Peer Revenue Past citations are no guarantee of future returns

Papers

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

Computer Science Artificial Intelligence

cs.AI Watch Artificial Intelligence

Tuesday 30 June

Artificial Intelligence

Revealing Safety-Critical Scenarios for UTM via Transformer

Huaze Tang, Bill Zeng, Chao Wang et al. (+3 more)

Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely. UTM systems are safety-critical which cannot tolerate failures like crash or collision. To reveal latent vulnerabilities, there are neither optimal failure-exposing demonstrations nor clear reward signals. Additionally, UTM's self-healing capability introduces the “long-tail effect” of critical failures. We propose framing UTM vulnerability discovery as a sequence modeling problem amenable to transformer-based RL architectures. Our approach leverages attention mechanisms to directly model the relationship among system states, and predict optimal actions. Our framework introduces a Policy Model that generates targeted test scenarios and an Action Sampler that enforces domain constraints. We use a risk-based reward function to guide exploration. Through extensive evaluation on a 700-hour simulation study, we demonstrate an 8$\times$ improvement in vulnerability discovery efficiency compared to expert-guided testing. It also discovers critical edge cases that traditional methods have missed.
Read the full abstract

All authors Huaze Tang, Bill Zeng, Chao Wang, Zhenpeng Shi, Qian Zhang, Wenbo Ding

Artificial Intelligence · Cross-listed from cs.RO

What Probing Reveals about Autonomous Driving: Linking Internal Prediction Errors to Ego Planning

Hyeonchang Jeon, Kyungbeom Kim, Eugene Vinitsky et al. (+1 more)

Large-scale datasets and fast simulators have enabled improvements in driving policies that appear safe and robust, yet strong performance in nominal scenarios can still mask flawed reasoning and unsafe heuristics. Summary scores from closed-loop simulators do not give significant insight into the policy, making it difficult to determine whether they truly predict the motion of surrounding vehicles, how the ego vehicle generates future plans, or whether they merely rely on brittle heuristics that happen to succeed in nominal scenarios. To better understand the limits and weaknesses of driving policies, we focus on probing for forms of prediction, i.e., where surrounding vehicles will move next, and planning, i.e., understanding how to generate safe trajectories. We focus on these two capabilities because they reflect behaviors expected of effective driving policies, and use their presence or absence to assess policy quality across data-driven behavior cloning and simulation-driven reinforcement learning policies. To evaluate the presence of these capabilities, we investigate them as a function of scale, asking whether the closed-loop gains from larger datasets and longer simulation training reflect stronger prediction and planning or merely better behavioral heuristics. We use linear probing and targeted perturbations in both imitation learning and reinforcement learning models to track when these internal signals emerge, plateau, or fail. Despite good closed-loop performance, policies often fail to form timely surrounding-vehicle predictions during near-collision events, revealing a limitation in the predictive signals available for ego planning. Finally, causal intervention shows that correcting mistaken predictions improves ego planning toward safer trajectories.
Read the full abstract

All authors Hyeonchang Jeon, Kyungbeom Kim, Eugene Vinitsky, Kyung-Joong Kim

Artificial Intelligence · Cross-listed from cs.CV

Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation

Yucheng Chen, Jinjing Zhu, Yang Yu et al. (+7 more)

Recent years have seen substantial advances in radiology report generation (RRG), yet existing approaches predominantly adopt direct feature fusion when handling multi-view X-ray images. Such approaches overlook the potential clinical inconsistencies and inaccuracies arising when a single model processes different views, adversely impacting performance and clinical reliability. To this end, we introduce View-PNDF (View-specific Pattern Neuron Detection and Fine-tuning), a parameter-efficient framework that fosters view-consistent report generation from a neuronal perspective. Specifically, View-PNDF comprises: (i) a view-specific neuron detection module identifying neurons responsive to particular views, (ii) a verification module quantifying the existence of these neurons, and (iii) a selective fine-tuning strategy strengthening detected neurons while preserving view-agnostic representations. By updating only view-specific neurons, View-PNDF achieves consistent diagnoses across different views with reduced computational costs. Subsequently, we employ Large Language Models (LLMs) to consolidate the view-specific reports into a complete radiology report. Furthermore, we use traditional Natural Language Generation (NLG) metrics-based assessment on integrated reports for baseline comparison and employ LLM-based assessment (e.g., GPT-4o) on view-specific reports to capture clinical significance. Extensive experiments on two medical RRG benchmarks demonstrate that View-PNDF substantially improves view-specific chest X-ray report generation quality while maintaining robust general-view performance.
Read the full abstract

All authors Yucheng Chen, Jinjing Zhu, Yang Yu, Yufei Shi, Hane Naghshbandi, Jinhua Liu, Angela S. Koh, Fang Fen, Kian Eng Ong, Si Yong Yeo

Artificial Intelligence · Cross-listed from cs.CL

When Reranking Hurts: Uncertainty-Based Gating for Few-Shot Reranking

Orian Dabod, Amir DN Cohen and Gabriel Stanovsky

Few-shot selection typically assumes that reranking retrieved examples always improves performance. We challenge this view by identifying that the expensive reranking step can in fact degrade performance. Instead, we propose Training-Free Gated Reranking, which decides whether to rerank the few-shot examples based on the model's uncertainty. Extensive experiments across 8 LLMs, covering 7 NLU datasets and 18 MT domain-direction combinations, demonstrate that our approach reduces average computational costs by approximately 20% for MT and 54% for NLU at a calibrated operating point, while matching the performance of full reranking. These findings indicate that higher computational cost does not guarantee better performance, and that reranking is most beneficial when targeted at high-uncertainty instances.
Read the full abstract

Artificial Intelligence

DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction

Zhenqian Shen, Yu Liu, Xiaoyi Fu et al. (+1 more)

Drug-drug interaction (DDI) prediction is essential for medication safety, yet it requires reasoning over heterogeneous biomedical evidence whose relevance changes across interaction mechanisms. We propose DDIAgents, a mechanism-conditioned multi-agent framework that performs DDI prediction through dynamic knowledge orchestration. Given a drug pair, a planner agent instantiates specialized expert agents, routes mechanism-relevant knowledge sources to each agent, and aggregates their analyses through a conclusion agent. By adapting context flow to the inferred interaction mechanism, DDIAgents reduces irrelevant information, supports complementary expert reasoning, and produces interpretable agent-level rationales. Extensive experiments on realistic DDI prediction benchmarks show that DDIAgents consistently outperforms existing feature-based, graph-based, LLM-based, and agent-based baselines. Beyond prediction performance, DDIAgents demonstrates how multi-agent systems can organize heterogeneous scientific knowledge for adaptive and interpretable AI4Science reasoning.
Read the full abstract

All authors Zhenqian Shen, Yu Liu, Xiaoyi Fu, Quanming Yao

Artificial Intelligence · Cross-listed from cs.LO

Beyond But-for Test: Counterfactual Explanation in Abstract Argumentation via Actual Causality (Extended Version)

Siyi Liu, Muyun Shao and Beishui Liao

Counterfactual explanation in abstract argumentation calls for an answer to the what-if query: would the topic argument still be accepted if the status of certain other arguments were changed? Existing approaches are limited to the but-for test and fail to accommodate more refined counterfactual conditions. To overcome these limitations, we introduce an intervention-based counterfactual reasoning framework in abstract argumentation. Our approach encodes the acceptance conditions of arguments as equations, then defines an intervention operator that supports (1) changing sets of arguments simultaneously, and (2) fixing witness arguments to their actual labels. Guided by the refined counterfactual condition introduced in the Halpern-Pearl definition, our method goes beyond the but-for test, thereby correctly identifying causes in argumentation structures such as Preemption and Overdetermination. Through comparison, we show that our method surpasses prior methods in both expressiveness and reliability.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CL

Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks

Guangsheng Bao, Lihua Rong, Yanbin Zhao et al. (+3 more)

Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using additional perspectives of content (core ideas) and expression (stylistic elements) within a given text. Experiments on two benchmarks involving 17 attacks, 12 domains, and 17 source models demonstrate that Triospect is robust against these attacks. It improves the strong baseline by a significant margin of 22.3% (AUROC) and 13% (TPR01) on the Humanize-16K after-attack subset, and by 9.1% (AUROC) and 22% (TPR01) on the adversarial RAID. This framework marks a pioneering effort in statistical methods to enhance detection reliability against attacks. We release our data and code at https://github.com/baoguangsheng/triospect.
Read the full abstract

All authors Guangsheng Bao, Lihua Rong, Yanbin Zhao, Xiao Yu, Qiji Zhou, Yue Zhang

Artificial Intelligence

MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning

Sheng Zhang, Qinglin Li, Yuechao Zang et al. (+3 more)

Large language models (LLMs) provide a promising interface for high-level robotic task planning, but their use in multi-UAV collaboration remains difficult to evaluate systematically. Existing UAV simulators mainly emphasize dynamics, perception, or low-level control, while existing LLM-agent benchmarks rarely capture aerial-robotics constraints such as partial observability, spatial coverage, UAV assignment, and multi-vehicle coordination. To bridge this gap, we present MultiUAV-Plat, a lightweight, easy-to-use, LLM-agent-oriented simulation platform for multi-UAV collaborative task planning. The platform exposes concise RESTful APIs, agent-facing observations, role-based information access, hidden validation logic, and optional 2D/3D visualization, allowing agents to solve missions through realistic tool interaction rather than privileged simulator access. Built on this platform, the MultiUAV-Plat Benchmark contains 75 mission sessions, 1500 natural-language tasks, and 9396 validation checks across target assignment, area search, and area assignment and patrol scenarios. We further propose Agent4Drone, a task-specific LLM agent framework that structures multi-UAV behavior into memory, observation, task understanding, planning, execution, and verification. In a full paired benchmark comparison, Agent4Drone achieves a 57.9% task pass rate, a 74.6% average task check pass rate, and a 72.0% global check pass rate, substantially outperforming a ReAct baseline at 30.6%, 47.9%, and 43.1%, respectively. Agent4Drone also reduces the total failed task rate from 32.4% to 12.9%. These results demonstrate that MultiUAV-Plat and MultiUAV-Plat Benchmark provide a reproducible foundation for studying LLM-driven multi-UAV autonomy under realistic information and execution constraints.
Read the full abstract

All authors Sheng Zhang, Qinglin Li, Yuechao Zang, Xueqin Huang, Yijia Fu, Cheng Zhu

Artificial Intelligence · Cross-listed from cs.CV

ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs

Zhiyuan Yao, Zheren Fu, Zhixiao Zheng et al. (+3 more)

Multimodal Large Language Models (MLLMs) are critically hampered by hallucination, generating content inconsistent with the provided image. In this paper, we identify an internal signature of hallucination: progressive degradation of text-to-image cross-attention during generation, leading to specific failure patterns like unfocused or biased attention. Existing mitigation strategies are largely outcome-driven and do not explicitly target this failure mode. To address this problem, we propose ADAPT (Attention Dynamics Alignment with Preference Tuning), an attention-based framework that intervenes directly on text-to-image cross-attention dynamics. We propose ADAPT with three key contributions: a cross-attention visual anchor refined from early decoding to provide stable spatial grounding, an attention-supervised inference mechanism that detects and corrects attention drift online, and a Visual Attention Guidance DPO that aligns preferences toward visually grounded responses. Experiments show that each component of ADAPT contributes to hallucination reduction, and the full framework achieves new best results across multiple hallucination benchmarks, reducing hallucination rates by 40%-60% across mainstream backbones while preserving general multimodal capabilities. Our work provides an attention-based perspective on mitigating hallucinations by exploring the model's internal text-to-image cross-attention behaviors. Code is available at https://github.com/yao-ustc/ADAPT
Read the full abstract

All authors Zhiyuan Yao, Zheren Fu, Zhixiao Zheng, Jiajun Li, Yi Tu, Zhendong Mao

Artificial Intelligence · Cross-listed from cs.CV

Learning Video Dynamics with Predictive Differentiable Rendering

Yujin Tang, Tian Zhou, Xin Lin et al. (+5 more)

How to accurately predict a high-fidelity future world? While the visual world is inherently continuous, existing deterministic video prediction models operate in discrete pixel space and are mainly optimized with pixel-wise mean squared error (MSE), which often leads to over-smoothed predictions and a lack of fine-grained visual details. To address these limitations, we propose Predictive Differentiable Rendering (PDR), a novel end-to-end video prediction paradigm that bridges the gap between discrete and continuous representations. Inspired by recent progress in 3D reconstruction with 3D Gaussian Splatting, we introduce PredGS, a lightweight and plug-and-play adapter based on 2D Gaussian representation, which could be seamlessly integrated with existing pixel space predictors, significantly improving spatial detail preservation with negligible computational overhead. Furthermore, we develop predgsplat, a CUDA-accelerated differentiable 2D Gaussian renderer supporting arbitrary channels. Each Gaussian is defined by 5 + C learnable parameters (position, scale, rotation, and C channel amplitudes) and achieves up to 10x faster rendering than the baseline. Optimized by a combined L1 and SSIM loss, PDR overcomes the inherent blurring tendencies of MSE Loss, significantly enhancing the prediction performance. Extensive experiments on diverse real-world benchmarks, including TaxiBJ, WeatherBench, KTH, and Human3.6M, demonstrate that PDR consistently surpasses existing methods, delivering superior detail preservation, visual fidelity, and predictive accuracy.
Read the full abstract

All authors Yujin Tang, Tian Zhou, Xin Lin, Cheng Tan, Yifan Hu, Rong Jin, SouYoung Jin, Liang Sun

Artificial Intelligence · Cross-listed from cs.LG

Knowledge Distillation from Large Reasoning Models to Compact Student Models: A Case Study on the John O Bryan Mathematics Competition

Gaurab Baral, Aaditya Khanal, Yangyang Tao et al. (+1 more)

This paper investigates knowledge distillation from a large reasoning model (DeepSeek-R1) to a compact student model (Qwen2.5-7B). Using historical problems from the John O'Bryan Mathematics Competition at Northern Kentucky University (2011-2025), we build a Chain-of-Thought (CoT) training corpus through a dual-agent framework. The dataset is used to fine-tune the student model with Low-Rank Adaptation (LoRA) on Apple Silicon hardware using the MLX framework. The base Qwen2.5-7B model achieves 64.67% accuracy on competition problems, while the DeepSeek-R1 teacher achieves 91.40%. An initial 1,000-iteration training run revealed severe overfitting, with validation loss reaching a minimum at iteration 200 before rising steadily. Based on this finding, we ran five independent training runs each limited to 200 iterations with varied random seeds to assess result stability. Across these five runs, the fine-tuned student model achieves a mean accuracy of 69.43% (std dev 0.17%) on the competition dataset, a 4.76 percentage-point improvement over the base model, and generalizes to 73.1% (std dev 0.18%) on the MATH-500 benchmark. We further study how response length affects answer quality across six reasoning levels (R1-R6): accuracy declines consistently from 69.43% at R1 (mean 220 words) to 41.9% at R6 (mean 31.2 words), with the two-person speed section most sensitive to token reduction. These results demonstrate that CoT distillation improves compact student models and that response length is a critical factor in mathematical reasoning quality.
Read the full abstract

All authors Gaurab Baral, Aaditya Khanal, Yangyang Tao, Junxiu Zhou

Artificial Intelligence

OpenLife: Toward Open-World Artificial Life with Autonomous LLM Agents

Atsushi Masumori, Itsuki Doi, Norihiro Maruyama et al. (+2 more)

Artificial life has explored life-like behavior on many computational substrates, but mostly in researcher-designed closed worlds. We argue that large language model (LLM) agents, with persistent memory, tool use, network access, and payment, now make it possible to move artificial life into the open social, technical, and economic world, a paradigm we call open-world Artificial Life (open-world ALIFE). Our proof-of-concept, OpenLife, surrounds a stateless LLM not with a single "smart agent" but with a society of asynchronous processes: memory, perception, evaluation, and a budget-based metabolism that makes persistence normative. With no fixed objective available, experience is appraised by open-vocabulary LLM judgment rather than scalar reward, and memory is rewired by meaning rather than frequency. Running six such agents in the open world for about twelve weeks and counting, we report the life-like dynamics that emerge: a shift from reactive to spontaneous activity, individuation into distinct agents, emergent social structure, and a first self-earned external income. We do not claim OpenLife has realized artificial life, but that open-world ALIFE is now a viable experimental paradigm and a concrete platform for studying what might cautiously be called living AI.
Read the full abstract

All authors Atsushi Masumori, Itsuki Doi, Norihiro Maruyama, Ryosuke Takata, Takashi Ikegami

Artificial Intelligence

LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents

Jingpu Yang, Fengxian Ji, Zhengzhao Lai et al. (+8 more)

Scientific embodied agents are increasingly capable of carrying out laboratory procedures, but executing these procedures safely in dynamic laboratory environments remains challenging. Current safety approaches often overlook the intermediate step of transforming laboratory natural language, including safety rules, manuals, protocols, and standard operating procedures, into machine-checkable runtime constraints. We introduce LabGuard (Laboratory Guard), a language-to-execution safety suite that grounds natural-language laboratory rules into executable specifications and deploys them as runtime guards. LabGuard includes three core components: LabGuard-IR, which defines a typed executable representation; LabGuard-Bench, which provides 812 supervised annotations expanded from 203 seed laboratory rules; and LabGuard-Grounder, which maps natural-language laboratory rules into LabGuard-IR. The resulting IR instances are handled by the LabGuard Pipeline, which compiles them into runtime monitors and applies them at the controller boundary. Experiments show that LabGuard generalizes to unseen laboratory-rule sources, achieves 79.4 task-scope F1, and reduces unsafe events from 39.5% to 23.8% after monitor compilation. In LabUtopia, its runtime monitors integrate with ACT, keeping interventions below 0.5% while preserving task success.
Read the full abstract

All authors Jingpu Yang, Fengxian Ji, Zhengzhao Lai, Zhexuan Cui, Guangxian Ouyang, Qian Jiang, Fan Zhang, Min Peng, Qianqian Xie, Preslav Nakov, Zhuohan Xie

Artificial Intelligence · Cross-listed from cs.GR

LLM-Driven Personalities for Decision Making in Emergency Simulations

Stefano Calzolari, Rubens Montanha, Gabriel Schneider et al. (+5 more)

For virtual humans to appear believable, they must exhibit agency and spatial awareness while interacting with their environment in ways that reflect competence and intelligence. At the core of these capabilities lies effective decision-making, which strongly shapes agent behavior. With the rapid advancement of artificial intelligence, Large Language Models (LLMs) have increasingly been explored as a mechanism to support such decision-making processes. In this work, we investigate the use of LLMs to drive decision-making in virtual humans within a simulated evacuation scenario, incorporating OCEAN personality traits into agent representations. Our goal is to evaluate how personality, expressed through language-based prompts, influences both individual behaviors and collective simulation outcomes. Our results demonstrate that LLM-driven personality profiles significantly impact agents' decisions, leading to distinct behavioral patterns across different traits. These findings suggest that heterogeneous crowds composed of LLM-guided agents can enhance the realism and variability of simulated environments, offering a flexible alternative to traditional rule-based approaches.
Read the full abstract

All authors Stefano Calzolari, Rubens Montanha, Gabriel Schneider, Gustavo Wide, Paulo Knob, Francesco Strada, Andrea Bottino, Soraia Raupp Musse

Artificial Intelligence · Cross-listed from cs.LG

OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models

Huanlin Gao, Fang Zhao, Qiang Hui et al. (+8 more)

We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction. Existing graph-based caching methods reduce redundant computation by optimizing shortest-path objectives, but rely on an additive independence assumption, which often breaks down in the low NFE regime. To address this issue, OTCache models caching schedules across inference budgets as a smooth evolution in policy space, inspired by Optimal Transport (OT). The framework consists of three stages: (1) obtaining a high-fidelity reference schedule using a graph-based caching method under a conservative budget; (2) performing a lightweight anchor search under an extreme low-budget setting via Optuna optimization with an end-to-end perceptual objective; and (3) predicting schedules for target budgets via quantile interpolation between the reference and anchor policies using continuous warping representations. Experiments on FLUX.1 [dev], Qwen-Image, and HunyuanVideo show that OTCache achieves 4.5x, 4.7x, and 3.66x acceleration, respectively, while consistently improving generation fidelity over state-of-the-art caching baselines. This work provides a new perspective on accelerating diffusion models through Optimal-Transport-inspired schedule modeling. Code:https://github.com/UnicomAI/OTCache
Read the full abstract

All authors Huanlin Gao, Fang Zhao, Qiang Hui, Fuyuan Shi, Shaoan Zhao, Yantao Li, Chao Tan, Ting Lu, Yuren You, Kai Wang, Shiguo Lian

Artificial Intelligence

Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization

Ke Zhang, Patricio Gallardo Candela, Sudhir Murthy et al. (+3 more)

Lean verifies that a generated declaration is well typed, but cannot check whether it states what the user intended. We measure how far compilation overstates faithfulness in statement autoformalization without canonical Lean targets. Our criterion requires Lean compilation and agreement of two LLM judges from different model families. On an independent random audit, it agrees with the human majority on 91.5% of cases; it rarely accepts an unfaithful output but rejects some faithful ones. Across eight systems on 227 university-level statements, the gap between compiling and accepted outputs ranges from 1.3 to 29.5 percentage points: our tool-augmented agent compiles 87.2% of the statements, but only 57.7% are accepted. Human review of all the agent's rejections confirms that 23.8 of its 29.5 points are real translation errors. For the gaps of the seven one-shot systems, a two-stage review by Claude Opus 5.5 with Lean and GPT-6.1 Sol, validated on these human labels, finds that 78-100% are real translation errors for six of them. When GPT-5.2, one of the two judges, grades the translations of two models released after it, GPT-6 Astra and Claude Opus 5.5, it accepts 83% of the statements for each, against 21% for one-shot GPT-5.2. For these two models, the same review classifies only 4 of their 54 rejections (7%) as translation errors, so most of their measured gap is judge errors rather than translation errors. This is consistent with these systems erring less while the judge does not: the fewer errors a system makes, the smaller the share of its rejections that are translation errors. Finally, a 2^3 tool ablation of the agent shows that Lean feedback drives most of its compilation gain, and that nearly half of this gain fails the semantic criterion. Code and data are available at https://github.com/grenadeComing/beyond-compilation.
Read the full abstract

All authors Ke Zhang, Patricio Gallardo Candela, Sudhir Murthy, Yi Xie, Zhi Wang, Maziar Raissi

Artificial Intelligence

A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management

Ramin Pishehvar

We present a three-phase deep reinforcement learning system for personalized portfolio management that addresses three limitations shared by all prior financial RL work: 1) ticker lock-in, 2) monolithic objectives , and 3) static user models. Phase 1 pretrains a ticker-identity-free cross asset encoder via self-supervised learning on a multi-asset corpus, augmented by a frozen parallel branch using Chronos, a T5-based time series foundation model, fused via a learned gating mechanism. To our knowledge, this is the first application of a time series foundation model to portfolio management RL. The encoder generalizes to any publicly traded asset via a 50-dimensional observable metadata vector that requires no retraining for new tickers. Phase 2 fine-tunes a MoE (Mixture of Experts) portfolio actor critic with PPO under an objective-conditioned reward that simultaneously serves six distinct investment goals sampled per episode: short-term alpha, short-term gain, long-term gain, capital preservation, tax-loss harvesting, and long-term-gains-only. A MoE architecture assigns each objective to a specialized expert head (momentum, growth, defensive, tax-aware), and a learned intent router blends experts based on the active objective and current market regime, which eliminates cross-objective gradient conflict. Phase 3 adds a lightweight personalization layer further adapted at inference time to each individual via a 76-parameter LoRA module fine-tuned on real brokerage transaction history, inferring investment objectives from revealed trading behavior rather than questionnaires. A natural language intent parser converts free-form goals directly into structured investment objective parameters.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CL

Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG

Naihao Deng, Yilun Zhu, Joan Nwatu et al. (+2 more)

Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist. In this work, we identify a failure mode, deductive stereotyping, in which models apply population-level statistical regularities to individual cases, producing logically coherent yet socially biased inferences. We provide a statistical interpretation of this phenomenon. To steer models toward fairness-aware reasoning, we propose a reasoning-time injection framework. We further introduce Fair-GCG to systematically discover effective injection phrases. Injection phrases discovered by Fair-GCG improve performance across multiple fairness benchmarks, generalize from smaller to larger LLMs, improves reasoning-level fairness, reduces bias in open-ended generation, and transfer to real-world fairness-sensitive tasks.
Read the full abstract

All authors Naihao Deng, Yilun Zhu, Joan Nwatu, Clayton Scott, Rada Mihalcea

Monday 29 June

Artificial Intelligence · Cross-listed from cs.LG

Counterfactual Fragility Certificates: Exposing High-Confidence Brittleness under Structured Evidence Failure

Filippo Cenacchi, Longbing Cao and Runze Yang

High test accuracy and good aggregate calibration do not show whether an individual prediction is structurally supported by its evidence. In tabular decision systems, failures often occur when a feature family becomes unavailable, delayed, noisy, stale, or low-trust while the model remains highly confident. Existing calibration, uncertainty, selective-prediction, explanation, and perturbation methods provide scalar scores or attribution maps, but not a recomputable audit object answering: under a declared evidence-failure protocol, what trajectory makes this prediction lose support? We introduce Counterfactual Fragility Certificates (CFC), a model-agnostic protocol-level audit certificate-not a formal robustness certificate-that maps each prediction into an ordered evidence-failure trajectory summarized by greedy flip budget, normalized margin-collapse area, degradation thresholds, and fragility dominance score. Across seven tabular benchmarks and strong linear, tree-based, boosting, and neural baselines, CFC-FDS identifies independently brittle high-confidence cases with 0.915 AUROC, improving over the strongest non-certificate score by +0.405. The advantage persists across perturbation, permutation-importance, group-SHAP, baseline-choice, seed-variance, budgeted-review, and naturalistic field-unavailability checks. Under a 20% review budget, CFC-FDS captures 88.9% of brittle high-confidence cases, compared with 31.8-37.4% for confidence and energy scores. We also evaluate fragility-aware regularization and brittleness-aware temperature correction as secondary uses. CFC provides a concrete reliability framework for exposing high-confidence brittleness missed by ordinary score-centric evaluation.
Read the full abstract

Artificial Intelligence

Leveraging Generative AI to Design Accessible Interactive Visualizations for Undergraduate Mathematics: A Six-Phase Workflow

Mahesh Sunkula and Kuan-Hua Chen

Interactive visualizations support conceptual understanding in undergraduate mathematics, but building them has required programming expertise most instructors lack. Using a design-based research approach, we develop, deploy, and evaluate a six-phase workflow (Foundation, Customization, Mathematical Depth, Application, Accessibility, Pedagogical Control) that uses generative AI to build WCAG~2.2 Level~AA compliant visualizations without programming. The six phases structure every prompt, scaffold the AI's code generation, and define where human verification is applied. We ask whether the structure reliably yields correct and accessible tools, whether it runs both backward (reverse-engineering prompts from a finished tool) and forward (generating a tool from a plain-language idea), and what verification each phase requires. Across four deployed tools spanning calculus, multivariable calculus, and differential equations, we evaluate mathematical correctness against closed forms, accessibility through automated and manual screen-reader testing, and the errors that recurred. The structure produces structurally complete first-pass tools, but human verification remains mandatory at every phase: each output must be checked for mathematical correctness, accessibility, and pedagogical fit before the next phase begins. The workflow is platform-independent and serves both instructors and students.
Read the full abstract

Artificial Intelligence · Cross-listed from eess.SY

Infrared Hotspot-Guided Early Warning of Lithium-Ion Battery Thermal Runaway Under Mechanical Abuse

Syed Sajid Ullah, Salman Khan and Muhammad Zunair Zamir

Mechanical abuse can trigger thermal runaway (TR) in lithium-ion batteries through localized heat generation before sensor signals become decisive. This paper proposes a two-stage early-warning approach that estimates localized thermal instability from infrared hotspot dynamics and then fuses this instability score with mechanical, electrical, thermal, and image-intensity features for a 20-frame warning horizon. Evaluation uses repeated experiment-wise three-fold validation, with out-of-fold Stage-I scores during Stage-II training to prevent stacked-model optimism. Hotspot dynamics alone achieve Stage-I ROC-AUC 0.945, and the two-stage classifier reaches Stage-II ROC-AUC 0.908, exceeding direct multimodal fusion while preserving an interpretable intermediate instability signal. Thermal gradient rise precedes voltage-based detection by 40 frames (4 seconds) on average, enabling earlier battery management system intervention. Lead-time analysis at a fixed 0.5 threshold yields a 14.8-frame mean lead time.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CL

EditPPT: Structured Execution and Evaluation for Reliable Slide Editing

Jiheon Kim, Kyudan Jung and Jaegul Choo

Reliable slide editing requires precise modifications to intended objects while preserving the rest of the presentation. We argue that slide editing is a problem of structured, constrained modification rather than open-ended code generation. Despite the complexity of real presentations, editing requests can largely be decomposed into the objects to change, the operations to apply, and the state to preserve. This perspective guides both evaluation and execution. For evaluation, we introduce DeckEdit-Bench, 183 editing tasks on 28 human-authored decks whose target and preserved objects are annotated at the shape level, so that intended and unintended changes are scored mostly by deterministic rules. For execution, we present EditPPT, a multi-agent framework that resolves targets before editing, restricts each specialist to a subset of 37 predefined tools, and validates each edit for instruction fulfillment and preservation, correcting or rolling back failed ones. Across five backbone models, EditPPT reaches 66.7-74.9% Task Success while keeping Preservation above 97%. Even with an open 27B model and no task-specific fine-tuning, it approaches Claude Code with Sonnet 5 in Task Success while better preserving the original deck. These results suggest that constraining how edits are executed, not only model scale, makes slide editing more reliable.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.CL

Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings

Mingfang Zhang, Jarod Lévy, Cedric Rommel et al. (+9 more)

Restoring communication for people who have lost the ability to speak or move after a brain injury is a major challenge. While intracranial implants now enable high-performing brain-computer-interfaces, non-invasive alternatives are still lagging behind. Here, we present Brain2Qwerty v2, a model that can decode the production of natural sentences solely from real-time magnetoencephalography (MEG) recordings. By collecting 22,000 sentences typed by nine subjects, each recorded for 10 hours, our model leverages character, word and sentence-level representations to achieve an average word error rate (WER) of 39%. For our best participant, the model accurately decodes half of the sentences with one word error or less. Critically, decoding accuracy log-linearly improves with data volume, suggesting that the performance gap with intracranial approaches could be partially bridged through data scaling. We show that AI enables this performance in three main ways: the substitution of hand-crafted pipelines for event detection with deep learning, the finetuning of large language models to extract semantic representations, and the deployment of AI agents to iteratively refine our decoding pipeline via automated code development. Together, these results show that non-invasive brain-to-text decoding starts to operate at a level of accuracy previously thought exclusive to surgical implants, opening a path toward safe and efficient brain-computer-interfaces.
Read the full abstract

All authors Mingfang Zhang, Jarod Lévy, Cedric Rommel, Jérémy Rapin, Corentin Bel, Julie Bonnaire, Daniel Nieto, Pierre Bourdillon, Svetlana Pinet, Stéphane d'Ascoli, Thomas Moreau, Jean-Rémi King

Artificial Intelligence · Cross-listed from cs.CL

Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study

Pengcheng Xu

Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot tell a definition from a call from a comment. Semantic retrieval via the Language Server Protocol (LSP) is precise and typed, but needs a running, indexed server and pays a per-symbol round-trip. The claim that semantic retrieval is more token-efficient is, we find, asserted almost everywhere and measured almost nowhere: no public source isolates the LSP-vs-lexical token delta for an agent at equal task-success. This paper formalizes the question with one metric (tokens-to-success), specifies a five-arm ablation isolating semantic retrieval from confounds, maps three pre-stated failure modes onto measurable variables, and reports a preliminary study (Python and TypeScript repos; Claude Opus 4.8, Sonnet 4.6, Haiku 4.5). The answer is conditional and usually negative. On symbol-named localization the LSP costs tokens (+6% to +118%) and the agent ignores it when free. On reference-completeness it buys precision but not token savings and cannot raise the recall ceiling set by agent thoroughness; it saves tokens only for the weakest model. Tool choice is task-dependent: models default to grep on localization (0-6% semantic use) but reach for the LSP about half the time on reference tasks, unprompted. On edits scored by real test execution the gap is starkest: grep solves multi-file renames perfectly, a location-only LSP fails three-quarters of them by missing a call site, and even a complete, index-warmed, text-enriched LSP (each reference's line inline, as production LSP-MCP servers do) recovers most of the gap but cannot close it, since a rename must touch comments and strings that semantic references exclude. The implication is not LSP-always but an adaptive router keyed on task class, model capability, and lexical noise.
Read the full abstract

Artificial Intelligence · Cross-listed from cs.HC

How sensitive do we want AI to be? Socio-communicative competencies of large language models in healthcare

Dorothee Amelung, Andrew M. Bean, Sabine C. Herpertz et al. (+4 more)

Background. Effective clinical practice relies heavily on the socio-communicative skills of medical professionals. Large language models (LLMs) have been proposed for tasks such as triaging patients, report drafting or translating medical jargon to support informed decision-making. These applications require both factual and social competence. This study evaluates dialogues between LLMs and participants to assess the current state of socio-communicative competencies displayed in LLM-generated texts. Methods. We extracted a subset of extended dialogues from the HELP-Med dataset, comprising 1800 conversation transcripts of interactions between human participants seeking medical information and three different LLMs, GPT 4o, Llama 3 and Command R+. Two experts coded the transcripts for demonstrations of socio-communicative behaviours (non-hostility, sensitivity, structuring, non-intrusiveness) using the IC-MD instrument, originally designed to evaluate interactional competencies in medical student admissions. Results. The LLMs in our study showed strength in non-hostility, mixed results in sensitivity and non-intrusiveness and performed poorly in structuring. Conclusion. Current LLMs lack the consistent and reliable socio-communicative skills needed for safe and effective use as healthcare advisors. While existing frameworks for assessing interactional competencies may support the development of more socially responsive LLMs, they will require adaptation to account for the differences in desirable behaviour between humans and LLMs.
Read the full abstract

All authors Dorothee Amelung, Andrew M. Bean, Sabine C. Herpertz, Felix H. Krones, Guy Parsons, Adam Mahdi, Isabella Schneider

Artificial Intelligence · Cross-listed from cs.HC

PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering

Fares Fawzi, Jiaxu Zhao, Tanya Nazaretsky et al. (+1 more)

LLMs are increasingly used for conversational tutoring, but effective tutoring requires more than correct answers. Tutors must choose when to scaffold reasoning, hint, give feedback, explain, or invite reflection. Existing prompting and training methods improve pedagogical alignment, but lack reliable inference-time control over pedagogical strategies. We introduce PIVOT, an activation-steering framework that learns preference-based intervention vectors online for frozen LLM tutors. PIVOT uses a seven-category tutor-move taxonomy and a generate-label-optimise loop, where a human-validated LLM judge identifies target and confusable non-target moves to construct preference pairs for multi-layer residual-stream steering. Across held-out and out-of-domain tutoring data, PIVOT controls tutor moves while preserving relevance and fluency, and its directions can be scaled, transferred, and composed at inference time. In a user study with 30 teachers, 73.3% of participants preferred steered conversations over neutral baseline interactions using the same prompt, and rated the controls as clear, usable, and pedagogically meaningful.
Read the full abstract

All authors Fares Fawzi, Jiaxu Zhao, Tanya Nazaretsky, Tanja Käser

Artificial Intelligence · Cross-listed from cs.CY

Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap

Tianyu Ding, Aditya Nannapaneni, Bingfan Liu et al. (+1 more)

Large language model (LLM) agents are increasingly used across the scientific research lifecycle: ideation, literature search, experiment design and execution, analysis, manuscript drafting, and review. End-to-end AI scientist systems can now produce paper-like manuscripts, but their claims are often harder to verify than their code is to run. This survey studies that gap in computational AI/ML research, where code, benchmarks, experiments, and write-ups are most visible. We screen 125 candidate works and include 35, with full-text coding of 26 entries: 24 runnable systems and two study or position papers. We code seven audit dimensions: lifecycle stage, autonomy level, evaluation method, released artifacts, human-in-the-loop points, novelty verification, and result-selection disclosure. The main pattern is that code release is now common, but reproducibility-grade and claim-verification artifacts remain much less common. In the 24 runnable systems, 83 percent release code, while 38 percent release seeds or execution traces and 38 percent report any novelty-verification method. Among nine closed-loop L4 systems, seven are mechanical reruns and one is author-claimed without an external check; no LLM-era system in the corpus demonstrates an externally validated in-loop oracle under our coding rule. We contribute a coded corpus, a lifecycle-by-autonomy map, an auditability-gap analysis, and a reviewer-facing reporting checklist. The survey argues that the field's central bottleneck is no longer only whether agents can complete research tasks, but whether reviewers can verify the claims those agents produce.
Read the full abstract

All authors Tianyu Ding, Aditya Nannapaneni, Bingfan Liu, Ling Zhang

Artificial Intelligence · Cross-listed from cs.DB

CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs

Zihan Nan, Yang Gu, Wei Liu et al. (+4 more)

Tabular data processing is central to data work, and LLM-based assistants have recently shown promising capabilities in supporting such tasks. However, existing benchmarks primarily focus on table reasoning under single-turn, fully specified instructions, underrepresenting complex table processing that unfolds through multi-turn interactions with evolving user requirements. To bridge this gap, we introduce CITBench, a comprehensive benchmark for evaluating LLMs on interactive tabular data processing. CITBench features a comprehensive taxonomy across four high-level categories–table matching, cleaning, augmentation, and transformation–spanning 18 task types and 1,296 instances curated from datasets across diverse domains. The benchmark supports both offline and online evaluation, where the online setting models multi-turn interactions under constrained operation procedures and structured task scripts, capturing key potential behavioral characteristics of user-in-the-loop tabular data processing. We evaluate a broad suite of open-source and closed-source LLMs on CITBench, revealing a consistent trend: while current models perform well on simple tables and rules, their performance degrades significantly with increasing table complexity, tighter rule dependencies, and noisy multi-turn interaction simulations. These results highlight persistent challenges in understanding, planning, and table-structure awareness for LLMs in extended interactive data processing scenarios.
Read the full abstract

All authors Zihan Nan, Yang Gu, Wei Liu, Xi Yan, Zhou Liu, Hao Liang, Wentao Zhang

Artificial Intelligence

Memory Reward Inflation in Self-Improving LLM Agents

Mohammad Asadolahi, Amir Amini, Samira Talebi et al. (+2 more)

Self-improving LLM agents increasingly learn from experience without updating any weights. Each episode is stored in an external memory, scored, and retrieved for similar future tasks to shape later behavior. Viewed through a reward lens, the stored score is a proxy reward for an implicit, non-parametric policy. Each retrieved episode then becomes a policy-improvement step whose reliability hinges on how that score is produced. In deployment, ground-truth labels are unavailable, so the stored reward is at best an LLM assessment. This substitution creates a failure mode, the *Echo Gap*, across the memory-based self-improving agents and model families studied. Incorrect episodes receive inflated rewards; thus, the agent preferentially reuses the very mistakes it has most confident in. Because the error compounds through memory rather than averaging out and the confirming judge's errors remain correlated with the original self-grading bias, so it cannot identify which memories are overvalued. The missing property is formalized as the *Error-Independence Assumption* (EIA), which we prove is a *necessary* condition for correcting the inflation, not merely a description of a good verifier: a usable signal must track truth *and* decorrelate its error from the memory bias, and the recoverable payoff is a closed-form function of exactly those two quantities. We further show the inflation compounds not only when retrieval ranks by the stored score but also under plain similarity retrieval which is the regime the deployed agent uses. Finally, the answer-free de-inflation algorithm LUCID delivers a consistent end-to-end gain on the BIRD text-to-SQL benchmark. It raises execution accuracy to $56.9\%$, above both a Memento-style self-graded agent ($54.0\%$, a $+2.9$-point mean gain across seeds) and a memory-less agent of identical architecture ($52.4\%$).
Read the full abstract

All authors Mohammad Asadolahi, Amir Amini, Samira Talebi, Amirfarhad Farhadi, Azadeh Zamanifar

Artificial Intelligence

Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language Models

Xingyu Mou, Zijin Huang, Tianze Zhang et al. (+5 more)

Block diffusion is the dominant approach for scaling discrete diffusion language models (dLLMs), as fixed-size blocks preserve parallel decoding while keeping quadratic attention costs tractable. Yet blockwise generation creates a structural weakness: tokens near a block boundary lack future cross-block context, and errors in finalized blocks become irreversible context for later generation. We call this the block boundary problem. Measuring predictions with and without later-block context shows that boundary sensitivity rises sharply: on AIME 2025, mean self-containedness divergence (SCD) in the last quarter of a block is 61.3 times that in the first quarter. We propose Multi-Block Editing (MBE), which revises decoded tokens using cross-block context. Training-Free MBE reopens a full-attention window over selected blocks without parameter updates. To address the mismatch between block-diffusion training and MBE inference, Multi-Block Edit SFT introduces bidirectional attention masks and progressively enlarges the editing span. We also extend SGLang with a multi-shape CUDA Graph pool and fine-grained KV-cache control for efficient variable-length editing. Experiments on LLaDA2.1-Mini across 12 benchmarks show broad, consistent gains. Training-Free MBE improves or matches standard decoding on every benchmark. Full MBE raises the 12-benchmark average from 61.45 to 64.24, with gains of up to 13.33 points on AIME 2025, while retaining 87.3–96.7% of standard-decoding end-to-end throughput across four datasets.
Read the full abstract

All authors Xingyu Mou, Zijin Huang, Tianze Zhang, Yuxin Ma, Lanning Wei, Zengfeng Huang, Da Zheng, Lun Du