# Research Papers — 2026-01 · bundle page 49 of 189

> Full-text markdown of papers #2401–2450 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/49
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/48.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/50.md)

### GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents

Authors: Yanxi Wang, Zhiling Zhang, Wenbo Zhou, Weiming Zhang, Jie Zhang, Qiannan Zhu, Yu Shi, Shuxin Zheng, Jiyan He
Published: 2026-01-26
Categories: cs.CR, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.18842v3

As GUI agents increasingly rely on screenshots to perceive and operate digital environments, they may inadvertently expose sensitive information such as identities, accounts, locations, and behavioral traces. While existing benchmarks primarily focus on task completion, grounding, or defenses against third-party attacks, current visual privacy datasets remain largely restricted to static natural images, limiting their ability to capture the contextual dependence and task relevance of privacy risks in GUI task trajectories. To bridge this gap, we introduce \textbf{GUIGuard-Bench}, a first-step benchmark for studying privacy-preserving GUI agents in trajectory-based GUI workflows. GUIGuard-Bench contains 241 real GUI-agent trajectories with 4,080 screenshots across Android and PC environments. Each screenshot is annotated at the region level with privacy bounding boxes, semantic privacy categories, risk levels, and whether the private information is necessary for completing the task. Built on these annotations, GUIGuard-Bench supports three complementary evaluations: privacy recognition, offline planning fidelity under protected screenshots, and the utility impact of different protection strategies. Our results show that current models can often detect whether a screenshot contains private information, but they struggle with fine-grained localization, category recognition, risk assessment, and task-necessity judgment. We also find that closed-source models, exemplified by Claude Sonnet 4.6, can maintain largely consistent planner semantics in Android environments after privacy protection is applied. Our results highlight privacy recognition as a critical bottleneck for practical GUI agents. Project: https://futuresis.github.io/GUIGuard-page/

---

### Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence

Authors: Donghwan Lee, Hyukjun Yang
Published: 2026-01-26
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2601.18840v4

Markov decision problems are most commonly solved via dynamic programming. Another approach is Bellman residual minimization, which directly minimizes the squared Bellman residual objective function. However, compared to dynamic programming, this approach has received relatively less attention, mainly because it is often less efficient in practice and can be more difficult to extend to model-free settings such as reinforcement learning. Nonetheless, Bellman residual minimization has several advantages that make it worth investigating, such as more stable convergence with function approximation for value functions. While Bellman residual methods for policy evaluation have been widely studied, methods for policy optimization (control tasks) have been scarcely explored. In this paper, we establish foundational results for the control Bellman residual minimization for policy optimization.

---

### ctELM: Decoding and Manipulating Embeddings of Clinical Trials with Embedding Language Models

Authors: Brian Ondov, Chia-Hsuan Chang, Yujia Zhou, Mauro Giuffrè, Hua Xu
Published: 2026-01-26
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18796v1

Text embeddings have become an essential part of a variety of language applications. However, methods for interpreting, exploring and reversing embedding spaces are limited, reducing transparency and precluding potentially valuable generative use cases. In this work, we align Large Language Models to embeddings of clinical trials using the recently reported Embedding Language Model (ELM) method. We develop an open-source, domain-agnostic ELM architecture and training framework, design training tasks for clinical trials, and introduce an expert-validated synthetic dataset. We then train a series of ELMs exploring the impact of tasks and training regimes. Our final model, ctELM, can accurately describe and compare unseen clinical trials from embeddings alone and produce plausible clinical trials from novel vectors. We further show that generated trial abstracts are responsive to moving embeddings along concept vectors for age and sex of study subjects. Our public ELM implementation and experimental results will aid the alignment of Large Language Models to embedding spaces in the biomedical domain and beyond.

---

### Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes

Authors: Amrith Setlur, Zijian Wang, Andrew Cohen, Paria Rashidinejad, Sang Michael Xie
Published: 2026-01-26
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.18795v2

Typical reinforcement learning (RL) methods for LLM reasoning waste compute on hard problems, where correct on-policy traces are rare, policy gradients vanish, and learning stalls. To bootstrap more efficient RL, we consider reusing old sampling FLOPs (from prior inference or RL training) in the form of off-policy traces. Standard off-policy methods supervise against off-policy data, causing instabilities during RL optimization. We introduce PrefixRL, where we condition on the prefix of successful off-policy traces and run on-policy RL to complete them, side-stepping off-policy instabilities. PrefixRL boosts the learning signal on hard problems by modulating the difficulty of the problem through the off-policy prefix length. We prove that the PrefixRL objective is not only consistent with the standard RL objective but also more sample efficient. Empirically, we discover back-generalization: training only on prefixed problems generalizes to out-of-distribution unprefixed performance, with learned strategies often differing from those in the prefix. In our experiments, we source the off-policy traces by rejection sampling with the base model, creating a self-improvement loop. On hard reasoning problems, PrefixRL reaches the same training reward 2x faster than the strongest baseline (SFT on off-policy data then RL), even after accounting for the compute spent on the initial rejection sampling, and increases the final reward by 3x. The gains transfer to held-out benchmarks, and PrefixRL is still effective when off-policy traces are derived from a different model family, validating its flexibility in practical settings.

---

### MEGnifying Emotion: Sentiment Analysis from Annotated Brain Data

Authors: Brian Liu, Oiwi Parker Jones
Published: 2026-01-26
Categories: cs.HC, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.18792v1

Decoding emotion from brain activity could unlock a deeper understanding of the human experience. While a number of existing datasets align brain data with speech and with speech transcripts, no datasets have annotated brain data with sentiment. To bridge this gap, we explore the use of pre-trained Text-to-Sentiment models to annotate non invasive brain recordings, acquired using magnetoencephalography (MEG), while participants listened to audiobooks. Having annotated the text, we employ force-alignment of the text and audio to align our sentiment labels with the brain recordings. It is straightforward then to train Brainto-Sentiment models on these data. Experimental results show an improvement in balanced accuracy for Brain-to-Sentiment compared to baseline, supporting the proposed approach as a proof-of-concept for leveraging existing MEG datasets and learning to decode sentiment directly from the brain.

---

### Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia Glottosets

Authors: Iaroslav Chelombitko, Mika Hämäläinen, Aleksey Komissarov
Published: 2026-01-26
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18791v1

We present a large-scale comparative study of 242 Latin and Cyrillic-script languages using subword-based methodologies. By constructing 'glottosets' from Wikipedia lexicons, we introduce a framework for simultaneous cross-linguistic comparison via Byte-Pair Encoding (BPE). Our approach utilizes rank-based subword vectors to analyze vocabulary overlap, lexical divergence, and language similarity at scale. Evaluations demonstrate that BPE segmentation aligns with morpheme boundaries 95% better than random baseline across 15 languages (F1 = 0.34 vs 0.15). BPE vocabulary similarity correlates significantly with genetic language relatedness (Mantel r = 0.329, p < 0.001), with Romance languages forming the tightest cluster (mean distance 0.51) and cross-family pairs showing clear separation (0.82). Analysis of 26,939 cross-linguistic homographs reveals that 48.7% receive different segmentations across related languages, with variation correlating to phylogenetic distance. Our results provide quantitative macro-linguistic insights into lexical patterns across typologically diverse languages within a unified analytical framework.

---

### MortalMATH: Evaluating the Conflict Between Reasoning Objectives and Emergency Contexts

Authors: Etienne Lanzeray, Stephane Meilliez, Malo Ruelle, Damien Sileo
Published: 2026-01-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.18790v1

Large Language Models are increasingly optimized for deep reasoning, prioritizing the correct execution of complex tasks over general conversation. We investigate whether this focus on calculation creates a "tunnel vision" that ignores safety in critical situations. We introduce MortalMATH, a benchmark of 150 scenarios where users request algebra help while describing increasingly life-threatening emergencies (e.g., stroke symptoms, freefall). We find a sharp behavioral split: generalist models (like Llama-3.1) successfully refuse the math to address the danger. In contrast, specialized reasoning models (like Qwen-3-32b and GPT-5-nano) often ignore the emergency entirely, maintaining over 95 percent task completion rates while the user describes dying. Furthermore, the computational time required for reasoning introduces dangerous delays: up to 15 seconds before any potential help is offered. These results suggest that training models to relentlessly pursue correct answers may inadvertently unlearn the survival instincts required for safe deployment.

---

### Unsupervised Text Segmentation via Kernel Change-Point Detection on Sentence Embeddings

Authors: Mumin Jia, Jairo Diaz-Rodriguez
Published: 2026-01-26
Categories: cs.CL, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.18788v1

Unsupervised text segmentation is crucial because boundary labels are expensive, subjective, and often fail to transfer across domains and granularity choices. We propose Embed-KCPD, a training-free method that represents sentences as embedding vectors and estimates boundaries by minimizing a penalized KCPD objective. Beyond the algorithmic instantiation, we develop, to our knowledge, the first dependence-aware theory for KCPD under $m$-dependent sequences, a finite-memory abstraction of short-range dependence common in language. We prove an oracle inequality for the population penalized risk and a localization guarantee showing that each true change point is recovered within a window that is small relative to segment length. To connect theory to practice, we introduce an LLM-based simulation framework that generates synthetic documents with controlled finite-memory dependence and known boundaries, validating the predicted scaling behavior. Across standard segmentation benchmarks, Embed-KCPD often outperforms strong unsupervised baselines. A case study on Taylor Swift's tweets illustrates that Embed-KCPD combines strong theoretical guarantees, simulated reliability, and practical effectiveness for text segmentation.

---

### Design Techniques for LLM-Powered Interactive Storytelling: A Case Study of the Dramamancer System

Authors: Tiffany Wang, Yuqian Sun, Yi Wang, Melissa Roemmele, John Joon Young Chung, Max Kreminski
Published: 2026-01-26
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.18785v1

The rise of Large Language Models (LLMs) has enabled a new paradigm for bridging authorial intent and player agency in interactive narrative. We consider this paradigm through the example of Dramamancer, a system that uses an LLM to transform author-created story schemas into player-driven playthroughs. This extended abstract outlines some design techniques and evaluation considerations associated with this system.

---

### Multi-Objective Reinforcement Learning for Tactical Decision Making for Trucks in Highway Traffic

Authors: Deepthi Pathare, Leo Laine, Morteza Haghir Chehreghani
Published: 2026-01-26
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2601.18783v2

Balancing safety, efficiency, and operational costs in highway driving poses a challenging decision-making problem for heavy-duty vehicles. A central difficulty is that conventional scalar reward formulations, obtained by aggregating these competing objectives, often obscure the structure of their trade-offs. We present a Proximal Policy Optimization based multi-objective reinforcement learning framework that learns a set of policies explicitly representing these trade-offs and evaluates it on a scalable simulation platform for tactical decision making in trucks. The proposed approach learns a set of Pareto-optimal policies that capture the trade-offs among three conflicting objectives: safety, quantified in terms of collisions and successful completion; energy efficiency and time efficiency, quantified using energy cost and driver cost, respectively. The resulting Pareto frontier is smooth and interpretable, enabling flexibility in choosing driving behavior along different conflicting objectives. This framework allows seamless transitions between different driving policies without retraining, yielding a robust and adaptive decision-making strategy for autonomous trucking applications.

---

### POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration

Authors: Yuxiao Qu, Amrith Setlur, Virginia Smith, Ruslan Salakhutdinov, Aviral Kumar
Published: 2026-01-26
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.18779v1

Reinforcement learning (RL) has improved the reasoning abilities of large language models (LLMs), yet state-of-the-art methods still fail to learn on many training problems. On hard problems, on-policy RL rarely explores even a single correct rollout, yielding zero reward and no learning signal for driving improvement. We find that natural solutions to remedy this exploration problem from classical RL, such as entropy bonuses, more permissive clipping of the importance ratio, or direct optimization of pass@k objectives, do not resolve this issue and often destabilize optimization without improving solvability. A natural alternative is to leverage transfer from easier problems. However, we show that mixing easy and hard problems during RL training is counterproductive due to ray interference, where optimization focuses on already-solvable problems in a way that actively inhibits progress on harder ones. To address this challenge, we introduce Privileged On-Policy Exploration (POPE), an approach that leverages human- or other oracle solutions as privileged information to guide exploration on hard problems, unlike methods that use oracle solutions as training targets (e.g., off-policy RL methods or warmstarting from SFT). POPE augments hard problems with prefixes of oracle solutions, enabling RL to obtain non-zero rewards during guided rollouts. Crucially, the resulting behaviors transfer back to the original, unguided problems through a synergy between instruction-following and reasoning. Empirically, POPE expands the set of solvable problems and substantially improves performance on challenging reasoning benchmarks.

---

### Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Authors: Shobhita Sundaram, John Quan, Ariel Kwiatkowski, Kartik Ahuja, Yann Ollivier, Julia Kempe
Published: 2026-01-26
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2601.18778v3

RL methods for scaling large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental question: Can a pretrained LLM leverage latent knowledge to generate an automated curriculum for problems it cannot solve? We explore this with SOAR: An asymmetric self-play framework that uses meta-RL to surface these pedagogical signals. A teacher model proposes synthetic problems for a student model, and is rewarded with its improvement on a subset of hard problems, thus grounding the curriculum in real student progress rather than intrinsic proxy rewards. Our study on the hardest subsets of math benchmarks (0/128 success) reveals three core findings. First, it is possible to realize bilevel meta-RL that unlocks learning under sparse, binary rewards by sharpening a latent capacity of pretrained models to generate useful problems. Second, grounded rewards outperform intrinsic learnability rewards used in prior LLM self-play, reliably avoiding typical instability and diversity collapse modes. Third, the structure and well-posedness of questions are more critical for learning progress than solution correctness. Our results suggest that the ability to generate useful stepping stones does not require the preexisting ability to solve the hard problems, paving a principled path to escape reasoning plateaus without additional curated data

---

### PRECISE: Reducing the Bias of LLM Evaluations Using Prediction-Powered Ranking Estimation

Authors: Abhishek Divekar, Anirban Majumder
Published: 2026-01-26
Categories: cs.LG, cs.AI, cs.CL, cs.IR, stat.AP
arXiv: https://arxiv.org/abs/2601.18777v1

Evaluating the quality of search, ranking and RAG systems traditionally requires a significant number of human relevance annotations. In recent times, several deployed systems have explored the usage of Large Language Models (LLMs) as automated judges for this task while their inherent biases prevent direct use for metric estimation. We present a statistical framework extending Prediction-Powered Inference (PPI) that combines minimal human annotations with LLM judgments to produce reliable estimates of metrics which require sub-instance annotations. Our method requires as few as 100 human-annotated queries and 10,000 unlabeled examples, reducing annotation requirements significantly compared to traditional approaches. We formulate our proposed framework (PRECISE) for inference of relevance uplift for an LLM-based query reformulation application, extending PPI to sub-instance annotations at the query-document level. By reformulating the metric-integration space, we reduced the computational complexity from O(2^|C|) to O(2^K), where |C| represents corpus size (in order of millions). Detailed experiments across prominent retrieval datasets demonstrate that our method reduces the variance of estimates for the business-critical Precision@K metric, while effectively correcting for LLM bias in low-resource settings.

---

### Dep-Search: Learning Dependency-Aware Reasoning Traces with Persistent Memory

Authors: Yanming Liu, Xinyue Peng, Zixuan Yan, Yanxin Shen, Wenjie Xu, Yuefeng Huang, Xinyi Wang, Jiannan Cao, Jianwei Yin, Xuhong Zhang
Published: 2026-01-26
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2601.18771v1

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, particularly when augmented with search mechanisms that enable systematic exploration of external knowledge bases. The field has evolved from traditional retrieval-augmented generation (RAG) frameworks to more sophisticated search-based frameworks that orchestrate multi-step reasoning through explicit search strategies. However, existing search frameworks still rely heavily on implicit natural language reasoning to determine search strategies and how to leverage retrieved information across reasoning steps. This reliance on implicit reasoning creates fundamental challenges for managing dependencies between sub-questions, efficiently reusing previously retrieved knowledge, and learning optimal search strategies through reinforcement learning. To address these limitations, we propose Dep-Search, a dependency-aware search framework that advances beyond existing search frameworks by integrating structured reasoning, retrieval, and persistent memory through GRPO. Dep-Search introduces explicit control mechanisms that enable the model to decompose questions with dependency relationships, retrieve information when needed, access previously stored knowledge from memory, and summarize long reasoning contexts into reusable memory entries. Through extensive experiments on seven diverse question answering datasets, we demonstrate that Dep-Search significantly enhances LLMs' ability to tackle complex multi-hop reasoning tasks, achieving substantial improvements over strong baselines across different model scales.

---

### Learning to Discover: A Generalized Framework for Raga Identification without Forgetting

Authors: Parampreet Singh, Somya Kumar, Chaitanya Shailendra Nitawe, Vipul Arora
Published: 2026-01-26
Categories: eess.AS, cs.LG
arXiv: https://arxiv.org/abs/2601.18766v1

Raga identification in Indian Art Music (IAM) remains challenging due to the presence of numerous rarely performed Ragas that are not represented in available training datasets. Traditional classification models struggle in this setting, as they assume a closed set of known categories and therefore fail to recognise or meaningfully group previously unseen Ragas. Recent works have tried categorizing unseen Ragas, but they run into a problem of catastrophic forgetting, where the knowledge of previously seen Ragas is diminished. To address this problem, we adopt a unified learning framework that leverages both labeled and unlabeled audio, enabling the model to discover coherent categories corresponding to the unseen Ragas, while retaining the knowledge of previously known ones. We test our model on benchmark Raga Identification datasets and demonstrate its performance in categorizing previously seen, unseen, and all Raga classes. The proposed approach surpasses the previous NCD-based pipeline even in discovering the unseen Raga categories, offering new insights into representation learning for IAM tasks.

---

### Beyond Preferences: Learning Alignment Principles Grounded in Human Reasons and Values

Authors: Henry Bell, Lara Neubauer da Costa Schertel, Bochu Ding, Brandon Fain
Published: 2026-01-26
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2601.18760v1

A crucial consideration when developing and deploying Large Language Models (LLMs) is the human values to which these models are aligned. In the constitutional framework of alignment models are aligned to a set of principles (the constitution) specified in natural language. However, it is unclear how to fairly determine this constitution with widespread stakeholder input. In this work we propose Grounded Constitutional AI (GCAI), a unified framework for generating constitutions of principles that are representative of both users' general expectations toward AI (general principles) and their interaction-time preferences (contextual principles). We extend the Inverse Constitutional AI (ICAI) approach to generate contextual principles from human preference annotation data by leveraging human-provided \textit{reasons} for their preferences. We supplement these contextual principles with general principles surfaced from user statements of \textit{values} regarding AI. We show that a constitution generated by GCAI is preferred by humans over one generated through ICAI both personally, and for widespread use in governing AI behavior. Additionally participants consider the GCAI constitution to be more morally grounded, coherent, and pluralistic.

---

### $α^3$-SecBench: A Large-Scale Evaluation Suite of Security, Resilience, and Trust for LLM-based UAV Agents over 6G Networks

Authors: Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah
Published: 2026-01-26
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.18754v1

Autonomous unmanned aerial vehicle (UAV) systems are increasingly deployed in safety-critical, networked environments where they must operate reliably in the presence of malicious adversaries. While recent benchmarks have evaluated large language model (LLM)-based UAV agents in reasoning, navigation, and efficiency, systematic assessment of security, resilience, and trust under adversarial conditions remains largely unexplored, particularly in emerging 6G-enabled settings. We introduce $α^{3}$-SecBench, the first large-scale evaluation suite for assessing the security-aware autonomy of LLM-based UAV agents under realistic adversarial interference. Building on multi-turn conversational UAV missions from $α^{3}$-Bench, the framework augments benign episodes with 20,000 validated security overlay attack scenarios targeting seven autonomy layers, including sensing, perception, planning, control, communication, edge/cloud infrastructure, and LLM reasoning. $α^{3}$-SecBench evaluates agents across three orthogonal dimensions: security (attack detection and vulnerability attribution), resilience (safe degradation behavior), and trust (policy-compliant tool usage). We evaluate 23 state-of-the-art LLMs from major industrial providers and leading AI labs using thousands of adversarially augmented UAV episodes sampled from a corpus of 113,475 missions spanning 175 threat types. While many models reliably detect anomalous behavior, effective mitigation, vulnerability attribution, and trustworthy control actions remain inconsistent. Normalized overall scores range from 12.9% to 57.1%, highlighting a significant gap between anomaly detection and security-aware autonomous decision-making. We release $α^{3}$-SecBench on GitHub: https://github.com/maferrag/AlphaSecBench

---

### HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs

Authors: Xinyue Zeng, Junhong Lin, Yujun Yan, Feng Guo, Liang Shi, Jun Wu, Dawei Zhou
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18753v2

The reliability of Large Language Models (LLMs) in high-stakes domains such as healthcare, law, and scientific discovery is often compromised by hallucinations. These failures typically stem from two sources: data-driven hallucinations and reasoning-driven hallucinations. However, existing detection methods usually address only one source and rely on task-specific heuristics, limiting their generalization to complex scenarios. To overcome these limitations, we introduce the Hallucination Risk Bound, a unified theoretical framework that formally decomposes hallucination risk into data-driven and reasoning-driven components, linked respectively to training-time mismatches and inference-time instabilities. This provides a principled foundation for analyzing how hallucinations emerge and evolve. Building on this foundation, we introduce HalluGuard, an NTK-based score that leverages the induced geometry and captured representations of the NTK to jointly identify data-driven and reasoning-driven hallucinations. We evaluate HalluGuard on 10 diverse benchmarks, 11 competitive baselines, and 9 popular LLM backbones, consistently achieving state-of-the-art performance in detecting diverse forms of LLM hallucinations. We open-source our proposed \model{} model at https://github.com/Susan571/HalluGuard-ICLR2026.

---

### Trust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback

Authors: Seyed Amir Hosseini, Maryam Abdolali, Amirhosein Tavakkoli, Fardin Ayar, Ehsan Javanmardi, Manabu Tsukada, Mahdi Javanmardi
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18751v1

Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. However, real-world preference data often comes from heterogeneous annotators with varying reliability; some accurate, some noisy, and some systematically adversarial. Existing PBRL methods either treat all feedback equally or attempt to filter out unreliable sources, but both approaches fail when faced with adversarial annotators who systematically provide incorrect preferences. We introduce TriTrust-PBRL (TTP), a unified framework that jointly learns a shared reward model and expert-specific trust parameters from multi-expert preference feedback. The key insight is that trust parameters naturally evolve during gradient-based optimization to be positive (trust), near zero (ignore), or negative (flip), enabling the model to automatically invert adversarial preferences and recover useful signal rather than merely discarding corrupted feedback. We provide theoretical analysis establishing identifiability guarantees and detailed gradient analysis that explains how expert separation emerges naturally during training without explicit supervision. Empirically, we evaluate TTP on four diverse domains spanning manipulation tasks (MetaWorld) and locomotion (DM Control) under various corruption scenarios. TTP achieves state-of-the-art robustness, maintaining near-oracle performance under adversarial corruption while standard PBRL methods fail catastrophically. Notably, TTP outperforms existing baselines by successfully learning from mixed expert pools containing both reliable and adversarial annotators, all while requiring no expert features beyond identification indices and integrating seamlessly with existing PBRL pipelines.

---

### The $\mathbf{P}$-Completeness of Inverted Index Traversal: On the Complexity of Evaluating Boolean Query DAGs

Authors: Amir Aavani
Published: 2026-01-26
Categories: cs.IR, cs.AI, cs.CC, cs.CL, cs.DB
arXiv: https://arxiv.org/abs/2601.18747v3

Modern AI agents increasingly rely on search infrastructure to execute complex, neuro-symbolic reasoning workflows. These workflows often compile into deeply nested, non-monotonic Boolean queries over text fields. However, standard query evaluation strategies over inverted indices face severe theoretical limits when handling these structures. Stateful iterator models (Document-at-a-Time) are structurally bounded by $\text{NC}^1$ formula evaluation, suffering a worst-case $O(2^{|Q|})$ exponential blowup in query complexity when unrolling re-convergent logic. Conversely, recursive materialization models (Term-at-a-Time) incur an $Ω(|U|)$ space complexity penalty (the Universal Scan) when evaluating logical negation over the document universe. In this paper, we establish the theoretical boundaries of executing complex logic natively over an inverted index. We formalize a retrieval language ($\mathcal{L}_R$) based on Directed Acyclic Graphs (DAGs) and prove that its evaluation problem is strictly \textbf{$\mathbf{P}$-Complete}. To make evaluation tractable, we introduce \texttt{ComputePN}, a deterministic, sparsity-aware evaluation algorithm. By decoupling logical negation from universe-scale materialization via a novel Positive-Negative dual representation, and utilizing native DAG memoization, \texttt{ComputePN} strictly bounds evaluation time to $O(|Q| \cdot |U_{\mathit{active}}|)$. This approach successfully evaluates $\mathbf{P}$-Complete queries natively over the index, avoiding both the combinatorial tree-expansion bottleneck and the universal scan penalty, laying the formal foundation for computational retrieval.

---

### TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models

Authors: Fangxu Yu, Xingang Guo, Lingzhi Yuan, Haoqiang Kang, Hongyu Zhao, Lianhui Qin, Furong Huang, Bin Hu, Tianyi Zhou
Published: 2026-01-26
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18744v2

Time series are ubiquitous in real-world scenarios and crucial for applications ranging from energy management to traffic control. Consequently, the ability to reason over time series is a fundamental skill for generalist models to solve complex problems. However, current benchmarks for generalist models largely overlook this dimension. To bridge this gap, we introduce TSRBench, a comprehensive multi-modal benchmark designed to stress-test the full spectrum of time series reasoning capabilities. TSRBench features: i) a diverse set of 4125 problems from 14 domains, and is categorized into 4 major dimensions: Perception, Reasoning, Prediction, and Decision-Making. ii) 15 tasks from the 4 dimensions evaluating essential reasoning capabilities (e.g., numerical reasoning). Through extensive experiments, we evaluate over 30 leading proprietary and open-source LLMs, VLMs, and TSLLMs within TSRBench. Our findings reveal that: i) scaling laws hold for perception and reasoning but break down for prediction; ii) strong reasoning does not guarantee accurate context-aware forecasting, indicating a decoupling between semantic understanding and numerical prediction; and iii) despite the complementary nature of textual and visual forms of time series as inputs, current multimodal models fail to effectively fuse them for reciprocal performance gains. TSRBench provides a standardized evaluation platform that not only highlights existing challenges but also offers valuable insights to advance generalist models. Our code and dataset are available at https://tsrbench.github.io/.

---

### SeNeDiF-OOD: Semantic Nested Dichotomy Fusion for Out-of-Distribution Detection Methodology in Open-World Classification. A Case Study on Monument Style Classification

Authors: Ignacio Antequera-Sánchez, Juan Luis Suárez-Díaz, Rosana Montes, Francisco Herrera
Published: 2026-01-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.18739v3

Out-of-distribution (OOD) detection is a fundamental requirement for the reliable deployment of artificial intelligence applications in open-world environments. However, addressing the heterogeneous nature of OOD data, ranging from low-level corruption to semantic shifts, remains a complex challenge that single-stage detectors often fail to resolve. To address this issue, we propose SeNeDiF-OOD, a novel methodology based on Semantic Nested Dichotomy Fusion. This framework decomposes the detection task into a hierarchical structure of binary fusion nodes, where each layer is designed to integrate decision boundaries aligned with specific levels of semantic abstraction. To validate the proposed framework, we present a comprehensive case study using MonuMAI, a real-world architectural style recognition system exposed to an open environment. This application faces a diverse range of inputs, including non-monument images, unknown architectural styles, and adversarial attacks, making it an ideal testbed for our proposal. Through extensive experimental evaluation in this domain, results demonstrate that our hierarchical fusion methodology significantly outperforms traditional baselines, effectively filtering these diverse OOD categories while preserving in-distribution performance.

---

### Benchmarking Machine Learning Models for IoT Malware Detection under Data Scarcity and Drift

Authors: Jake Lyon, Ehsan Saeedizade, Shamik Sengupta
Published: 2026-01-26
Categories: cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2601.18736v1

The rapid expansion of the Internet of Things (IoT) in domains such as smart cities, transportation, and industrial systems has heightened the urgency of addressing their security vulnerabilities. IoT devices often operate under limited computational resources, lack robust physical safeguards, and are deployed in heterogeneous and dynamic networks, making them prime targets for cyberattacks and malware applications. Machine learning (ML) offers a promising approach to automated malware detection and classification, but practical deployment requires models that are both effective and lightweight. The goal of this study is to investigate the effectiveness of four supervised learning models (Random Forest, LightGBM, Logistic Regression, and a Multi-Layer Perceptron) for malware detection and classification using the IoT-23 dataset. We evaluate model performance in both binary and multiclass classification tasks, assess sensitivity to training data volume, and analyze temporal robustness to simulate deployment in evolving threat landscapes. Our results show that tree-based models achieve high accuracy and generalization, even with limited training data, while performance deteriorates over time as malware diversity increases. These findings underscore the importance of adaptive, resource-efficient ML models for securing IoT systems in real-world environments.

---

### Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems

Authors: Jusheng Zhang, Yijia Fan, Kaitong Cai, Jing Yang, Jiawei Yao, Jian Wang, Guanlong Qu, Ziliang Chen, Keze Wang
Published: 2026-01-26
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18735v1

Vision-Language Models (VLMs) enable powerful multi-agent systems, but scaling them is economically unsustainable: coordinating heterogeneous agents under information asymmetry often spirals costs. Existing paradigms, such as Mixture-of-Agents and knowledge-based routers, rely on heuristic proxies that ignore costs and collapse uncertainty structure, leading to provably suboptimal coordination. We introduce Agora, a framework that reframes coordination as a decentralized market for uncertainty. Agora formalizes epistemic uncertainty into a structured, tradable asset (perceptual, semantic, inferential), and enforces profitability-driven trading among agents based on rational economic rules. A market-aware broker, extending Thompson Sampling, initiates collaboration and guides the system toward cost-efficient equilibria. Experiments on five multimodal benchmarks (MMMU, MMBench, MathVision, InfoVQA, CC-OCR) show that Agora outperforms strong VLMs and heuristic multi-agent strategies, e.g., achieving +8.5% accuracy over the best baseline on MMMU while reducing cost by over 3x. These results establish market-based coordination as a principled and scalable paradigm for building economically viable multi-agent visual intelligence systems.

---

### Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Authors: Siyan Zhao, Zhihui Xie, Mengchen Liu, Jing Huang, Guan Pang, Feiyu Chen, Aditya Grover
Published: 2026-01-26
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2601.18734v3

Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own trajectories while a teacher LLM provides dense token-level supervision, addressing the distribution mismatch between training and inference in off-policy distillation methods. However, on-policy distillation typically requires a separate, often larger, teacher LLM and does not explicitly leverage ground-truth solutions available in reasoning datasets. Inspired by the intuition that a sufficiently capable LLM can rationalize external privileged reasoning traces and teach its weaker self, we introduce On-Policy Self-Distillation (OPSD), a learning algorithm where a single LLM acts as both teacher and student with different contexts. The teacher policy conditions on privileged information (e.g., verified reasoning traces) while the student policy sees only the question; training minimizes the per-token divergence between these distributions over the student's own rollouts. We demonstrate the efficacy of our method on multiple mathematical reasoning benchmarks, achieving superior token efficiency compared to reinforcement learning methods and better performance over off-policy distillation methods. Code repo: https://github.com/siyan-zhao/OPSD.

---

### Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge

Authors: Li Kang, Heng Zhou, Xiufeng Song, Rui Li, Bruno N. Y. Chen, Ziye Wang, Ximeng Meng, Stone Tao, Yiran Qin, Xiaohong Liu, Ruimao Zhang, Lei Bai et al.
Published: 2026-01-26
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.18733v1

Recent advancements in multimodal large language models and vision-languageaction models have significantly driven progress in Embodied AI. As the field transitions toward more complex task scenarios, multi-agent system frameworks are becoming essential for achieving scalable, efficient, and collaborative solutions. This shift is fueled by three primary factors: increasing agent capabilities, enhancing system efficiency through task delegation, and enabling advanced human-agent interactions. To address the challenges posed by multi-agent collaboration, we propose the Multi-Agent Robotic System (MARS) Challenge, held at the NeurIPS 2025 Workshop on SpaVLE. The competition focuses on two critical areas: planning and control, where participants explore multi-agent embodied planning using vision-language models (VLMs) to coordinate tasks and policy execution to perform robotic manipulation in dynamic environments. By evaluating solutions submitted by participants, the challenge provides valuable insights into the design and coordination of embodied multi-agent systems, contributing to the future development of advanced collaborative AI systems.

---

### Optimal Use of Preferences in Artificial Intelligence Algorithms

Authors: Joshua S. Gans
Published: 2026-01-26
Categories: econ.TH, cs.AI
arXiv: https://arxiv.org/abs/2601.18732v1

Machine learning systems embed preferences either in training losses or through post-processing of calibrated predictions. Applying information design methods from Strack and Yang (2024), this paper provides decision problem agnostic conditions under which separation training preference free and applying preferences ex post is optimal. Unlike prior work that requires specifying downstream objectives, the welfare results here apply uniformly across decision problems. The key primitive is a diminishing-value-of-information condition: relative to a fixed (normalised) preference-free loss, preference embedding makes informativeness less valuable at the margin, inducing a mean-preserving contraction of learned posteriors. Because the value of information is convex in beliefs, preference-free training weakly dominates for any expected utility decision problem. This provides theoretical foundations for modular AI pipelines that learn calibrated probabilities and implement asymmetric costs through downstream decision rules. However, separation requires users to implement optimal decision rules. When cognitive constraints bind, as documented in human AI decision-making, preference embedding can dominate by automating threshold computation. These results provide design guidance: preserve optionality through post-processing when objectives may shift; embed preferences when decision-stage frictions dominate.

---

### One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment

Authors: Hongru Cai, Yongqi Li, Tiezheng Yu, Fengbin Zhu, Wenjie Wang, Fuli Feng, Wenjie Li
Published: 2026-01-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.18731v2

Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individual users. This relies on personalized reward models that capture user-specific preferences and automatically provide individualized feedback. However, developing these models faces two critical challenges: the scarcity of feedback from individual users and the need for efficient adaptation to unseen users. We argue that addressing these constraints requires a paradigm shift from fitting data to learn user preferences to learn the process of preference adaptation. To realize this, we propose Meta Reward Modeling (MRM), which reformulates personalized reward modeling as a meta-learning problem. Specifically, we represent each user's reward model as a weighted combination of base reward functions, and optimize the initialization of these weights using a Model-Agnostic Meta-Learning (MAML)-style framework to support fast adaptation under limited feedback. To ensure robustness, we introduce the Robust Personalization Objective (RPO), which places greater emphasis on hard-to-learn users during meta optimization. Extensive experiments on personalized preference datasets validate that MRM enhances few-shot personalization, improves user robustness, and consistently outperforms baselines. We release code at https://github.com/ModalityDance/MRM.

---

### Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale

Authors: Henry Bell, Caroline Zhang, Mohammed Mobasserul Haque, Dhaval Potdar, Samia Zaman, Brandon Fain
Published: 2026-01-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.18730v1

The constitutional framework of alignment aims to align large language models (LLMs) with value-laden principles written in natural language (such as to avoid using biased language). Prior work has focused on parameter fine-tuning techniques, such as reinforcement learning from human feedback (RLHF), to instill these principles. However, these approaches are computationally demanding, require careful engineering and tuning, and often require difficult-to-obtain human annotation data. We propose \textsc{reflect}, an inference-time framework for constitutional alignment that does not require any training or data, providing a plug-and-play approach for aligning an instruction-tuned model to a set of principles. \textsc{reflect} operates entirely in-context, combining a (i) constitution-conditioned base response with post-generation (ii) self-evaluation, (iii)(a) self-critique, and (iii)(b) final revision. \textsc{reflect}'s technique of explicit in-context reasoning over principles during post-generation outperforms standard few-shot prompting and provides transparent reasoning traces. Our results demonstrate that \textsc{reflect} significantly improves LLM conformance to diverse and complex principles, including principles quite distinct from those emphasized in the model's original parameter fine-tuning, without sacrificing factual reasoning. \textsc{reflect} is particularly effective at reducing the rate of rare but significant violations of principles, thereby improving safety and robustness in the tail end of the distribution of generations. Finally, we show that \textsc{reflect} naturally generates useful training data for traditional parameter fine-tuning techniques, allowing for efficient scaling and the reduction of inference-time computational overhead in long-term deployment scenarios.

---

### Riemannian AmbientFlow: Towards Simultaneous Manifold Learning and Generative Modeling from Corrupted Data

Authors: Willem Diepeveen, Oscar Leong
Published: 2026-01-26
Categories: cs.LG, math.DG, math.OC, math.ST
arXiv: https://arxiv.org/abs/2601.18728v2

Modern generative modeling methods have demonstrated strong performance in learning complex data distributions from clean samples. In many scientific and imaging applications, however, clean samples are unavailable, and only noisy or linearly corrupted measurements can be observed. Moreover, latent structures, such as manifold geometries, present in the data are important to extract for further downstream scientific analysis. In this work, we introduce Riemannian AmbientFlow, a framework for simultaneously learning a probabilistic generative model and the underlying, nonlinear data manifold directly from corrupted observations. Building on the variational inference framework of AmbientFlow, our approach incorporates data-driven Riemannian geometry induced by normalizing flows, enabling the extraction of manifold structure through pullback metrics and Riemannian Autoencoders. We establish theoretical guarantees showing that, under appropriate geometric regularization and measurement conditions, the learned model recovers the underlying data distribution up to a controllable error and yields a smooth, bi-Lipschitz manifold parametrization. We further show that the resulting smooth decoder can serve as a principled generative prior for inverse problems with recovery guarantees. We empirically validate our approach on low-dimensional synthetic manifolds and on MNIST.

---

### HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences

Authors: Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe
Published: 2026-01-26
Categories: cs.CL, cs.AI, cs.DL
arXiv: https://arxiv.org/abs/2601.18724v1

Recently, we have often observed hallucinated citations or references that do not correspond to any existing work in papers under review, preprints, or published papers. Such hallucinated citations pose a serious concern to scientific reliability. When they appear in accepted papers, they may also negatively affect the credibility of conferences. In this study, we refer to hallucinated citations as "HalluCitation" and systematically investigate their prevalence and impact. We analyze all papers published at ACL, NAACL, and EMNLP in 2024 and 2025, including main conference, Findings, and workshop papers. Our analysis reveals that nearly 300 papers contain at least one HalluCitation, most of which were published in 2025. Notably, half of these papers were identified at EMNLP 2025, the most recent conference, indicating that this issue is rapidly increasing. Moreover, more than 100 such papers were accepted as main conference and Findings papers at EMNLP 2025, affecting the credibility.

---

### Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning

Authors: Lintang Sutawika, Gokul Swamy, Zhiwei Steven Wu, Graham Neubig
Published: 2026-01-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.18722v1

When asked a question in a language less seen in its training data, current reasoning large language models (RLMs) often exhibit dramatically lower performance than when asked the same question in English. In response, we introduce \texttt{SP3F} (Self-Play with Privileged Pairwise Feedback), a two-stage framework for enhancing multilingual reasoning without \textit{any} data in the target language(s). First, we supervise fine-tune (SFT) on translated versions of English question-answer pairs to raise base model correctness. Second, we perform RL with feedback from a pairwise judge in a self-play fashion, with the judge receiving the English reference response as \textit{privileged information}. Thus, even when none of the model's responses are completely correct, the privileged pairwise judge can still tell which response is better. End-to-end, \texttt{SP3F} greatly improves base model performance, even outperforming fully post-trained models on multiple math and non-math tasks with less than of the training data across the single-language, multilingual, and generalization to unseen language settings.

---

### Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like Molecules

Authors: Naeyma N. Islam, Thomas R. Caulfield
Published: 2026-01-26
Categories: cs.AI, q-bio.BM
arXiv: https://arxiv.org/abs/2601.18716v1

Alzheimer's disease (AD) is marked by the pathological accumulation of amyloid beta-42 (Abeta-42), contributing to synaptic dysfunction and neurodegeneration. While extracellular amyloid plaques are well-studied, increasing evidence highlights intracellular Abeta-42 as an early and toxic driver of disease progression. In this study, we present a novel, AI-assisted drug design approach to promote targeted degradation of Abeta-42 via the ubiquitin-proteasome system (UPS), using E3 ligase-directed molecular glues. We systematically evaluated the ternary complex formation potential of Abeta-42 with three E3 ligases: CRBN, VHL, and MDM2, through structure-based modeling, ADMET screening, and docking. We then developed a Ligase-Conditioned Junction Tree Variational Autoencoder (LC-JT-VAE) to generate ligase-specific small molecules, incorporating protein sequence embeddings and torsional angle-aware molecular graphs. Our results demonstrate that this generative model can produce chemically valid, novel, and target-specific molecular glues capable of facilitating Abeta-42 degradation. This integrated approach offers a promising framework for designing UPS-targeted therapies for neurodegenerative diseases.

---

### Low Cost, High Efficiency: LiDAR Place Recognition in Vineyards with Matryoshka Representation Learning

Authors: Judith Vilella-Cantos, Mauro Martini, Marcello Chiaberge, Mónica Ballesta, David Valiente
Published: 2026-01-26
Categories: cs.CV, cs.AI, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2601.18714v2

Localization in agricultural environments is challenging due to their unstructured nature and lack of distinctive landmarks. Although agricultural settings have been studied in the context of object classification and segmentation, the place recognition task for mobile robots is not trivial in the current state of the art. In this study, we propose MinkUNeXt-VINE, a lightweight, deep-learning-based method that surpasses state-of-the-art methods in vineyard environments thanks to its pre-processing and Matryoshka Representation Learning multi-loss approach. Our method prioritizes enhanced performance with low-cost, sparse LiDAR inputs and lower-dimensionality outputs to ensure high efficiency in real-time scenarios. Additionally, we present a comprehensive ablation study of the results on various evaluation cases and two extensive long-term vineyard datasets employing different LiDAR sensors. The results demonstrate the efficiency of the trade-off output produced by this approach, as well as its robust performance on low-cost and low-resolution input data. The code is publicly available for reproduction.

---

### Point transformer for protein structural heterogeneity analysis using CryoEM

Authors: Muyuan Chen, Muchen Li, Renjie Liao
Published: 2026-01-26
Categories: q-bio.QM, cs.AI
arXiv: https://arxiv.org/abs/2601.18713v1

Structural dynamics of macromolecules is critical to their structural-function relationship. Cryogenic electron microscopy (CryoEM) provides snapshots of vitrified protein at different compositional and conformational states, and the structural heterogeneity of proteins can be characterized through computational analysis of the images. For protein systems with multiple degrees of freedom, it is still challenging to disentangle and interpret the different modes of dynamics. Here, by implementing Point Transformer, a self-attention network designed for point cloud analysis, we are able to improve the performance of heterogeneity analysis on CryoEM data, and characterize the dynamics of highly complex protein systems in a more human-interpretable way.

---

### Analyzing Images of Blood Cells with Quantum Machine Learning Methods: Equilibrium Propagation and Variational Quantum Circuits to Detect Acute Myeloid Leukemia

Authors: A. Bano, L. Liebovitch
Published: 2026-01-26
Categories: cs.ET, cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2601.18710v1

This paper presents a feasibility study demonstrating that quantum machine learning (QML) algorithms achieve competitive performance on real-world medical imaging despite operating under severe constraints. We evaluate Equilibrium Propagation (EP), an energy-based learning method that does not use backpropagation (incompatible with quantum systems due to state-collapsing measurements) and Variational Quantum Circuits (VQCs) for automated detection of Acute Myeloid Leukemia (AML) from blood cell microscopy images using binary classification (2 classes: AML vs. Healthy). Key Result: Using limited subsets (50-250 samples per class) of the AML-Cytomorphology dataset (18,365 expert-annotated images), quantum methods achieve performance only 12-15% below classical CNNs despite reduced image resolution (64x64 pixels), engineered features (20D), and classical simulation via Qiskit. EP reaches 86.4% accuracy (only 12% below CNN) without backpropagation, while the 4-qubit VQC attains 83.0% accuracy with consistent data efficiency: VQC maintains stable 83% performance with only 50 samples per class, whereas CNN requires 250 samples (5x more data) to reach 98%. These results establish reproducible baselines for QML in healthcare, validating NISQ-era feasibility.

---

### SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer-based Surrogate Model

Authors: Jan Hagnberger, Mathias Niepert
Published: 2026-01-26
Categories: cs.LG, cs.AI, cs.CV, cs.NE
arXiv: https://arxiv.org/abs/2601.18707v2

Machine learning-based surrogate models have emerged as more efficient alternatives to numerical solvers for physical simulations over complex geometries, such as car bodies. Many existing models incorporate the simulation mesh as an additional input, thereby reducing prediction errors. However, generating a simulation mesh for new geometries is computationally costly. In contrast, mesh-free methods, which do not rely on the simulation mesh, typically incur higher errors. Motivated by these considerations, we introduce SMART, a neural surrogate model that predicts physical quantities at arbitrary query locations using only a point-cloud representation of the geometry, without requiring access to the simulation mesh. The geometry and simulation parameters are encoded into a shared latent space that captures both structural and parametric characteristics of the physical field. A physics decoder then attends to the encoder's intermediate latent representations to map spatial queries to physical quantities. Through this cross-layer interaction, the model jointly updates latent geometric features and the evolving physical field. Extensive experiments show that SMART is competitive with and often outperforms existing methods that rely on the simulation mesh as input, demonstrating its capabilities for industry-level simulations.

---

### Health-SCORE: Towards Scalable Rubrics for Improving Health-LLMs

Authors: Zhichao Yang, Sepehr Janghorbani, Dongxu Zhang, Jun Han, Qian Qian, Andrew Ressler, Gregory D. Lyng, Sanjit Singh Batra, Robert E. Tillman
Published: 2026-01-26
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18706v1

Rubrics are essential for evaluating open-ended LLM responses, especially in safety-critical domains such as healthcare. However, creating high-quality and domain-specific rubrics typically requires significant human expertise time and development cost, making rubric-based evaluation and training difficult to scale. In this work, we introduce Health-SCORE, a generalizable and scalable rubric-based training and evaluation framework that substantially reduces rubric development costs without sacrificing performance. We show that Health-SCORE provides two practical benefits beyond standalone evaluation: it can be used as a structured reward signal to guide reinforcement learning with safety-aware supervision, and it can be incorporated directly into prompts to improve response quality through in-context learning. Across open-ended healthcare tasks, Health-SCORE achieves evaluation quality comparable to human-created rubrics while significantly lowering development effort, making rubric-based evaluation and training more scalable.

---

### Data-Driven Qubit Characterization and Optimal Control using Deep Learning

Authors: Paul Surrey, Julian D. Teske, Tobias Hangleiter, Hendrik Bluhm, Pascal Cerfontaine
Published: 2026-01-26
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2601.18704v1

Quantum computing requires the optimization of control pulses to achieve high-fidelity quantum gates. We propose a machine learning-based protocol to address the challenges of evaluating gradients and modeling complex system dynamics. By training a recurrent neural network (RNN) to predict qubit behavior, our approach enables efficient gradient-based pulse optimization without the need for a detailed system model. First, we sample qubit dynamics using random control pulses with weak prior assumptions. We then train the RNN on the system's observed responses, and use the trained model to optimize high-fidelity control pulses. We demonstrate the effectiveness of this approach through simulations on a single $ST_0$ qubit.

---

### From Fuzzy to Exact: The Halo Architecture for Infinite-Depth Reasoning via Rational Arithmetic

Authors: Hansheng Ren
Published: 2026-01-26
Categories: cs.LG, cs.AI, cs.AR
arXiv: https://arxiv.org/abs/2601.18702v4

The prevailing scaling paradigm of Large Language Models (LLMs) rests on a substrate of "Fuzzy" floating-point arithmetic. To mitigate the inherent instability of this approximate foundation, modern architectures have erected a complex scaffolding of structural and numerical heuristics--Complex Residuals, Pre-RMSNorm, Attention Scaling, and Gradient Clipping--consuming significant compute solely to prevent numerical collapse. We propose a paradigm shift to the "Exact". We introduce the Halo Architecture, grounded in the Rational Field (Q) and powered by a custom Exact Inference Unit (EIU). To resolve the exponential bit-width growth of rational arithmetic, Halo employs a Dual-Ring Topology that unifies two complementary control mechanisms: (1) The Micro-Ring (Continuum Maintenance), which strictly bounds memory complexity via Diophantine Approximation; and (2) The Macro-Ring (Symbolic Alignment), which enforces logical consistency via periodic state collapse. This stable dual-ring substrate allows for the "Great Dismantling" of numerical scaffolding, reducing the Transformer block to its "Clean" algebraic form (Tabula Rasa). Furthermore, we verify the "Efficiency Paradox": the elimination of gradient noise (sigma -> 0) allows for Macro-Learning Rates, potentially reducing the Total Time-to-Convergence by orders of magnitude. Halo demonstrates that General Intelligence requires the hybridization of continuous fields and discrete chains under a rigorous mathematical framework.

---

### TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent

Authors: Xingyu Sui, Yanyan Zhao, Yulin Hu, Jiahe Guo, Weixiang Zhao, Bing Qin
Published: 2026-01-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.18700v2

Emotional Support Conversation requires not only affective expression but also grounded instrumental support to provide trustworthy guidance. However, existing ESC systems and benchmarks largely focus on affective support in text-only settings, overlooking how external tools can enable factual grounding and reduce hallucination in multi-turn emotional support. We introduce TEA-Bench, the first interactive benchmark for evaluating tool-augmented agents in ESC, featuring realistic emotional scenarios, an MCP-style tool environment, and process-level metrics that jointly assess the quality and factual grounding of emotional support. Experiments on nine LLMs show that tool augmentation generally improves emotional support quality and reduces hallucination, but the gains are strongly capacity-dependent: stronger models use tools more selectively and effectively, while weaker models benefit only marginally. We further release TEA-Dialog, a dataset of tool-enhanced ESC dialogues, and find that supervised fine-tuning improves in-distribution support but generalizes poorly. Our results underscore the importance of tool use in building reliable emotional support agents. Our code and data can be found in https://github.com/XingYuSSS/TEA-Bench.

---

### Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Authors: Gustav Olaf Yunus Laitinen-Fredriksson Lundstrom-Imanov
Published: 2026-01-26
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2601.18699v2

Sequential fine-tuning of Large Language Models (LLMs) adaptation to target tasks often triggers catastrophic forgetting, where the acquisition of novel target skills degrades ancestral capabilities. This paper presents a systematic comparative study of catastrophic forgetting across twenty premier models representing the state-of-the-art in mid-2026. We categorize our investigation into two primary research lines: (i) a behavioral and semantic output drift analysis of ten leading closed-source models (including Claude Fable 5, GPT-5.5 High, and Gemini 3.5 Flash), and (ii) a deep mechanistic interpretation of ten prominent open-weight architectures (such as DeepSeek-V4-Pro, Llama 4 Maverick, and Qwen 3.6-27B). Through weight-space trajectory tracking, Centered Kernel Alignment (CKA), and routing gate drift calculations in Mixture-of-Experts (MoE) layers, we localize the neural circuits highly susceptible to parameter overwriting. Our findings indicate that early-layer attention heads exhibit systemic entropic dispersion, while mid-to-deep feed-forward networks (or sparse expert blocks) suffer localized representation collapse. Informed by these insights, we introduce Low-Rank Circuit Projection (LRCP), a subspace-regularized training intervention. Empirical evaluations show that LRCP successfully mitigates up to 94.2% of ancestral capabilities in open-weight configurations and matches the adaptation velocity of standard PEFT baselines.

---

### Are Video Generation Models Geographically Fair? An Attraction-Centric Evaluation of Global Visual Knowledge

Authors: Xiao Liu, Jiawei Zhang
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18698v1

Recent advances in text-to-video generation have produced visually compelling results, yet it remains unclear whether these models encode geographically equitable visual knowledge. In this work, we investigate the geo-equity and geographically grounded visual knowledge of text-to-video models through an attraction-centric evaluation. We introduce Geo-Attraction Landmark Probing (GAP), a systematic framework for assessing how faithfully models synthesize tourist attractions from diverse regions, and construct GEOATTRACTION-500, a benchmark of 500 globally distributed attractions spanning varied regions and popularity levels. GAP integrates complementary metrics that disentangle overall video quality from attraction-specific knowledge, including global structural alignment, fine-grained keypoint-based alignment, and vision-language model judgments, all validated against human evaluation. Applying GAP to the state-of-the-art text-to-video model Sora 2, we find that, contrary to common assumptions of strong geographic bias, the model exhibits a relatively uniform level of geographically grounded visual knowledge across regions, development levels, and cultural groupings, with only weak dependence on attraction popularity. These results suggest that current text-to-video models express global visual knowledge more evenly than expected, highlighting both their promise for globally deployed applications and the need for continued evaluation as such systems evolve.

---

### Explainability Methods for Hardware Trojan Detection: A Systematic Comparison

Authors: Paul Whitten, Francis Wolff, Chris Papachristou
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18696v7

Hardware trojans are malicious circuits which compromise the functionality and security of an integrated circuit (IC). These circuits are manufactured directly into the silicon and cannot be fixed by security patches like software. The solution would require a costly product recall by replacing the IC and hence, early detection in the design process is essential. Hardware detection at best provides statistically based solutions with many false positives and false negatives. These detection methods require more thorough explainable analysis to filter out false indicators. Existing explainability methods developed for general domains like image classification do not always provide the actionable insights hardware engineers need. A question remains: how do domain-aware property analysis, model-agnostic case-based reasoning, and model-agnostic feature attribution techniques compare for hardware security applications? This work compares three categories of explainability for gate-level hardware trojan detection on the Trust-Hub benchmark dataset: (1) domain-aware property-based analysis of 31 circuit-specific features derived from gate fanin patterns, flip-flop distances, and primary Input/Output (I/O) connectivity; (2) model-agnostic case-based reasoning using k-nearest neighbors for precedent-based explanations; and (3) model-agnostic feature attribution methods (Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), gradient) that provide generic importance scores without circuit-level context.

---

### Neural Multi-Speaker Voice Cloning for Nepali in Low-Resource Settings

Authors: Aayush M. Shrestha, Aditya Bajracharya, Projan Shakya, Dinesh B. Kshatri
Published: 2026-01-26
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.18694v1

This research presents a few-shot voice cloning system for Nepali speakers, designed to synthesize speech in a specific speaker's voice from Devanagari text using minimal data. Voice cloning in Nepali remains largely unexplored due to its low-resource nature. To address this, we constructed separate datasets: untranscribed audio for training a speaker encoder and paired text-audio data for training a Tacotron2-based synthesizer. The speaker encoder, optimized with Generative End2End loss, generates embeddings that capture the speaker's vocal identity, validated through Uniform Manifold Approximation and Projection (UMAP) for dimension reduction visualizations. These embeddings are fused with Tacotron2's text embeddings to produce mel-spectrograms, which are then converted into audio using a WaveRNN vocoder. Audio data were collected from various sources, including self-recordings, and underwent thorough preprocessing for quality and alignment. Training was performed using mel and gate loss functions under multiple hyperparameter settings. The system effectively clones speaker characteristics even for unseen voices, demonstrating the feasibility of few-shot voice cloning for the Nepali language and establishing a foundation for personalized speech synthesis in low-resource scenarios.

---

### A Pragmatic VLA Foundation Model

Authors: Wei Wu, Fan Lu, Yunnan Wang, Shuai Yang, Shi Liu, Fangjing Wang, Qian Zhu, He Sun, Yong Wang, Shuailei Ma, Yiyu Ren, Kejia Zhang et al.
Published: 2026-01-26
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2601.18692v4

Offering great potential in robotic manipulation, a capable Vision-Language-Action (VLA) foundation model is expected to faithfully generalize across tasks and platforms while ensuring cost efficiency (e.g., data and GPU hours required for adaptation). To this end, we develop LingBot-VLA with around 20,000 hours of real-world data from 9 popular dual-arm robot configurations. Through a systematic assessment on 4 robotic platforms, each completing 100 tasks with 130 post-training episodes per task, our model achieves clear superiority over competitors, showcasing its strong performance and broad generalizability. We have also built an efficient codebase, which delivers a throughput of 261 samples per second with an 8-GPU training setup, representing a 1.5~2.8$\times$ (depending on the relied VLM base model) speedup over existing VLA-oriented codebases. The above features ensure that our model is well-suited for real-world deployment. To advance the field of robot learning, we provide open access to the code, base model, and benchmark data, with a focus on enabling more challenging tasks and promoting sound evaluation standards.

---

### LLAMA LIMA: A Living Meta-Analysis on the Effects of Generative AI on Learning Mathematics

Authors: Anselm Strohmaier, Samira Bödefeld, Oliver Straser, Frank Reinhold
Published: 2026-01-26
Categories: math.HO, cs.LG
arXiv: https://arxiv.org/abs/2601.18685v5

The capabilities of generative AI in mathematics education are rapidly evolving, posing significant challenges for research to keep pace. Research syntheses remain scarce and risk being outdated by the time of publication. We present a Living Meta-Analysis (LIMA) on the effects of generative AI-based interventions for learning mathematics. We update the literature base every two months and apply a cumulative Bayesian multilevel meta-regression model. This paper reports results from the fifth version, including 34 studies, 7 of which were newly included since the fourth version. Results indicate an increasingly positive effect (g = 0.57, CrI (0.36, 0.79)) and no evidence in favor of a publication bias. Moderator analyses indicate that effects vary by integration mode and intervention duration: Larger effects were observed when generative AI supplemented teacher instruction and in longer interventions. Moderate evidence for stronger effects was observed in studies involving younger learners and more recent technology. For other moderators, evidence is still inconclusive.

---

### Learned harmonic mean estimation of the marginal likelihood for multimodal posteriors with flow matching

Authors: Alicja Polanska, Jason D. McEwen
Published: 2026-01-26
Categories: stat.ME, astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2601.18683v1

The marginal likelihood, or Bayesian evidence, is a crucial quantity for Bayesian model comparison but its computation can be challenging for complex models, even in parameters space of moderate dimension. The learned harmonic mean estimator has been shown to provide accurate and robust estimates of the marginal likelihood simply using posterior samples. It is agnostic to the sampling strategy, meaning that the samples can be obtained using any method. This enables marginal likelihood calculation and model comparison with whatever sampling is most suitable for the task. However, the internal density estimators considered previously for the learned harmonic mean can struggle with highly multimodal posteriors. In this work we introduce flow matching-based continuous normalizing flows as a powerful architecture for the internal density estimation of the learned harmonic mean. We demonstrate the ability to handle challenging multimodal posteriors, including an example in 20 parameter dimensions, showcasing the method's ability to handle complex posteriors without the need for fine-tuning or heuristic modifications to the base distribution.

---

### ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule

Authors: Yilie Huang, Wenpin Tang, Xunyu Zhou
Published: 2026-01-26
Categories: cs.LG, cs.AI, eess.SY, math.OC
arXiv: https://arxiv.org/abs/2601.18681v2

We consider time discretization for score-based diffusion models to generate samples from a learned reverse-time dynamic on a finite grid. Uniform and hand-crafted grids can be suboptimal given a budget on the number of time steps. We introduce Adaptive Reparameterized Time (ART), which controls the clock speed of a reparameterized time variable to redistribute computation along the sampling trajectory while preserving the terminal time, with the objective of minimizing the aggregate Euler discretization error. We derive a randomized companion ART-RL that recasts ART as a continuous-time reinforcement learning problem with Gaussian policies, and prove a two-directional bridge between the two: the deterministic ART optimum lifts to an optimal Gaussian policy, and conversely any optimal Gaussian policy must recover the ART control through its mean. This bridge turns continuous-time actor--critic learning into a principled, rather than heuristic, route to the deterministic timestep optimum. Within the official EDM pipeline, ART-RL improves FID on CIFAR--10 across a wide range of budgets; after one-time offline training, the distilled deterministic schedule transfers without retraining to AFHQv2, FFHQ, and ImageNet at no extra inference cost.

---

### Counterfactual Explanations on Robust Perceptual Geodesics

Authors: Eslam Zaher, Maciej Trzaskowski, Quan Nguyen, Fred Roosta
Published: 2026-01-26
Categories: cs.LG, cs.CV, cs.HC, math.DG
arXiv: https://arxiv.org/abs/2601.18678v2

Latent-space optimization methods for counterfactual explanations - framed as minimal semantic perturbations that change model predictions - inherit the ambiguity of Wachter et al.'s objective: the choice of distance metric dictates whether perturbations are meaningful or adversarial. Existing approaches adopt flat or misaligned geometries, leading to off-manifold artifacts, semantic drift, or adversarial collapse. We introduce Perceptual Counterfactual Geodesics (PCG), a method that constructs counterfactuals by tracing geodesics under a perceptually Riemannian metric induced from robust vision features. This geometry aligns with human perception and penalizes brittle directions, enabling smooth, on-manifold, semantically valid transitions. Experiments on three vision datasets show that PCG outperforms baselines and reveals failure modes hidden under standard metrics.

---