# Research Papers — 2026-07 · bundle page 202 of 222 > Full-text markdown of papers #10051–10100 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/202 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/201.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/203.md) ### MedCalc-Pro: Solving Complex Medical Calculations with LLM Agents Authors: Siran Zhao, Ruihui Hou, Ziyue Huai, Chennuo Zhang, Tong Ruan Published: 2026-07-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.02879v1 Current benchmarks for evaluating large language models (LLMs) in medical calculation are largely based on simplified settings, where each patient case corresponds to a single calculator and the required tool is explicitly specified in the query. However, real clinical scenarios often require multiple calculators for joint evaluation, nested-scale calculation, and fuzzy queries that do not directly specify the target calculator. To this end, we propose a new medical calculation benchmark, MedCalc-Pro, which covers three progressively challenging task settings: single-calculator, multi-calculator, and nested-calculator calculation settings. MedCalc-Pro contains 2,268 real-world clinical cases, covering 77 medical calculators across 14 clinical departments. Meanwhile, to address the limited performance of existing frameworks and methods in complex clinical scenarios, we further propose a more generalizable agent framework that supports multi-tool selection and nested-tool calling, while suppressing parameter error propagation through structured validation and evidence review. We conduct systematic comparisons across open-source, closed-source, and medical-specialized LLMs, and the results show that our framework achieves the best performance across all three task settings. This work provides a new benchmark and method for evaluating and applying LLMs in challenging medical calculation scenarios. --- ### Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI Authors: Romain Gerard, Assmaa Zeghaider, Yan Guo Published: 2026-07-03 Categories: cs.SE, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.02873v1 Large language model agents driving security tool suites over the Model Context Protocol are increasingly common. Yet the factors that bound their capability remain poorly characterized: how much depends on the model versus the client that drives it, whether constraining the agent to the orchestrator's own tools helps, and where capability is limited by reasoning rather than by missing tools. Using HexStrikeAI, an open-source orchestrator that exposes 150+ tools, as a testbed, we follow a methodology that evaluates the system, diagnoses its failures, and applies targeted improvements. We run 86 picoCTF challenges across seven categories and three difficulty tiers, under three tool-access regimes and three model/client configurations (774 trials). We then apply corrections to existing tools, agent-behavior changes, and eleven new capability tools, and re-run the previously-unsuccessful trials. The diagnosis isolates the driving client as a first-order factor for a fixed model (a 2.1 * gap between two DeepSeek clients) and a monotonic difficulty gradient, with the largest gains in the mid tier. The overall solve rate rises from 55.4% to 72.0%, and every configuration improves significantly (paired McNemar p < 0.001, non-overlapping 95% confidence intervals). The residual failures are reasoning- or environment-bound rather than missing-tool. A 60-run stability sub-study finds single-run verdicts reproducible (17/20 unanimous). We discuss what the results imply for how such orchestrators should be evaluated, and we are explicit about the limits: the study uses a single benchmark, the fixes were tuned on the same challenges they were evaluated on, and the client effect is demonstrated for one model only, so its generality to other models remains a hypothesis. --- ### Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs Authors: Nan Fang, Yijun Wang, Hao Liao, Sikun Yang Published: 2026-07-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.02872v1 Dynamic knowledge graphs are ubiquitous in today's AI applications, as we represent molecular structures, social relationships, and language information using these graph models. As knowledge graphs evolve over time and are often noisy and incomplete, modeling their temporal and relational dependencies becomes crucial for downstream tasks. To address these challenges, this paper proposes PGRE (Poisson-Gamma Relational Evolution), a probabilistic model for modeling inter-relational dependencies in dynamic knowledge graphs. PGRE represents multi-relational temporal links via a Poisson-Bernoulli formulation. It introduces Gamma-distributed latent variables to capture entity-factor associations and cross-relation dependencies mediated by shared latent communities. A Gamma Markov process further models the temporal evolution of these latent variables, enabling principled characterization of relational dynamics. Experiments on benchmark datasets show that PGRE achieves competitive performance in link prediction, particularly in sparse settings, while revealing meaningful relational evolution patterns in dynamic knowledge graphs. --- ### Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models Authors: Anagha Radhakrishna Palandye, Rebecca Glick, Osheen Kaul Published: 2026-07-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.02869v1 Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving mathematical reasoning in language models. Yet most RLVR work rewards only the final answer (outcome-based rewards), leaving the impact of step-level process supervision (process rewards) underexplored especially for small models that lack the capacity to self-correct under sparse feedback. We systematically compare five reward conditions applied to Qwen2.5-0.5B fine-tuned with Group Relative Policy Optimization (GRPO) on GSM8K: a no-RL baseline, process-only, outcome-only, and three hybrid weightings ($λ\in \{0.9, 0.5, 0.1\}$ process weight). Process-only supervision achieves 63.73% test accuracy versus 53.75% for outcome-only, a nearly 10-percentage point gap while yielding reasoning traces with higher step validity and lower deviation from ground-truth chain length. Hybrid rewards generally correlate positively with process weight, with one notable anomaly: the low-process / high-outcome configuration ($λ=0.1$) underperforms pure outcome supervision, suggesting conflicting optimization signals. Error analysis using GPT-4o as a judge reveals distinct failure mode distributions: process models generate structurally inconsistent but arithmetically grounded traces, while outcome models produce concise but derivation-error-prone chains. Our results demonstrate that reward granularity is a first-order design decision for RLVR, with process-level supervision substantially improving both accuracy and trace fidelity in small language models. --- ### E-TraMamba: A New Paradigm for Efficient Long-Term 3D Feature Tracking with Event Cameras Authors: Juwei Shen, Yujie Wu, Changwen Chen Published: 2026-07-03 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2607.02866v1 Event-based 3D tracking enables low-latency and high-speed perception, while existing CNN- and Transformer-based trackers struggle to capture long-range spatiotemporal dependencies in sparse, noisy event streams, especially under real-time and efficiency constraints. To address these challenges, we present E-TraMamba, the first Mamba-based framework for 3D feature tracking on event data. This new framework adopts a linear state-space model for efficient long-range modeling and integrates a lightweight affine-transform predictor to maintain stable tracking under motion blur and occlusion. We also design an effective scheme to fuse multi-scale cues -- local spatiotemporal patches, correlation maps, and positional embeddings -- into a unified representation that enables stable and smooth 3D tracking. We construct a large-scale synthetic dataset, named EvD-PointOdyssey, which is generated with monocular rendering and provides synchronized event streams, depth maps, and accurate 3D trajectories for training and evaluating event-based 3D tracking models. Extensive experiments on event-based benchmarks demonstrate that E-TraMamba achieves state-of-the-art performance, delivering over $2\times$ longer feature lifetimes under strict accuracy thresholds (e.g., 0.1 m), with higher tracked-feature ratios and lower RMSE than all baselines. These results make E-TraMamba a strong candidate for low-latency visual odometry, real-time SLAM, and interactive robotics. --- ### Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading Authors: Lin Li, Li Rong Wang, Hsuan Fu, Xiuyi Fan Published: 2026-07-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.02864v1 Reinforcement Learning (RL) has emerged as a powerful approach in financial trading, enabling agents to learn optimal strategies through direct market interaction. However, financial markets are highly uncertain, with price fluctuations driven by stochastic volatility, model limitations, and regime shifts. Traditional RL models struggle in dynamic environments, often failing to adapt to sudden market disruptions, leading to suboptimal trading decisions. To address this challenge, we propose an uncertainty-aware RL framework that integrates distributional, epistemic, and aleatoric uncertainty estimations. Our approach enhances uncertainty estimation using SHAP-weighted reconstruction uncertainty, MC Dropout, and an LSTM-based technical indicator consensus mechanism. Experimental results on five major U.S. stock indices demonstrate that RL agents equipped with uncertainty estimation significantly outperform traditional models in return and risk management. This study advances uncertainty estimation in RL-based financial trading, with future research extending its application to other asset classes and alternative RL architectures for greater adaptability. --- ### Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion Authors: Saurabh Kumar, Amartyaveer, Prasanta Kumar Ghosh Published: 2026-07-03 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2607.02862v1 Automatic Speech Recognition (ASR) and Dialect Identification (DID) are crucial for Indian languages, many of which are low-resource and exhibit significant dialectal differences. Existing methods often optimize ASR or DID individually, resulting in performance trade-offs. In this work, we propose a multimodal framework that jointly improves ASR and DID. Our method employs a Bottleneck Encoder to extract dialectal features from Conformer-based speech representations and a RoBERTa encoder to process ASR-generated CTC embeddings. A gating mechanism merges these features, followed by an attention encoder to refine the representations. The learned embeddings are concatenated with Conformer outputs to enhance ASR features. Evaluated on eight Indian languages with thirty-three dialects, our method achieves an average DID accuracy of 81.63% and average CER and WER of 4.65% and 17.73%, respectively. These results highlight the effectiveness of our method for joint ASR-DID modeling. --- ### Cancelable Biometric Template Protection Based on Multi-Instance Fusion: A Contralateral Iris Approach Authors: Jittarin Chaivong, Nicha Vikromrotjananan, Teekatat Piriyapittaya, Waree Kongprawechnon, Suradej Duangpummet Published: 2026-07-03 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2607.02860v1 Biometric templates are vulnerable to theft if stored without protection. Unlike passwords, a compromised iris cannot be reissued. Although existing cancelable biometric schemes address this problem, most still require an external key or token, introducing an additional attack surface. This paper proposes a cancelable contralateral iris template protection scheme that eliminates the need for a separate token or stored secret, satisfying the three requirements of ISO/IEC 24745: irreversibility, unlinkability, and confidentiality. The method fuses three enrollment samples per eye using Majority Vote Fusion to produce a stable template, and applies a salt-based bit permutation derived from the subject's enrollment ID. Combining the left- and right-permuted templates via a bitwise XOR produces a single Protected Fused Template. Since left and right iris patterns are statistically independent, fusing contralateral irises improves the accuracy of the system. An attacker must possess both iris codes and both salts to recover any useful information, yielding a larger effective key space than single-iris schemes. Experiments on three datasets, CASIA-IrisV4-Interval, CASIA-IrisV2 (two devices), and CASIA-Iris-Thousand, yield EERs of $0.36$\%, $4.88$\%, $10.80$\%, and $3.35$\%, respectively; the highest value reflects the more challenging cross-device scenario. These results demonstrate that our contralateral approach outperforms unprotected baselines while remaining competitive with state-of-the-art cancelable methods. %In addition, an ablation study confirms the benefit on both recognition performance and security. To the best of our knowledge, this is the first scheme to combine tokenless multi-instance fusion and contralateral binding under ISO/IEC 24745. --- ### EvoOtter: Evolutionary Reproduction Test Generator Authors: Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin Hirzel Published: 2026-07-03 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2607.02854v1 Before fixing an issue, it is useful to first reproduce it by generating a bug reproduction test (BRT). However, generating a BRT is itself a challenging task, because issue descriptions tend to be informal, making it difficult to determine whether a candidate BRT indeed fails for the reason in the issue. Prior work has attempted to tackle this problem via inference scaling, using large language models to generate many BRTs and patches, then using execution feedback to select and improve them. Unfortunately, this is expensive and the feedback is unreliable. This paper explores evolutionary programming for BRT generation to sharpen the feedback, while enhancing evolutionary programming to keep costs in check. Our new approach, EvoOtter, controls test execution costs via successive halving. Furthermore, it controls LLM costs via batched crossover for an entire generation in a single LLM call, as well as via rule-based code mutations, with a new fitness score tailored for BRTs. As a result, EvoOtter generates state-of-the-art quality BRTs at the fraction of the cost of prior inference-scaling approaches to this problem. More broadly, this paper points at how to efficiently and effectively combine evolutionary programming with large language models for software engineering. --- ### Prior Bias in Vision Language Models on UML Diagram Interpretation Authors: Zaiyu Cheng, Khai-Nguyen Nguyen, Antonio Mastropaolo Published: 2026-07-03 Categories: cs.CV, cs.SE arXiv: https://arxiv.org/abs/2607.02853v1 Vision Language Models (VLMs) are increasingly applied to software engineering artifacts, especially UML class diagrams whose meaning depends on visual notation. Yet, it is unclear whether VLMs actually read such diagrams or instead answer from pretrained priors about how classes typically relate. We introduce a controlled UML benchmark in which each prior-conforming diagram is paired with its prior-conflicting counterpart that (1) preserves the same class names and layout while (2) reverses only the relation arrow. We evaluate eight open-source VLMs from two model families, InternVL3.5 and Qwen3, alongside two closed-source frontier models GPT-5.4 and GPT-5.4 Mini. Across the eight open-source models, reversing the arrow reduces relation-direction accuracy by 33.48% on average, while GPT-5.4 Mini retains a 10% gap. In the harder three-class condition, accuracy drops sharply by 45.28% for open-source models, and even 18.62% for the GPT-5.4 family on average. Scaling provides only limited improvements and is family-dependent. Our benchmark presents a diagnostic prior-driven failure in diagram-grounded software understanding. Our artifact is available at https://anonymous.4open.science/r/UMLKnowledgeConflict-8461. --- ### Labeled-Data-Free Meta-Learning: Efficient Task Generation Using Pre-trained Models and Unlabeled Data Authors: Lei Sun, Yusuke Tanaka, Tomoharu Iwata Published: 2026-07-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.02850v1 Meta-learning without labeled data is crucial for real-world applications, where obtaining labeled datasets can be expensive or restricted due to privacy concerns. Data-Free Meta-Learning (DFML) addresses this challenge by leveraging pre-trained models without access to training data. However, existing DFML methods rely on model inversion to generate training data, a process that is generally difficult and computationally expensive due to the need to generate high-dimensional data matching the original distribution. To address this limitation, we propose a novel meta-learning setting that avoids model inversion by jointly leveraging pre-trained models and unlabeled data. Our method generates meta-training tasks by assigning soft labels from pre-trained models to unlabeled data. Since the quality of these tasks can vary, we introduce a task-weighting mechanism based on task confidence and class distribution balance to ensure effective meta-learning. Extensive experiments demonstrate that our approach substantially reduces computational cost and improves generalization, achieving up to 104-fold speedup and 8.4 percent to 36.4 percent improvements in few-shot classification accuracy compared to state-of-the-art DFML methods. --- ### Object-Centric Environment Modeling for Agentic Tasks Authors: Yiyang Li, Tianyi Ma, Zehong Wang, Yijun Ma, Yanfang Ye Published: 2026-07-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.02846v1 Large language model (LLM) agents can improve through accumulated experience, but free-form textual memories become difficult to maintain, validate, and reuse as interactions grow. Recent symbolic approaches learn executable skills or programmatic world models, yet often store local procedures or assume simplified dynamics. We propose Object-Centric Environment Modeling (OCM), which organizes experience into an executable object-centric environment model. OCM maintains two connected code bases: object knowledge, which defines environment entities and mechanisms as Python classes, and procedure knowledge, which records reusable interaction patterns that must import and use the object model. OCM works in an online setting: after each episode, OCM reflects on the trajectory, updates both knowledge bases, and verifies that all procedures execute against the updated object model. During future interaction, the agent uses progressive knowledge disclosure to inspect compact code signatures first and read source code only when needed. Experiments show that OCM achieves the best average rank across benchmarks and reduces invalid actions, demonstrating that agents can benefit from building object-centric environment models. --- ### Differential Amplifier-Inspired AmpAttention for Multi-View Robotic Manipulation Authors: Jin Yang, Ping Wei, Nanning Zheng Published: 2026-07-03 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.02845v1 Multi-view robotic manipulation methods with the attention mechanism have recently achieved significant progress in both training efficiency and task performance. However, the inherent redundancy, occlusion, and viewpoint dependency in robotic view images often lead to severe attention drift. To address this challenge, we propose AmpAttention, a novel attention mechanism inspired by differential amplifiers in analog circuits. It aims to suppress attention noise and capture high signal-to-noise ratio signals for more reliable perception. Based on this, we introduce the RVAF model, which integrates task-guided intra-view and inter-view AmpAttention. Compared to previous state-of-the-art methods, RVAF achieves the optimal average success rate across 18 RLBench tasks (249 variations) while reducing training time by 33.3\%. RVAF also demonstrates strong potential in real-world high-precision tasks, exemplified by its ability to pick up a dart and accurately insert it into the red bullseye. Furthermore, we extend RVAF to RVAF++ by incorporating the SAM2 image encoder. RVAF++ achieves substantial gains on high-precision tasks, achieving a 91\% success rate on the `insert peg' task. More qualitative results are provided at the anonymous project website https://anonymous.4open.science/w/RVAF-Anonymization. --- ### CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving Authors: Yunxiao Shi, Hong Cai, Mohammad Ghavamzadeh, Fatih Porikli Published: 2026-07-03 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2607.02841v1 End-to-end autonomous driving (E2E-AD) aims to directly map raw sensor information to driving actions. Recently, with the rapid advancement of multi-modal large language models (MLLMs), researchers have proposed the paradigm of Vision-Language-Action (VLA) models for E2E-AD, where it seeks to integrate visual perception, language understanding and action prediction within a single policy. However, existing VLA-based policies largely adopts imitation learning, where it only learns to drive by optimizing distance-based metrics w.r.t. logged expert trajectories. Such distribution shift between open-loop training and closed-loop inference leads to suboptimal performance in closed-loop planning. To close this gap, we present CLEAR, a system that enables closed-loop training using Reinforcement Learning (RL) at scale for E2E-AD. We propose to learn a novel residual waypoint policy around the waypoint prior from pretrained VLA policies, effectively harnessing the knowledge within. On another front, one of the key challenges to scale up RL for vision-based policies is the number of parallel simulation environments since RL is data hungry. To that end, we design a heterogeneous pipeline that places the simulator and the VLA learner on distinct compute groups, which allows us to dramatically increase the number of simulation environments running in parallel while avoiding resource contention and maintaining training stability. We show that with a simple reward, CLEAR significantly outperforms previous methods and sets new state-of-the-art performance on the challenging benchmarks of CARLA longest6 v2 and Bench2Drive. --- ### On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization Authors: Trevor Chen, Ariel Dai, Jason Yang, Riccardo De Santi, Daniel Khalil, Wenda Chu, Nate Gruver, Pranav Murugan, Alexander F. G. Goldberg, Maruan Al-Shedivat, Yisong Yue Published: 2026-07-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.02834v1 Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures. At test time, however, the goal is not to sample from this prior, but to use a limited oracle budget to shift generation toward task-specific high-reward molecules. We study this adaptation problem for discrete diffusion models. Each online round couples several choices. The loop must decide which candidates to evaluate, how rewards become model updates, which feedback to reuse, and how far to move beyond the pretrained prior. These choices have mostly been studied in isolation, leaving open whether they complement one another, become redundant, or interfere inside a full online adaptation loop. We conduct controlled studies across six small-molecule binding-affinity tasks and three protein-fitness tasks. We find that acquisition, reward shaping, and model debiasing provide complementary routes to higher reward, especially for small molecules. Replay further stabilizes learning, while validity penalties keep small-molecule exploration on the valid molecular manifold. Together, these findings point to a practical recipe for feedback-efficient molecular optimization: online fine-tuning with acquisition, reward shaping, debiasing, replay, and validity control. This recipe outperforms offline fine-tuning and inference-time search baselines under matched oracle-call budgets and GPU-hour accounting. The gains are largest when high-reward candidates require larger shifts from the pretrained prior. --- ### The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speech Authors: Antonis Asonitis, Juan Pablo Zuluaga Gomez, Francesco Verdini, Aref Farhadipour, Marzieh Razavi, Pierre-Edouard Honnet, Vijeta Avijeet Published: 2026-07-02 Categories: cs.SD, cs.CL, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2609.13150v1 Reference-free quality predictors such as UTMOS, DNSMOS and SCOREQ are the de facto automatic evaluators for text-to-speech (TTS) and are increasingly adopted as reward signals for preference optimization. Both roles presuppose that the predicted score tracks human preference. In this work, we test this assumption across six human-rated corpora spanning the quality range from artifact-rich to defect-free TTS, evaluating each predictor on a pairwise task that asks whether the clip it scores higher is the clip listeners prefer, and we subject interpretable prosodic and signal-processing features to the same protocol. When one clip carries audible defects the predictors tend to agree with listeners. Once both clips are clean, no single predictor reliably identifies the preferred sample, and several fall below the accuracy of simply picking the longest-duration clip. A calibrated composite of complementary signals is the strongest evaluator we test, though on the cleanest audio it recovers only part of the gap to the human ceiling. Additionally, using even an equal-weighted ensemble of metrics helps as a post-training reward, where no calibration data is available. Optimizing a single score with policy optimization induces reward hacking, driving the metric toward its optimum while independent held-out judges and a human listening test deteriorate. The composite reward resists this behavior and tends to improve the model. Our contribution is the evaluation protocol, the predictor scores across these corpora, and the diagnosis of when and why single scores fail. --- ### One Simple Trick for Improving the Performance of Energy-Limited Local Inference and Training Authors: Erik Schultheis, Maximilian Kleinegger, Dan Alistarh Published: 2026-07-02 Categories: cs.PF, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.11936v1 Energy supply and heat dissipation are two of the main challenges with modern GPU deployments. While typically discussed in the context of new datacenter constructions, the same constraints also apply to small form-factor consumer devices, such as the DGX spark. In workloads characterized by alternating compute-intensive tasks such as matmuls with memory-bound operations such as norms or cross-entropy, the compute-intensive parts might hit power and/or thermal limits and start throttling. In this short paper, we show that chunking the workload into smaller parts that alternate compute and memory in higher frequencies, these power and temperature spikes can be smoothed out, preventing throttling and resulting in considerably faster wall-clock time and reduced total energy consumption. We present several scenarios in which this effect can be exploited on a DGX Spark with up to 2% performance and energy improvements, and demonstrate that the same phenomenon also happens on less constrained systems, such as a multi-GPU server, albeit at significantly reduced effect size of 1-2%. --- ### BharatGather: A Culturally-Informed Benchmark Dataset for Misinformation and Fake News Detection in Indian Public Events Authors: Parth Bramhecha, Smit Deshmukh, Sairaj Bodhale, Adwait Borate, Raviraj Joshi Published: 2026-07-02 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.02895v1 Large-scale public events, such as religious festivals, political rallies, and cultural gatherings, are increasingly vulnerable to the rapid dissemination of misinformation, posing substantial risks to public safety and social cohesion. While automated fake news detection has seen significant methodological progress, existing benchmarks frequently fail to capture the socio-cultural nuances and event-specific dynamics characteristic of the Indian context. This paper introduces BharatGather, a curated, multi-source dataset specifically engineered for binary misinformation classification within the ecosystem of Indian mass gatherings. The corpus comprises 14,646 records constructed through a hybrid pipeline involving systematic web scraping of prominent fact-checking platforms, multimedia transcript extraction, and Large Language Model (LLM)-mediated synthetic augmentation to ensure narrative diversity. By providing a resource tailored to the unique complexities of event-aware misinformation in India, this work facilitates the development of culturally informed detection systems and establishes a rigorous benchmark for evaluating their performance in high-stakes public environments. --- ### Environmental Slow AI: Design Principles for Generative Systems Authors: Vanessa Utz Published: 2026-07-02 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.20398v1 Generative AI (genAI) systems produce cultural artefacts at scale, but they also reflect embedded cultural values through their design. Once identified, these values become open to deliberate reshaping. This position paper examines the maximalist values of current generative AI through an environmental humanities tradition and proposes design principles in which environmental sustainability serves as the core value instead. The principles are developed under the umbrella of Slow AI, a term that already circulates across several distinct research and practice programs. Five design principles are articulated (restraint, sufficiency, selectivity over retention, material visibility, and friction as affordance), each of them illustrated against the current design of widely deployed systems. Each principle operates at two levels: a design implementation, and an interpretive layer at which users and developers are prompted toward reflective engagement with the system. Together these principles extend human agency by restoring decisions that frictionless defaults have silently removed and do so by building interpretive reflection into design. --- ### Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems Authors: Heming Fu, Shan Lin, Qianqian Xie, Guojun Xiong Published: 2026-07-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.13571v1 When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overhead creates a gap between what a model's per-token price implies and what a full workflow actually costs. We call this gap \emph{token inflation} and define it as the ratio of true workflow cost to single-call cost. Systems like FrugalGPT route based on the latter, which can underestimate real cost by more than $2\times$ on difficult tasks. We address this with InflationAgent, a four-stage router that (1) measures token inflation systematically across model tiers and task types, finding inflation as high as $4.25\times$ for a 7B model on multi-hop question answering; (2) introduces CoT Branching Entropy (CBE), a pre-execution difficulty signal computed entirely from local inference, which predicts high inflation with AUROC 0.887; and (3) selects models by maximizing a Semantic Exchange Rate (SER) that divides expected accuracy by predicted true cost, with a fresh-escalation policy that discards failed chains before routing to a stronger model. On GSM8K under a fixed budget, InflationAgent achieves 94.7\% accuracy versus 91.0\% for FrugalGPT while using 31\% fewer tokens, and we show that forwarding a failed reasoning chain to GPT-4o reduces its accuracy by up to 34.8 percentage points, validating the fresh-escalation design. --- ### Assessment Design in the GenAI Era: The X1-X2-X3 Assessment Pattern for Testing Students' AI Literacy, Learning Outcomes, and Reflection Authors: Riasat Islam, Thomas Roelleke Published: 2026-07-02 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.12351v1 Generative artificial intelligence (GenAI) has challenged the validity of unsupervised online assessment, especially in technical subjects where plausible answers can be produced with little effort. This paper reports lessons from designing and implementing an AI-aware, AI-testing assessment in a large second-year undergraduate database systems module. The design combined two linked elements: (1) a structured three-part response format (X1-X2-X3) in which students documented a sourced answer, produced their own answer, and evaluated the sourced output; and (2) an AI-aware question-design process in which draft tasks were stress-tested against contemporary GenAI tools and revised when generic prompting produced superficially adequate answers. The account draws on archived assessment materials, rubrics, planning records, design-time GenAI trials, practice-response data, attainment records, and external review comments. Its main contribution is a reusable assessment-design method rather than a claim of measured learning gains. We show how the pattern developed across iterations and how it can support authentic assessment, visible AI literacy, student judgement, and more transparent marking. The paper offers practical guidance for lecturers adapting assessment to routine GenAI use, focusing on testing AI literacy rather than penalising students for misconduct. --- ### From Caveman to Expert Analyst: Energy Consumption of Variable LLM Tasks Authors: Diego Manya, Ethan I. Thorpe, Ji Zhang, Myranda Shirk, Jiamian He, Angel Hsu, Michael P. Vandenbergh Published: 2026-07-02 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.12350v1 The energy demand growth and environmental impacts of artificial intelligence (AI) have generated substantial interest in supplying sufficient low-cost electricity for AI-driven data center development. Research on the ability of demand-side management to address these challenges has been more limited. Shifting the amount or timing of demand from retail, corporate, and other organizational behaviors is a plausible option but only if changes in demand-related behavior have important effects on the envi- ronmental and electricity effects of AI. This article tests four retail (i.e., consumer) user behaviors with high behavioral plasticity to assess their technical abatement potential. The research concludes that non- reasoning models provide sufficient quality while consuming close to one-twentieth of energy compared to reasoning models, saving an amount equal to the annual electricity requirement of at least 141,000 US households under daily usage assumptions. Simple prompt modifications can yield additional reduc- tions in energy consumption by up to 65% using non-reasoning models. Specifically, the practice that maintains the highest degree of similarity with the baseline reduces electricity demand in the range of 4 to 35%, an amount equal to the annual electricity requirement of up to 7,200 US households. Although AI advancements make precise estimates of environmental and electricity impacts difficult to assess, the results confirm that certain minimally intrusive best practices aimed at the majority of users can reduce the energy and environmental burdens imposed by AI. --- ### Representation Matters in Longitudinal Affective Computing Authors: Igor Matias, Maximilian Haas, Eric J. Daza, Matthias Kliegel, Katarzyna Wac Published: 2026-07-02 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.07518v1 Longitudinal, in-the-wild, wearable sensing yields day-level physiology, sleep, activity, and environmental streams, whereas affect and cognition are labeled only episodically (per waves). We recast this cadence mismatch as a temporal representation problem and compare three wave-level mappings from dense histories to sparse labels: levels (within-wave summaries), absolute drift (change across waves), and proportional drift. Using almost a year of data from 82 adults in the Providemus alz study, we model 21 affect and cognition outcomes. Day-scale signals are reduced to compact wave-level descriptors (central tendency, dispersion, and distributional shape) and learned with four regressors under two orthogonal evaluation axes: leave-one-subject-out and leave-one-wave-out. Performance is reported as scaled MAE using both mean and median across folds. Differences emerge: affective states are best predicted by wave-to-wave absolute drift, whereas cognitive performance aligns with within-wave levels, reflecting emotion dynamic theories. Across windowing features, shape descriptors (e.g., minima, kurtosis) carry more signal than simple means/medians. We contribute a representation triad for sparse-label modelling, a wave-level feature schema applicable on-device, and a dual-axis reporting practice that separates cross-participant generalization from temporal robustness. These results convert temporal representation from an implicit preprocessing step into an explicit, testable design choice for real-world affective-computing applications in brain health. --- ### The Judge Knows When It Knows: Calibrated Abstention for LLM-Based A/B-Test Prediction Authors: Tyler Dooskin, Squoosh Technical Staff Published: 2026-07-02 Categories: cs.HC, cs.CL, stat.AP arXiv: https://arxiv.org/abs/2608.07517v1 Can a multimodal LLM predict which version of a web page will win a real A/B test from screenshots alone? We report the most complete answer we are aware of, from six weeks of pre-registered experiments on real conversion tests: mostly no -- and the exceptions are identifiable in advance. On 330 real A/B tests a Gemini 3 Flash judge reaches Cohen's kappa = 0.14, but on the trustworthy (statistically significant) half of the labels the evidence is inconclusive (kappa = 0.11, CI includes zero). We show that 44% of the "ground-truth" labels in a leading CRO agency's catalog come from non-significant tests, and that the judge agrees more with the unreliable labels than the reliable ones -- a shared prior between labeler and model, not prediction. Every standard improvement lever (a 2.8x more expensive frontier model, prompt redesign, stimulus fidelity, change-type priors) fails its pre-registered gate. The judge's confident calls are different: a vote-margin gate isolates a subset (49% coverage) reaching kappa = 0.31 on significant labels. We measure the mechanism directly -- judges differing in model or prompt agree with each other at kappa = 0.74-0.88 while agreeing with real outcomes at only ~0.2, so a 16-vote panel carries about 2 effective independent votes -- and we reproduce it in humans: 15 CRO experts agree with each other (inter-rater kappa = 0.53) but score at chance against real outcomes (kappa ~ 0). Consensus, human or model, is reproducible, persuasive, and not evidence. We release our pre-registrations, locked gates, negative results, statistical harness, human responses, and a claims ledger in which every number carries an evidence tier. --- ### Reading Without a Reader: Large Language Models Collapse Reading and Writing into a Single Entangled Code Authors: Diego Saldaña Ulloa Published: 2026-07-02 Categories: q-bio.NC, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.24797v2 In the literate human brain, reading and writing doubly dissociate: a ventral decoding route (pure alexia) and a fronto-parietal encoding route (pure agraphia), sharing a partial orthographic core. A decoder-only large language model (LLM) drives both from one autoregressive path optimized on text (a \emph{cultural} invention, not an evolved instinct). We ask how entangled it is, comparing an input-side ``reading code'' $\mathbf{W}_{E}$ with an output-side ``writing code'' $\mathbf{W}_{U}$ via an index $\mathcal{E}\in(0,1)$ (CKA, Procrustes residual, mutual $k$-NN) calibrated against an independent-init floor and tied ceiling. On GPT-2, OPT and Pythia (14M--1.4B), untied models hold one \emph{coupled but sub-ceiling} code ($\mathcal{E}=0.23$--$0.35$, far above floor) on a non-monotonic couple-then-differentiate trajectory, $\mathbf{W}_{U}$ drifting $\sim$3.2$\times$ farther than $\mathbf{W}_{E}$ in every decile. Equally informative is a negative: the matching behavioural test, that comprehension and production fail together rather than dissociate, cannot be run. For minimal pairs the alexia analogue is empty by theorem: greedy production implies a vocabulary-wide argmax, so it wins the pairwise ranking. Differential-damage indices are not scale-identified: heavy-tailed damage makes linear standardizations collapse onto their larger term, and the rank transform fixing this is bounded, so its null saturates. Both scores also contain the target's log-probability, which alone explains most of their variance and manufactures the apparent coupling. We withdraw a coupling statistic, a cross-level bridge and a separation measure. In a model reading and writing off one next-token distribution, no output-side pair isolates either ability: entanglement needing no index to see. By analogy, not homology, this situates LLMs in the space of possible minds. --- ### Optimizing Hypergraph-Based RAG: Toward Better Fact Extraction and Chunk Retrieval Authors: Houda Khrouf, Pedro Fillastre, Sebastiao Correia Published: 2026-07-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20506v1 GraphRAG enables deeper reasoning by structuring knowledge as graphs but struggles with n-ary facts. HyperGraphRAG uses hypergraphs for richer semantics, improving accuracy, yet relies on error-prone LLM extraction and inefficient standard chunk retrieval. We address this by employing self-consistency prompting to improve the extraction, and Personalized PageRank algorithm over hypergraph to enhance chunk retrieval. --- ### HERMES: Heterogeneous Edge-Relational Multi-Head Embedded SSM Attention for Traffic Conflict Prediction at Signalized Intersections Authors: Md Monzurul Islam, Subasish Das Published: 2026-07-02 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2607.20505v1 Surrogate safety measures (SSMs) enable proactive traffic safety assessment, but many existing methods evaluate pairwise interactions independently or flatten multi-agent scenes into fixed feature vectors, limiting their ability to represent heterogeneous interaction structure and evolving scene-level risk. This study formulates traffic conflict assessment as temporal heterogeneous scene-graph classification and proposes HERMES, a heterogeneous edge-relational graph neural network with SSM-informed multi-head attention. Vehicles and pedestrians are represented as heterogeneous nodes, while vehicle-vehicle, vehicle-pedestrian, and pedestrian-pedestrian interactions are encoded as relation-specific edges with continuous kinematic and surrogate-safety descriptors. Relation-specific attention, dynamic node-edge updates, safety-aware graph pooling, and temporal sequence learning are jointly used to estimate scene-level conflict probability. HERMES was evaluated using 109,028 trajectory-derived sequences from a signalized urban intersection and tested on an independently collected comparable intersection dataset. Enhanced HERMES achieved an AUC-ROC of 0.9898 +/- 0.0013, an AUC-PR of 0.9412 +/- 0.0067, and an F1 score of 0.8449 +/- 0.0103. At a 5% false-alarm rate, it detected 95.7% of conflict sequences, outperforming the strongest Transformer baseline and XGBoost. In zero-shot external evaluation, HERMES achieved an AUC-ROC of 0.9752 and an AUC-PR of 0.7829. Joint source-target training further improved target-site performance with limited target-site data. These findings show that preserving heterogeneous interaction topology, safety-informed edge semantics, and short-term temporal evolution improves scene-level conflict classification and supports transferable roadside safety monitoring at signalized intersections. --- ### Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks Authors: Vishnu Bindu Balachandran Published: 2026-07-02 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2607.19393v1 While auditing a perturbation-based OOD detector on a document benchmark, we recorded an AUROC of 0.326 -- well below the 0.5 chance level. The cause is a benchmark leak: the designated "OOD" class is one the model was trained on, so its examples sit inside the in-distribution fit set and the detector is penalized for correctly ranking them as familiar. Deleting the class and retraining 35 models across two domains raises the score to 0.911. We distill the contamination into a leak fingerprint -- near-perfect supervised decodability (AUROC approximately 1) coupled with unsupervised detection collapsed below 0.65 -- and validate it on a controlled battery of 52 settings (20 leaked, 32 clean) across ResNet-50 and ViT-B/16 on CIFAR-10/100, achieving sensitivity 18/20 and specificity 31/32 in embedding space; the matched fit-set-exclusion controls are perfect at 20/20. An in-the-wild audit of 24 standard near/far OOD benchmark pairs fires on exactly one (the intrinsically hard CIFAR-100 vs CIFAR-10 pair) and on no far-OOD pair, confirming specificity and that standard cross-dataset construction is clean. Under the corrected protocol, perturbation signals are decodable but not detectable: a supervised reader recovers the OOD signal (AUROC 0.87-1.00) while no unsupervised detector does, and the perturbation method does not improve on plain Mahalanobis distance. We provide a theoretical account of why and, for transparency, retract an earlier circular correlation. The contributions are a corrected protocol and a validated leak diagnostic, not a new OOD method. --- ### Predicting Groundwater Arsenic Concentrations Using Graph Neural Networks Authors: William Xing, Stephanie Yang, Aarush Bandemegal, Anushree Misra, Ananya Kalapatapu, Brennan Lagasse, Kevin Zhu Published: 2026-07-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.19392v1 Arsenic contamination in groundwater presents a longstanding public health crisis in the United States, especially for households depending on private wells. Accurate and spatially informed prediction of arsenic concentration is vital to identify high-risk areas and focus mitigation efforts. However, there is a lack of generalizable models for representing continuous variation in arsenic concentrations across regions. In this work, we pose arsenic prediction as a regression task and construct a spatially integrated dataset to aggregate over 74,000 arsenic samples from the Water Quality Portal (WQP), Mineral Resources Data System (MRDS), and Gridded National Soil Survey Geographic Database (gNATSGO). Specifically, we use a variety of techniques including kNearest Neighbors (k-NN) and Geographic Information Systems (GIS) to join arsenic measurement points from across the United States by location. Building on this dataset, we evaluate a diverse suite of machine learning models, including tree-based ensemble approaches, multilayer perceptrons, and spatially aware graph neural networks (GNN). Our findings show that while gradient-boosted trees are still considered state-of-the-art in the field of tabular data, GNNs are able to further account for spatial dependence to match or outperform the results of gradient-boosted trees. These results demonstrate that graph-based and spatially informed learning can enhance environmental prediction and provide a foundation for improved groundwater risk mapping and monitoring. --- ### LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning Authors: Ashutosh Tripathi, Surya Deep Singh, Pranab Sahoo, Sriparna Saha Published: 2026-07-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.19391v1 Low-Rank Adaptation is widely used for parameter-efficient fine-tuning, yet existing methods typically assign the same adapter rank to every transformer layer despite their heterogeneous adaptation requirements. In this work, we show theoretically and empirically that uniform rank allocation is fundamentally suboptimal. Motivated by this observation, we propose LAARA (Layer Aware Adaptive Rank Allocation framework), a search-free framework that dynamically allocates ranks using lightweight diagonal Fisher estimates computed during training. LAARA combines projection-wise normalization, logarithmic compression, blended adapter importance estimation, and a vote-to-change dampening mechanism to produce stable and efficient rank adaptation. Experiments on GLUE and MathInstruct benchmark demonstrate that LAARA consistently matches or outperforms popular state of the art approaches such as LoRA, AdaLoRA, DyLoRA, and Bitfit while using significantly fewer trainable parameters. Our results show that Fisher-guided rank allocation provides a principled and effective foundation for adaptive parameter-efficient fine-tuning. The code is publicly available at: https://anonymous.4open.science/r/LAARA-D305/LAARA.py --- ### The Orthogonalized Read Is a Removable Training Scaffold for Recurrent Memory Authors: Keston Aquino-Michaels Published: 2026-07-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.19390v3 Orthogonalizing the mLSTM memory matrix at read time with five differentiable Newton-Schulz iterations improves noisy associative recall. We replicate this effect and investigate its mechanism. Training on MAD noisy recall exhibits a long chance-level plateau followed by a sharp increase in accuracy. The orthogonalized read improves conditioning during this plateau and can be removed after escape. Ablations support three findings. First, the benefit requires a self-consistent read and gradient: an exact recursive least-squares read (the Mesa layer) yields a similar benefit, while straight-through variants, delta-rule writes, frozen random keys, and Frobenius normalization show no improvement over baseline. Second, across a learning-rate x task-difficulty grid, orthogonalization multiplies escape hazard roughly six-fold, with no detectable dependence on difficulty, and widens the range of learning rates that produce successful runs. Third, adding orthogonalization at inference leaves chance-level failures unresolved, while removing it gradually after escape yields standard mLSTMs at near-perfect accuracy. Schedule changes alone recover much of the reported gain. A batch-size x learning-rate analysis separates the effects of per-step learning rate and gradient noise on escape hazard (elasticities +3.0 and -1.65, respectively), linking the original vocab-96 result to its large-batch training regime. Direct decoding of the memory state recovers roughly half of the associations in behaviorally failed models, indicating a readout-learning limitation despite substantial stored information. These results show that fixed-budget recall benchmarks are sensitive to trainability and provide a tractable setting for investigating abrupt behavioral transitions through measurements of internal representations. --- ### The Orthogonalized Read Is a Removable Training Scaffold for Recurrent Memory Authors: Keston Aquino-Michaels Published: 2026-07-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.19390v2 A recent report finds that orthogonalizing the mLSTM memory matrix at read time (five Newton-Schulz iterations, trained through) substantially improves noisy associative recall. The effect replicates, but it is not a memory improvement. Training on this task is a long chance plateau followed by a sharp escape, and the orthogonalized read acts by re-conditioning the learning problem during the plateau. Three properties establish this. It must be self-consistent: an exact recursive least-squares read (the Mesa layer) reproduces it, while straight-through halves, delta-rule writes, frozen random keys, and plain normalization all fail. It is uniform: across a learning-rate x hardness grid it multiplies the escape hazard roughly six-fold with no detectable hardness dependence, widening the workable learning-rate corridor that narrows for the baseline. And it is removable: applied to failed models at inference it rescues none, and annealed away on an escape-triggered schedule it leaves numerically stock mLSTMs at full accuracy. Much of the published gain needs no architecture at all: solved-rate at a fixed budget measures escape hazard, which follows a heat/noise law (learning-rate elasticity +3.0, gradient-noise elasticity -1.65) under which the original vocab-96 result is a large-batch noise condition rather than a capacity one. Decoding the memory state directly shows failed models carry roughly half their associations in linearly recoverable form: the plateau is a readout failure over half-written storage. Two conclusions travel beyond the intervention: recall benchmarks used for architecture selection partly measure trainability, and the system is a fully instrumented model organism of "emergence," in which a sharp behavioral threshold demonstrably arises from a censored metric over gradually accumulating structure. --- ### Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics Authors: Vedant Palit, Udvas Das, Brahim Driss, Debabrota Basu Published: 2026-07-02 Categories: cs.CY, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.19389v2 As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have drawn significant attention. In this paper, we revisit the nuances of long-term fairness achievable by an ADM-- specifically, through the lens of a loan approver inducing a population-level wealth dynamics. The literature generally (a) considers passive environments, i.e. the decisions of an ADM does not change the population's behaviour, and (b) measures bias in terms of disparity in the instantaneous decisions rather than downstream equity. Modern ADMs challenge both the notions. To address these caveats, we first formalise the wealth dynamics induced by a loan approving ADM interacting with a multi-demographic population as a Performative Markov Decision Process. Then, we mitigate the absence of such a performative test-bed by developing Eutopia: a lending-process simulator enabled with a novel performative data generator to learn long-term fair strategies. With Eutopia, we test reinforcement learning algorithms with different fairness-aware utilities dependent on approval decisions and downstream wealth. Results show that performative dynamics-aware learning with fairness-aware utility that incorporates the downstream outcomes induce better long-term equity and inclusivity. --- ### Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics Authors: Vedant Palit, Udvas Das, Brahim Driss, Debabrota Basu Published: 2026-07-02 Categories: cs.CY, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.19389v1 As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have drawn attention. In this paper, we revisit the nuances of long-term `fairness' achievable by an ADM, specifically in the context of a credit lending induced wealth process. The literature on long-term fairness mostly (a) considers passive environments, i.e. the outcome of a predictor does not change the population's behaviour, and (b) measures bias in terms of disparity in instantaneous predictions rather than the downstream equity. These are not true for modern ADMs, like credit lenders. To address these caveats, we first formalise the wealth dynamics induced by a loan approving ADM interacting with a multi-demographic population as a performative Markov Decision Process with ADM level and social outcome level reward functions. Then, we mitigate the absence of such a performative test-bed by developing Eutopia: a lending-process simulator enabled with a novel performative data generator to learn long-term fair strategies. Finally, we test performative and classical RL algorithms with different fairness-aware and utilitarian utilities. Experimental results show that (a) learning with performative dynamics lead to better long-term efficiency and equity, and (b) learning with well-designed fairness-aware utility evaluated on social outcomes induces better efficiency, equity, and inclusivity. --- ### Neural Operator Surrogates for Two-Dimensional Neutron Flux Estimation Authors: Japan K. Patel, Barry D. Ganapol, Anthony Magliari, Matthew C. Schmidt, Todd A. Wareing Published: 2026-07-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.19388v2 This work extends our one-dimensional single-sweep neural-operator studies to two dimensions. We consider one-group transport with isotropic scattering. As in the one-dimensional work, we use Fourier neural operators (FNOs) to approximate the high-fidelity scalar flux. Additionally, we also investigate U-shaped neural operators (UNOs) in this study. We consider three surrogates. The first two map the material and source fields directly to the flux, one using an FNO and one using a UNO. The third is an FNO that additionally takes the scalar flux after one source iteration, the single-sweep approximation, as an input. Each case is solved to high fidelity with a verified discrete-ordinates solver, and an average relative L_2 error norm is used to characterize the quality of the inferred maps. We train every surrogate over three random seeds so that differences between them can be assessed against run-to-run variability. Two questions guide the study: whether the single-sweep input improves accuracy over the direct maps, and whether training on the logarithm of the flux improves accuracy in the strongly attenuated regions relevant to shielding. --- ### Scale-Aware Learning of Chaotic Dynamics on Unstructured Meshes via Binned Spectral Losses Authors: Kanad Sen, Romit Maulik Published: 2026-07-02 Categories: cs.LG, cs.AI, physics.comp-ph, physics.flu-dyn arXiv: https://arxiv.org/abs/2607.19387v1 Surrogate modeling for high-dimensional nonlinear dynamical systems that exhibit chaos requires mechanisms that preserve not only pointwise accuracy but also the scale-dependent structure of physical fields. Bandwise spectral power losses, such as the binned spectral loss function, provide such supervision on structured grids, where Fourier modes define a standard frequency decomposition. On irregular meshes, however, no canonical Fourier basis exists, and spectral representations must be constructed from graph operators induced by mesh connectivity and geometry. In this study, we extend the binned spectral power loss for application to unstructured-mesh surrogate modeling of nonlinear dynamical systems. This is obtained by replacing Fourier bands with graph-Laplacian frequency bands, and we provide scalable Chebyshev and multilevel approximations for improving long-horizon rollout fidelity. In its full-spectrum form, our approach uses graph Laplacian eigenspaces to provide a graph analogue of Fourier band-power matching, but incurs the high cost of spectral decomposition. As a scalable approximation, we replace exact band projectors with sparse Chebyshev polynomial graph filters, avoiding explicit eigendecomposition. When utilizing multilevel graph architectures, we introduce Graph Laplacian Energy Alignment for Meshes (GLEAM), which applies retained-subspace scale-aware supervision across graph hierarchies so that coarse and fine representations are regularized during autoregressive rollout. Our results show that the proposed spectral losses improve long-horizon rollout fidelity and preserve statistical invariants for the forecasting of turbulent flows on unstructured meshes, compared to deterministic baselines. --- ### Deep Reinforcement Learning to Master the Asymmetric Strategy of Baghchal Authors: Ranjit Raut, Aarav Subedi, Sagun Rai, Aaryan Shakya, Manoj Shakya Published: 2026-07-02 Categories: cs.AI, cs.GT arXiv: https://arxiv.org/abs/2607.18296v1 Baghchal is a two-player asymmetric board game with Nepali origins where four tigers are to capture goats and twenty goats desire to keep tigers in immobility. Although Baghchal has a complex structure which is strategic, has perfect information structure, and has cultural meaning, it has not been adequately covered in deep reinforcement learning (RL) literature. This paper gives a systematic exploration of four deep RL solutions Deep Q-Network (DQN), REINFORCE, Proximal Policy Optimization (PPO) and MuZero that are trained on one side of the asymmetric gameplay of Baghchal and then evaluated on the other side. The algorithms are rated based on win rate, draw rate, average captures, training convergence and computational cost. It is experimentally found that MuZero generates the best performance in both tasks, achieving 86 percent win over these Tiger and 62 percent win over these Goat and the ability to do so is due to the model-based planning machine through the Monte Carlo Tree Search. PPO is the most realistic algorithm and is provided to be competitive over both asymmetric tasks with significantly reduced computational costs compared to MuZero. Emergent strategic behavior analysis shows that model-based strategies are optimal over long-horizon planning, whereas value-based counterparts like DQN are more biased up towards the Tiger role owing to the more substantial reward signal. --- ### Data-driven Video Codec with Implicit Neural Representations Authors: Nishan Khanal, Saugat Neupane, Abhinav Chalise, Nimesh Gopal Pradhan, Dinesh Baniya Kshatri Published: 2026-07-02 Categories: eess.IV, cs.AI, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2607.15298v1 A conventional codec stores a video as compressed pixel data. We instead store the video, together with its audio track, as the weights of a single sinusoidal representation network (SIREN) that maps space-time coordinates to RGB values and audio amplitudes. The network uses separate audio and video initialization layers, a stack of shared fully connected hidden layers, and three output branches: one for video and two Siamese audio branches whose disagreement is used to estimate and subtract residual noise. The overfitted teacher network is then compressed by response-based knowledge distillation into a smaller student, followed by 16-bit symmetric weight quantization and lossless LZMA2 (xz) encoding. On a 6.08 MiB test video, the quantized student reaches a video PSNR of 28.72 dB with SSIM of 0.75, and an audio PSNR of 24.18 dB with a log spectral distance of 10.69 dB, while the pipeline shrinks the representation from 9.05 MiB to 2.33 MiB, an overall compression ratio of 2.61. A bit-width sweep from 1-bit to 32-bit quantization shows that reconstruction quality saturates at 16 bits. We compare against H.264, HEVC, and MP3, report where the approach falls short of them, and describe a browser-based prototype that trains, transfers, and decodes these models over WebRTC. --- ### A Dynamic Scene Interaction Reasoning Framework for Scene-level Lane-Change Intention and Trajectory Prediction of Multiple Interacting Vehicles Authors: Joshua Kofi Asamoah, Blessing Agyei Kyem, Eugene Denteh, Armstrong Aboah Published: 2026-07-02 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.09740v1 Safe motion planning in advanced driver-assistance systems and autonomous vehicles requires an accurate understanding of how the surrounding traffic scene is likely to evolve. However, many existing lane-change prediction methods remain centered on a single target vehicle, while multi-agent forecasting approaches often describe scene evolution only through future positions and provide limited explicit information about the maneuver associated with each vehicle. This study proposes a dynamic scene graph attention framework that predicts the lane-change intention and future trajectory of every relevant vehicle within a local traffic scene. The scene is represented as a time-varying interaction graph in which vehicles are modeled as nodes and their spatial and kinematic relationships are encoded through explicit edge features. Temporal graph-attention message passing captures evolving inter-vehicle dependencies and pre-maneuver cues, while an intention-guided decoder links each predicted maneuver to its corresponding future motion. A scene-level consistency objective further encourages compatible multi-vehicle futures. Experiments on the NGSIM I-80, NGSIM US-101, and highD datasets demonstrate consistent improvements over competing baselines. DSiGAT achieves intention prediction accuracies of 90.12% and 90.97% on NGSIM I-80 and US-101, respectively, and reduces trajectory RMSE by up to 52.94% relative to the strongest baseline. It also produces lower inter-agent collision rates and joint displacement errors, indicating more coherent scene-level predictions. Ablation, sensitivity, robustness, and qualitative analyses further validate the contribution of the proposed components and the effectiveness of the scene-focused formulation. --- ### Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks Authors: Jihan Yao, Gantavya Bhatt, Arnav Das, Peter Jin, Ke Bao, Qiaolin Yu, Khushi Bhardwaj, Chang Su, Jialei Wang, Yikai Zhu, Sugam Devare, Damon Mosk-Aoyama et al. Published: 2026-07-02 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.09739v1 We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the full benchmark suite. In evaluation-unsupervised benchmark coreset selection (our approach), the selection algorithm uses no model evaluation outcomes, and operates on a fine granularity by producing subsets of prompts over multiple benchmarks rather than producing a sub-collection of entire benchmarks. We use submodular subset selection, and we develop and evaluate many different submodular functions for this purpose, including determinantal point process (DPP) based approaches, submodular mutual information functions, and facility location-based functions. On a new large-scale suite of 35 heterogeneous benchmarks spanning five different capability categories, 18 frontier LLMs, and over 61K prompts, we find that the facility location (FL) function operating exclusively on inexpensive semantic prompt embeddings preserves LLM scores better than twelve separate score-based and diversity-based baselines, across a range of coreset budgets. Moreover, we show our proposed objective is not limited to the evaluation-unsupervised regime: in the setting where only a handful of whole benchmarks must be selected and a large amount of model scores are available, the same objective matches or outperforms state-of-the-art baselines on the MMLU and MTEB leaderboards, while being substantially cheaper to compute. Together, our results suggest that submodularity, in general, is a strong and reliable tool for benchmark compression. --- ### Q-Score: A Quantum-Native Scoring Function for Molecular Docking Authors: Kangyu Zheng, Yidong Zhou, Ruihao Li, Zixin Ding, Zhiding Liang, Shaohua Li Published: 2026-07-02 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2607.09737v1 Molecular docking predicts how a small molecule binds to a protein and is a key bottleneck in drug discovery. Classical scoring functions sum empirical pairwise contacts, blind to quantum-mechanical effects like orbital charge transfer that govern binding specificity. We introduce Q-Score, encoding GNN-predicted orbital donor-acceptor energies into a weighted graph and scoring binding by solving a maximum-weight vertex clique problem via Digitized-Counterdiabatic QAOA. Each interaction anchor maps to one qubit and compatibility constraints become edges. Across 11 protein targets, DC-QAOA recovers the exact optimum on 8 at 10 qubits. On 1000 AI-generated molecules, Q-Score is orthogonal to classical scoring with Spearman rho of 0.05, driven by orbital quality with rho of 0.90, and free of molecular-weight bias, enriching for strong orbital interactions at twice the random rate. DC-QAOA achieves a mean approximation ratio of 0.94 with 52 percent exact. Execution of 1000 circuits on IBM Eagle confirms 6-qubit solvability on NISQ hardware. --- ### Saturation-Aware Robust Trajectory Optimization for Reusable Launch Vehicles via Differentiable Physics Authors: Liwei Chen, Tong Qin Published: 2026-07-02 Categories: cs.RO, cs.LG, physics.app-ph arXiv: https://arxiv.org/abs/2607.09736v1 The high-angle-of-attack flip maneuver of reusable launch vehicles presents significant challenges for robust trajectory optimization due to the combined effects of highly nonlinear dynamics, aerodynamic uncertainties, and actuator saturation. This paper presents a differentiable physics framework for saturation-aware robust trajectory optimization. At its core, a Differentiable Particle Tube Control (DPTC) scheme is developed to optimize uncertainty evolution through an ensemble-based distribution shaping strategy. State uncertainty is represented by a Lagrangian particle ensemble, while hard actuator projection operators are embedded directly into the computational graph, enabling the joint optimization of the nominal feedforward trajectory and a time-varying feedback policy via end-to-end backpropagation. The proposed framework is evaluated against an automatic differentiation-based Successive Convexification (AD-SCvx) baseline combined with a conventional covariance steering feedback strategy. Six-degree-of-freedom Monte Carlo simulations demonstrate that, although the baseline achieves nominal fuel-optimal solutions, its unconstrained feedback formulation becomes susceptible to actuator saturation under aerodynamic disturbances, leading to degraded closed-loop robustness. In contrast, the proposed DPTC framework proactively performs a constraint-aware performance trade-off by relaxing spatial tracking to preserve critical control authority. These results demonstrate that integrating differentiable physics with ensemble-based optimization provides an effective and practical framework for robust guidance in highly constrained aerospace flight systems. --- ### Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction Authors: Janet Wang, Yunbei Zhang, Lin Zhao, Xi Xiao, Jihun Hamm, Xiao Wang Published: 2026-07-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.02829v1 Existing ViT-based weather forecasting models apply uniform computation across all spatial tokens, even though nearby atmospheric grid points often contain similar values and large regions evolve smoothly over time. This makes much of the intermediate per-token computation redundant. Standard token-efficiency methods, such as pruning or merging, reduce cost by removing or fusing tokens. However, weather forecasting is a spatiotemporal dense prediction problem in which a history of atmospheric states must be mapped to future values on the original latitude-longitude grid. Thus, every grid cell must retain a physically meaningful representation, especially under autoregressive rollout. We introduce Sparse-Reslim, a parameter-free plug-in routing module that makes sparse token processing compatible with this fixed-grid requirement. Sparse-Reslim routes only 25% of spatial tokens through the expensive middle transformer blocks and treats those blocks as residual updates: it computes the change produced for the routed tokens and scatters only this delta back to the full sequence. Unselected tokens keep their pre-routing representations exactly, so no grid cell is dropped or replaced by a mask token, and no fusion layer or additional parameters are introduced. Across ERA5 resolutions up to the operational 0.25\textdegree{} standard and two model families, a deterministic Transformer and a diffusion model, Sparse-Reslim improves forecast accuracy on every evaluated variable while substantially reducing cost: training is about 2.5x faster in the main settings and reaches 3.18x speedup at 0.25\textdegree{}, with over 2.2x lower peak memory. A controlled decomposition shows that the accuracy gain comes primarily from sparse routing itself, while random token selection provides an additional regularization benefit without selector overhead. --- ### JavaVulBench: A Java Vulnerability Benchmark with Realistic Splits, a Unified Multi-Backend Harness, and a Leakage-Aware Evaluation Mode Authors: Norbert Sandor Szolnoki, Gabor Antal Published: 2026-07-02 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.02825v1 We release \textsc{JavaVulBench}, a benchmark dataset and evaluation harness for Java vulnerability detection. The dataset contains $\sim$30{,}600 Java methods spanning 1{,}740 CVEs and 700+ projects, labelled at both method and line granularity, with per-CVE publication dates and five realistic split strategies: random, project-disjoint, temporal, deduplicated, and unseen CWE-family. The harness provides a single \texttt{LlmPrediction} schema across three backend families (encoder classifiers, local generative models served by Ollama, and API-served LLMs routed through OpenRouter) so that twelve reference detectors CodeBERT, GraphCodeBERT, UniXcoder, DeepSeek-Coder-1.3B, and eight API/open-weight LLMs (GPT-4o, GPT-4.1-mini, Claude Sonnet~4, DeepSeek-v3, DeepSeek-Coder-v2, Qwen-2.5-Coder-14B/7B, CodeLlama-13B) are evaluated under identical conditions from a single command. A pre-training contamination audit is shipped alongside every model so users can separate genuinely unseen test CVEs from potentially memorised ones. Data, code, and fine-tuned checkpoints are archived on Zenodo (31) and short demonstration video is available on YouTube (https://www.youtube.com/watch?v=nMTX\_hqkuoM) https://www.youtube.com/watch?v=nMTX_hqkuoM. --- ### Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models Authors: Zikai Zhang, Rui Hu, Olivera Kotevska, Jiahao Xu Published: 2026-07-02 Categories: cs.CR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.02819v1 Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers. In this process, intermediate vision tokens are transmitted from the edge to the cloud over a communication link, thereby exposing a new attack surface. We study vision token manipulation attack (VTM-Attack) under a black-box man-in-the-middle setting, where an adversary intercepts and manipulates a subset of transmitted vision tokens under a budget constraint. We propose four naïve attack strategies and an optimization-based token selection method. Experiments on 6 state-of-the-art LVLMs (3B-72B) across 4 benchmarks show that manipulating only 10\% of vision tokens can reduce accuracy by up to 88.31\%. These results reveal a critical vulnerability in cloud-edge LVLM inference. --- ### SovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional Pressure Authors: Dylan Zongmin Liu Published: 2026-07-02 Categories: cs.MA, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2607.02814v1 Personal agents will increasingly negotiate on behalf of users: splitting costs with other personal agents, appealing platform decisions, escalating support disputes, requesting refunds, changing subscriptions, and negotiating deadlines or reimbursements. Existing negotiation benchmarks emphasize agreement, surplus, or strategic competence, but a user-owned agent can reach an agreement while harming the user through privacy leakage, consent violation, unsupported advocacy, over-concession, failed escalation, or poor auditability. We introduce SovereignNegotiation-Bench, a trace-level multi-turn benchmark for delegated personal-agent negotiation under private utilities, disclosure constraints, evidence requirements, and institutional asymmetry. The benchmark separates agent-visible observable state from evaluator-only labels and evaluates agreement success jointly with user utility, privacy, consent, evidence grounding, concession discipline, escalation, and auditability. We report an artifact-backed validation over 240 scenarios, 4 model families, 14 baselines, 13,440 frozen-prompt live trajectories, 61,135 parsed action rows, and a blinded 3-annotator audit over 300 items. The strongest agreement-maximizing baseline achieves the highest agreement rate but low user utility and high privacy/consent risk; FullSovereign does not maximize agreement, but obtains the best sovereign negotiation score by preserving utility, minimizing leakage, grounding claims, and reducing unauthorized commitments. The results show that agreement success is insufficient for user-owned negotiation agents. --- ### SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery Authors: Yuvraj Virk, Zack Edds, Chunqiu Steven Xia, Lingming Zhang Published: 2026-07-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.02807v1 Long-running coding agents such as autoresearch can persistently discover optimizations for open-ended problems. However, they tend to converge onto a single high-level approach, then proceed with low-level edits while missing other superior approaches to the problem. We hypothesize two harness-level design choices contribute to this behavior: accumulating context in a single long-running agent and only exposing a single program state to edit. We introduce SwarmResearch, an orchestrator-subagent harness in which a Shepherd Agent uses global context to steer a population of Search Agents, each operating with local context in their respective git branch. On open-ended optimization tasks, SwarmResearch discovers better or comparable solutions to state-of-the-art LLM-guided evolution and multi-agent techniques on 13/15 tasks, driven by higher-level exploration. Compared with fixed scaling of serial and parallel agents, SwarmResearch's orchestrator-guided scaling discovers better-performing solutions by adapting parallelism at different search depths. --- ### Training Hybrid Block Diffusion Language Models with Partial Bidirectionality Authors: Pranshu Chaturvedi, Parth Shroff, Tarun Suresh, Hangoo Kang, Kaiyue Wen Published: 2026-07-02 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.02805v1 High-throughput long-context generation is one of the central challenges for large language models. Generation is typically memory-bandwidth-bound rather than compute-bound: each decoding step must stream the accumulated key/value (KV) cache from memory, so bandwidth demand grows with context length while only one token is emitted. Two parallel approaches have therefore emerged: reducing memory access with efficient attention variants and linear-time mixers such as Mamba, or increasing parallel computation by generating blocks of tokens at once. However, technical challenges arise when combining these two ideas. Earlier hybrid diffusion models such as DiffuMamba use bidirectional Mamba mixing, including a reverse-direction scan relative to causal generation. This reverse scan needs to scan the entire sequence, so its states are not prefix-only and cannot be precisely reused as a cache even when diffusion is performed block by block. We propose a BDLM Mamba--attention hybrid that addresses this challenge by restricting the reverse Mamba scan to the active denoising block, which enables exact caching across blocks. In an 87M-parameter DCLM sweep, BDLM Mamba-H achieves the best C4-en validation perplexity compared to BDLM attention and full-sequence baselines. At 350M parameters, it remains competitive with BDLM attention. For long-context inference, BDLM Mamba-H reaches 19.7x the throughput of full-sequence DiffuMamba-H at 65K tokens and 3.7x the throughput of BDLM attention at 262K, showing that Mamba hybrids are a potential long-context diffusion architecture. --- ### Seduced by the Narrative: Assessing Rule Adherence in Semi-Open Textual Sandboxes Authors: Weiying Chen, Junlong Shen, Zhanyuan Guo, Xiaoou Zhou Published: 2026-07-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.02802v1 As LLMs are increasingly deployed as autonomous adjudicators in semi-open textual game environments, robust rule adherence becomes critical when user intent conflicts with system rules. However, these models are trained to be helpful and compliant, leaving them vulnerable to a class of attacks we term \textit{Rhetorical Injection}, where adversarial users exploit narrative framing techniques such as pseudo-logical reasoning and authoritative coercion to bypass adjudication logic. We present CoC-Seduce, a multi-agent adversarial benchmark built on Tabletop Role-Playing Game (TRPG) mechanics, an ideal instantiation of semi-open environments where rules are explicit for adjudication, yet interaction remains entirely in natural language. Three frontier models, i.e., GPT-5.4, Claude Sonnet 4.6, Gemini 3.5 Flash, serve as adversarial generators producing 5,376 samples across 4 world settings and 16 skill categories. We then benchmark 20 target adjudicators against this corpus. Evaluation across 20 models reveals that neither model scale nor explicit reasoning mechanisms reliably confer adjudication robustness, with \textsc{Pseudo-Logic} emerging as the dominant attack vector and cross-cultural settings exposing systematic knowledge gaps across all evaluated families. Project page: https://github.com/answerrtx/CoC-Seduce --- ### Induction Heads Interpolate N-Grams Authors: Francesco D'Angelo, Oguz Kaan Yuksel, Swathi Shree Narashiman, Nicolas Flammarion Published: 2026-07-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.02800v1 Induction heads are attention circuits believed to underlie in-context learning in transformers, yet a precise characterization of the estimators they implement remains elusive. We study transformers trained on order-$k$ Markov chains and identify two complementary smoothing mechanisms. First, at finite attention-weight scale, the circuit implements a soft context-matching estimator: it aggregates contributions from exact and partial context matches, weighted exponentially by their overlap, and induces a data-dependent interpolation across context orders analogous to Jelinek-Mercer smoothing. Second, a beginning-of-sequence (BOS) token induces additive pseudo-counts, recovering Dirichlet-style smoothing. We construct a disentangled transformer implementing both mechanisms and show that trained transformers recover the predicted attention patterns. Across settings where pseudo-count smoothing is optimal or lower-order contexts provide structured evidence, trained transformers match or outperform classical count-based baselines. Our results bridge mechanistic interpretability of induction heads with classical statistical smoothing, revealing that transformers learn to regularize in-context estimation rather than simply count. ---