbent rule-based system, with monthly alert volume expanding from 211 to 302, reflecting broader true-positive coverage rather than increased noise. This corresponds to a 60% incremental adverse detection beyond existing review workflows, substantially outperforming the rule-based approach. Qualitative feedback from analysts indicates that LLM-generated narratives reduce cognitive load during alert triage. We further discuss implications of deploying LLM-augmented explainability in regulated financial environments.
Read the full abstract ▾
All authors Yuge Zhang, Yuanxing Zhang, Yichao Jin, Khairul Amsyar Mohd Razis, Nicholas Qi An Choo, Kai Yin Anders Wong, Xinyan Tang, Kenneth Zhu Ke, Wee Keong Dennis Lee, Jingyuan Zhao
Artificial Intelligence
A Dual-Hypothesis Reasoning Framework for LLM Guardrails
Md Asiful Islam, Fahmida Alam and Mihai Surdeanu
We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis
reasoning, a
reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a
prompt before making a safety decision, and (ii) multi-component supervised fine-tuning (MC-SFT), a structured training loss for
reasoning-based guardrails that decomposes LLM outputs into logical components and weights them according to their importance. Existing
reasoning-based guardrails often rely on expensive procedures, such as generating
reasoning traces using larger or closed-source teacher models and applying full-parameter fine-tuning. In contrast, ARBITER uses a cost-effective self-generation strategy for
reasoning traces and LoRA-based parameter-efficient fine-tuning while still achieving better performance than these expensive approaches. Additionally, ARBITER provides faithful evidence-phrase explanations for unsafe decisions, enabling a more transparent and interpretable guardrail method. Experiments on three safety moderation
benchmarks show that ARBITER outperforms existing
reasoning-based and non-
reasoning guardrail baselines, with clear gains in out-of-domain evaluations.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Predictive Training with Latent Imagination for Visual Quadruped Navigation
Yancheng Zhu, Wanli Ma, Chen Han et al. (+3 more)
Reinforcement-learning
navigation policies for legged
robots select actions reactively from current observations and short-term
memory, with limited capacity to anticipate how moving obstacles will evolve in the near future. In dynamic environments, this reactivity causes the
robot to respond too late because collision risk depends on short-horizon scene structure rather than on current obstacle positions alone. Lightweight predictive supervision applied to the policy's recurrent state during training can encode anticipatory obstacle dynamics without modifying the inference-time controller. We augment a reactive LSTM-SRU
navigation backbone with an auxiliary JEPA-style predictor and SIGReg regularization: during training, the predictor supervises the deterministic hidden state to anticipate its own next state; at inference, it is fully discarded, incurring zero additional computational cost. On simulated and real-world
navigation benchmarks with dynamic obstacles, our method substantially improves
navigation success while reducing collision rates through the predictive training signal alone, without additional inference-time parameters. Real-
robot deployment on a Unitree Go2 demonstrates zero-shot sim-to-real transfer: the controller navigates cluttered indoor and dynamic outdoor environments without fine-tuning, with evasive behavior consistent with the collision reduction observed in simulation.
Read the full abstract ▾
All authors Yancheng Zhu, Wanli Ma, Chen Han, Irvin Haozhe Zhan, Bingfeng Qin, Yixin Xu
Artificial Intelligence · Cross-listed from cs.LG
Zhiren Gong, Zihao Zeng, Tiantong Wang et al. (+6 more)
Resource-constrained deployment requires sustaining large
language model (LLM) capabilities as models scale under fixed
memory and computation budgets. Structured
pruning advances this deployment frontier with smaller dense checkpoints, yet deciding what to prune remains bottlenecked by interactions among joint removals. We introduce Cross-Module Co-
Pruning Curvature (CoCurve), which formulates structured
pruning as set-dependent predictive risk over a unified inventory of
attention heads and feed-forward groups. A co-
pruning graph built from single-unit forward ablations assigns individual risk to nodes and reinforcement or cancellation to interaction edges, conditioning each decision on the units already removed. We evaluate 6 LLMs (3B–70B) and 3
vision–
language models (VLMs) across 3 perplexity corpora, 12
language tasks, and 7
multimodal benchmarks. Across the five-model 20–40% grid and the 70B 10–50% sweep, CoCurve ranks first in 53/60 corpus comparisons (15/15 at 70B); matched-quality interpolation permits 2.2–6.6 more
pruning points in 9/10 cases, while CoCurve leads all 6 VLM Avg$_7$ blocks. After the same lightweight recovery, its retained structures remain strongest through 50%
pruning, where the 8B checkpoint regains 10.8 Avg$_{12}$ points; physical slicing delivers $1.58\times$ dense prefill throughput with 41% lower peak
memory. Mechanism analysis across 10 LLMs and 7 VLMs finds organized within- and cross-module edge structure; matched low-saliency, high-coupling removals degrade 19/20 capability groups by up to 23.7 points.
Read the full abstract ▾
All authors Zhiren Gong, Zihao Zeng, Tiantong Wang, Yixin Wang, Honoka Anada, Zijie Wang, Ming Xiao, Chau Yuen, Wei Yang Bryan Lim
Artificial Intelligence
ZifaMem: Structured Memory for Persona, Preference, and Emotional Continuity in AI Companions
Jingzhe Fang, Guozhi Xu, Yunfan Cui et al. (+2 more)
AI companions are judged not only by single-turn fluency but by whether they sustain emotional continuity: remembering who the companion is, what the user prefers, and how the relationship has felt. We present ZifaMem, a structured
memory system that organizes dialogue into session summaries, episodic
memories, and a consolidated user model. Against a deployment-honest comparator that supplies the full raw dialogue history, and under a fixed LLM-as-a-judge protocol with route audits, structured
memory raises pooled four-backbone emotional-intelligence scores by 11.4% (95% CI 6.3% to 17.1%), and persona grounding improves on all four backbones (Claude +42% relative). Multi-turn affect context wins a +39% net preference over a single-turn snapshot (exploratory), whereas an additional
emotion state machine yields no measurable gain on any of five endpoints. Under an identical preregistered protocol, three
memory systems (ZifaMem, Mem0, and filtered verbatim
retrieval) each improve significantly over raw-history deployment, and ZifaMem and Mem0 are statistically equivalent within +/-5 points on the preregistered primary preference endpoint. The ZifaMem SDK, CLI, and portable
Agent Skills are open-sourced at https://github.com/zifacorp/zifamem.
Read the full abstract ▾
All authors Jingzhe Fang, Guozhi Xu, Yunfan Cui, Xiaochen Yang, Zhangyu Hua
Artificial Intelligence
Reinforcement Learning: From Algorithms To Foundation Models
Zihan Ding
Reinforcement learning (RL) provides a framework for sequential decision making under explicit objectives. In its classical form, RL studies how an
agent should act to maximise long-term reward in a dynamic environment. In richer settings, the problem extends beyond a single
agent and fixed environment: intelligent behavior may require strategic interaction, adaptation to uncertainty, and
reasoning over high-dimensional worlds. This thesis studies RL from two perspectives:
algorithms in games and RL in the era of foundation models. The first part focuses on multi-
agent RL in games. It examines how incentives, policies, and
equilibrium concepts interact in competitive and general-sum environments, spanning two-player zero-sum games, large-scale
video games, and multi-player settings with general structure. These works investigate learning in multi-
agent systems and the behavior of RL methods in interactive environments. The second part studies RL with generative and foundation models, motivated by the idea that prior knowledge can enrich sequential decision making. Pretrained generative models and learned world models serve as representation tools and structured priors for planning, control, and policy optimization. The thesis develops
diffusion-based world models, investigates RL for efficient
video generation, explores generative models as policy classes, and studies interactive
video world models in which actions shape future observations. It also addresses long-horizon modeling through architectures with
memory. Together, these contributions present a unified view of RL as objective-driven adaptation in complex sequential domains. From strategic games to generative world models, the thesis highlights how RL connects decision making, environment modeling, and emerging foundation-model capabilities, offering a broader perspective on the principles underlying intelligent behavior.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Kordel Kade France
The Contrastive Olfaction-
Language-Image Pre-training 2 (COLIP-2) model is a
multimodal embeddings space that places olfaction as a first-class citizen among
vision and
language. Molecular structure, gas-sensor readings, odor-descriptor
language, and images are all trained into a single shared representation space, so that a
robot can localize a detected aroma to objects in a scene probabilistically. No ImageNet-scale
datasets of paired image-scent examples exists which warrants the need for their collection. Our intent with the release of COLIP-2 is to demonstrate the limit of what can be built for robotics with open-sourced olfactory data in order to ground the argument for why new methodologies and
datasets are necessary in order to enable advanced olfactory-oriented perception capabilities. We enumerate results from internal testing of the COLIP-2 architecture and make necessary optimizations to run the model at the edge for real-time robotics applications. While developed with robotics in mind, the design of COLIP-2 has been influenced by experts across many disciplines of science in academia and industry, and we hope that the model can be useful in any
multimodal domain requiring olfactory intelligence.
Read the full abstract ▾
Artificial Intelligence
Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?
Fan Yang, Rui Meng and Yuxin Wen
On-policy self-
distillation (OPSD) offers a promising approach for training large
language models without relying on a separate teacher model. However, its effectiveness on complex agentic tasks remains largely unexplored. In this work, we instantiate Feedback-Augmented Self-
Distillation (FA-SD), a self-
distillation algorithm for agentic search that leverages successful demonstrations as privileged information. We identify that models can rely on recurring
reasoning-and-search output templates, producing trajectories that appear diverse but are largely agnostic to the input question, making the KL-based self-
distillation signal uninformative. We term this phenomenon decoding collapse, a failure mode that can be missed by existing evaluation metrics. To understand its underlying cause, we show that although the self-teacher achieves stronger performance, learning remains inherently unstable due to inconsistent supervision signals. We further decompose this inconsistency into model inconsistency and
prompt inconsistency, and show that the latter can significantly degrade the quality of the supervision signal, limiting the effectiveness of self-teacher learning. To mitigate this inconsistency, we introduce an exponential moving average (EMA) teacher to stabilize the self-teacher and provide more consistent supervision signals. Although the EMA teacher requires a warm-up phase during which performance may temporarily regress, it ultimately improves model performance by providing more stable supervision.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Hierarchy-Aware and Anatomy-Guided Learning for Lung Ultrasound Video Classification
Alya Almsouti, Lotfi Mecharbat, Noha Aboukhater et al. (+5 more)
Lung ultrasound (LUS) is a bedside tool for assessing pulmonary edema in patients at risk due to heart failure or impaired kidney function. However, automated LUS analysis remains challenging because of speckle noise, imaging artifacts, and operator-dependent acquisition variability. In this work, we present a deep learning framework for multi-class LUS
video classification that explores two components: hierarchy-aware training, and anatomy-guided learning. Starting from a strong baseline, we introduce hierarchical training strategies and then introduce pleural line mask supervision to guide model
attention toward anatomically relevant regions. We study four clinically relevant classes–healthy, B-lines, consolidations, and mixed B-lines with consolidations–using an open-access
dataset of 1,886
videos from 219 patients, evaluated with patient-level five-fold cross-validation. Results show that hierarchy-aware training improves pathological separation relative to flat classification, while mask-guided
attention supervision achieves the highest mean macro-F1 of 65.7% and produces more localized
attention patterns. Transfer experiments on the external COVID-BLUeS
dataset further show competitive and parameter-efficient adaptation while preserving pleural-focused
attention behavior. These findings suggest that combining clinically structured objectives with anatomy-guided supervision is a practical approach to robust, interpretable LUS
video analysis. Code and model implementations are available at https://github.com/Alya-Almsouti/LUS-
video-classification.
Read the full abstract ▾
All authors Alya Almsouti, Lotfi Mecharbat, Noha Aboukhater, Yousef Alabrach, Siddiq Anwar, Andre Kumar, Ibrahim Almakky, Mohammad Yaqub
Artificial Intelligence · Cross-listed from cs.HC
Human-in-the-Loop User Feedback Affects Perceived Accuracy and Trust, but Task Subjectivity Matters
Donald R. Honeycutt, Mahsan Nourani and Eric D. Ragan
While ML can produce complex models beyond those that a human could produce manually, incorporating human input can often improve performance beyond purely data-driven models. While this feedback could come from system designers or domain experts, in many cases, the end users who regularly use the system will naturally develop an understanding of its flaws and desire the ability to change the system's behavior based on their knowledge. While soliciting feedback from end users can result in significant model improvement over time, introducing these feedback techniques can also affect several human factors-such as trust or perception of system accuracy-that are not yet fully understood and have different effects reported in the existing literature. Therefore, we sought to build on the existing research to further explore how the act of providing feedback can affect user understanding of an intelligent system and its accuracy in different contexts. We present three controlled experiments that study the effects of interactive feedback collections on user impressions in domains with objective and subjective feedback. The results show that in a context where there is an objectively correct answer, providing HITL feedback lowered both participants' trust in the system and their perception of system accuracy, regardless of whether the system accuracy improved in response to their feedback. However, when the feedback being provided involved subjective opinion, no such negative bias was observed. Furthermore, in the objective context, participants distrusted the system over time, whereas participants in the subjective context mistrusted the system over time. These results highlight the importance of considering the effects of allowing different types of end-user feedback on user trust when designing intelligent systems.
Read the full abstract ▾
Artificial Intelligence
Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory
Qingcan Kang, Mingyang Liu, Shixiong Kai et al. (+5 more)
Language agents depend on
memory across interactions. However, the limited context windows of large
language models (LLMs) and their inference costs constrain how much
memory can be used at once. Existing systems mainly follow two strategies:
memory retention and
memory consolidation. Retention keeps raw records and preserves exact details, but relevant evidence may not fit under a tight budget; consolidation compresses and combines records, improving coverage per
token but risking the loss of query-critical details. Neither strategy is universally preferable. This raises two central questions: when should consolidation replace retention, and which operator – Merge, Abstract, or Rewrite – should be selected? We formalize this decision by decomposing each operator's utility into a coverage effect on evidence omitted by retention and a signed replacement effect on raw evidence that already fits. Their balance explains why the preferred action changes with relative budget pressure. We implement this mechanism with Offline Abstraction-Safety (OAS), a lightweight learner that estimates action utilities from pre-generation features with held-out harm calibration. The public LongMemEval and LoCoMo
benchmarks show the same budget-dependent pattern. On LongMemEval, consolidation improves absolute accuracy by up to 48% under tight budgets, whereas retention is preferable under loose budgets; LoCoMo replicates this crossover at a smaller budget, consistent with its shorter evidence. On both
datasets, cross-note abstraction and merging generally outperform local rewriting when compression is necessary.
Read the full abstract ▾
All authors Qingcan Kang, Mingyang Liu, Shixiong Kai, Kaichao Liang, Zhentao Tang, Yuqi Cui, Tao Zhong, Mingxuan Yuan
Artificial Intelligence · Cross-listed from eess.AS
X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System
Yuxiang Zhao, Yichi Zhang, Yanjie An et al. (+10 more)
Real-time
speech-to-
speech translation (S2ST) systems must balance translation quality, latency,
speech naturalness, and speaker consistency. Publicly documented S2ST systems have advanced direct,
multilingual, streaming, and expressive modeling, while proprietary products and APIs increasingly expose real-time translation capabilities to users. However, practical deployment remains challenging for open and reproducible systems, especially in long-form and multi-speaker conversations where partial ASR hypotheses are unstable, turn boundaries are ambiguous, and target
speech must be generated with an appropriate speaker
prompt. We present X-Translator, a low-cost modular cascaded S2ST system that combines streaming ASR, machine translation, and
prompt-conditioned TTS through a session-level runtime controller. The system uses incremental segment commitment to convert unstable ASR streams into translation-ready units, and an online speaker
prompt manager to bind source
speech spans to speaker-specific voice
prompts for synthesis. We evaluate translation,
speech quality, and latency with OpenSTBench, compare against proprietary
speech translation APIs as behavioral baselines, measure long-form voice stability, evaluate speaker preservation in multi-speaker conversations, and assess
multilingual translation quality. X-Translator provides an open platform for understanding the practical trade-offs of deployment-oriented S2ST. Code and demo are available at https://github.com/zhaoyx239/X-Translator.
Read the full abstract ▾
All authors Yuxiang Zhao, Yichi Zhang, Yanjie An, Yanqiao Zhu, Zhanxun Liu, Yushen Chen, Qixi Zheng, Haina Zhu, Yunchong Xiao, Keqi Deng, Shuai Fan, Kai Yu, Xie Chen