# Research Papers — 2026-01 · bundle page 18 of 189

> Full-text markdown of papers #851–900 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/18
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/17.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/19.md)

### RulePlanner: All-in-One Reinforcement Learner for Unifying Design Rules in 3D Floorplanning

Authors: Ruizhe Zhong, Xingbo Du, Junchi Yan
Published: 2026-01-30
Categories: cs.AR, cs.AI
arXiv: https://arxiv.org/abs/2601.22476v2

Floorplanning determines the coordinate and shape of each module in Integrated Circuits. With the scaling of technology nodes, in floorplanning stage especially 3D scenarios with multiple stacked layers, it has become increasingly challenging to adhere to complex hardware design rules. Current methods are only capable of handling specific and limited design rules, while violations of other rules require manual and meticulous adjustment. This leads to labor-intensive and time-consuming post-processing for expert engineers. In this paper, we propose an all-in-one deep reinforcement learning-based approach to tackle these challenges, and design novel representations for real-world IC design rules that have not been addressed by previous approaches. Specifically, the processing of various hardware design rules is unified into a single framework with three key components: 1) novel matrix representations to model the design rules, 2) constraints on the action space to filter out invalid actions that cause rule violations, and 3) quantitative analysis of constraint satisfaction as reward signals. Experiments on public benchmarks demonstrate the effectiveness and validity of our approach. Furthermore, transferability is well demonstrated on unseen circuits. Our framework is extensible to accommodate new design rules, thus providing flexibility to address emerging challenges in future chip design. Code will be available at: https://github.com/Thinklab-SJTU/EDA-AI

---

### Continual Policy Consolidation for Lifelong Robot Learning

Authors: Qijun He, Yuxuan Li, Mingqi Yuan, Xiaoquan Sun, Wen-Tse Chen, Jeff Schneider, Jiayu Chen
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22475v2

Building a generalist robot policy requires continuously integrating new skills while preserving previously acquired behaviors. Directly optimizing a single policy over a growing task stream is difficult because robotic interaction is expensive, task distributions are heterogeneous, and sequential updates induce interference. To address these problems, we propose continual policy consolidation (CPC), a teacher--student framework that combines continual policy distillation with prioritized experience replay and expandable experts. This architecture separates skill acquisition from policy consolidation: teachers are trained independently through reinforcement learning, and their behaviors are continually distilled into a central generalist student. This decomposition retains the practical strength of reinforcement learning for task-specialized training while casting student-side consolidation as a supervised policy-learning problem. To balance stability and plasticity as the task stream grows, the student combines an expandable Transformer-based mixture-of-experts architecture with prioritized trajectory replay. Extensive experiments show that the student recovers a large proportion of teacher performance while achieving near-zero forgetting. These results demonstrate a scalable route for consolidating independently acquired robot skills into a continually growing generalist policy.

---

### Unrewarded Exploration in Large Language Models Reveals Latent Learning from Psychology

Authors: Jian Xiong, Jingbo Zhou, Zihan Zhou, Yixiong Xiao, Le Zhang, Jingyong Ye, Rui Qian, Yang Zhou, Dejing Dou
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22474v1

Latent learning, classically theorized by Tolman, shows that biological agents (e.g., rats) can acquire internal representations of their environment without rewards, enabling rapid adaptation once rewards are introduced. In contrast, from a cognitive science perspective, reward learning remains overly dependent on external feedback, limiting flexibility and generalization. Although recent advances in the reasoning capabilities of large language models (LLMs), such as OpenAI-o1 and DeepSeek-R1, mark a significant breakthrough, these models still rely primarily on reward-centric reinforcement learning paradigms. Whether and how the well-established phenomenon of latent learning in psychology can inform or emerge within LLMs' training remains largely unexplored. In this work, we present novel findings from our experiments that LLMs also exhibit the latent learning dynamics. During an initial phase of unrewarded exploration, LLMs display modest performance improvements, as this phase allows LLMs to organize task-relevant knowledge without being constrained by reward-driven biases, and performance is further enhanced once rewards are introduced. LLMs post-trained under this two-stage exploration regime ultimately achieve higher competence than those post-trained with reward-based reinforcement learning throughout. Beyond these empirical observations, we also provide theoretical analyses for our experiments explaining why unrewarded exploration yields performance gains, offering a mechanistic account of these dynamics. Specifically, we conducted extensive experiments across multiple model families and diverse task domains to establish the existence of the latent learning dynamics in LLMs.

---

### Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector

Authors: Wenqiang Zu, Shenghao Xie, Bo Lei, Lei Ma
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22468v1

Recent progress in generative modeling has enabled high-quality visual synthesis with diffusion-based frameworks, supporting controllable sampling and large-scale training. Inference-time guidance methods such as classifier-free and representative guidance enhance semantic alignment by modifying sampling dynamics; however, they do not fully exploit unsupervised feature representations. Although such visual representations contain rich semantic structure, their integration during generation is constrained by the absence of ground-truth reference images at inference. This work reveals semantic drift in the early denoising stages of diffusion transformers, where stochasticity results in inconsistent alignment even under identical conditioning. To mitigate this issue, we introduce a guidance scheme using a representation alignment projector that injects representations predicted by a projector into intermediate sampling steps, providing an effective semantic anchor without modifying the model architecture. Experiments on SiTs and REPAs show notable improvements in class-conditional ImageNet synthesis, achieving substantially lower FID scores; for example, REPA-XL/2 improves from 5.9 to 3.3, and the proposed method outperforms representative guidance when applied to SiT models. The approach further yields complementary gains when combined with classifier-free guidance, demonstrating enhanced semantic coherence and visual fidelity. These results establish representation-informed diffusion sampling as a practical strategy for reinforcing semantic preservation and image consistency.

---

### CARE: Multi-Task Pretraining for Latent Continuous Action Representation in Robot Control

Authors: Jiaqi Shi, Xulong Zhang, Xiaoyang Qu, Jianzong Wang
Published: 2026-01-30
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2601.22467v1

Recent advances in Vision-Language-Action (VLA) models have shown promise for robot control, but their dependence on action supervision limits scalability and generalization. To address this challenge, we introduce CARE, a novel framework designed to train VLA models for robotic task execution. Unlike existing methods that depend on action annotations during pretraining, CARE eliminates the need for explicit action labels by leveraging only video-text pairs. These weakly aligned data sources enable the model to learn continuous latent action representations through a newly designed multi-task pretraining objective. During fine-tuning, a small set of labeled data is used to train the action head for control. Experimental results across various simulation tasks demonstrate CARE's superior success rate, semantic interpretability, and ability to avoid shortcut learning. These results underscore CARE's scalability, interpretability, and effectiveness in robotic control with weak supervision.

---

### EvoEGF-Mol: Evolving Exponential Geodesic Flow for Structure-based Drug Design

Authors: Yaowei Jin, Junjie Wang, Cheng Cao, Penglei Wang, Duo An, Qian Shi
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22466v2

Structure-Based Drug Design (SBDD) aims to discover bioactive ligands. Conventional approaches construct probability paths separately in Euclidean and probabilistic spaces for continuous atomic coordinates and discrete chemical categories, leading to a mismatch with the underlying statistical manifolds. We address this issue by representing molecules using composite exponential-family distributions, where coordinates and categories are represented within a unified natural parameter space to evolve synchronously along exponential geodesics under the Fisher-Rao metric. To avoid the instantaneous trajectory collapse induced by geodesics directly targeting Dirac distributions, we propose Evolving Exponential Geodesic Flow for SBDD (EvoEGF-Mol), which replaces static Dirac targets with dynamically concentrating distributions and is trained with a progressive-parameter-refinement architecture. Our model approaches a reference-level PoseBusters passing rate (93.4%) on CrossDock, demonstrating remarkable geometric precision and interaction fidelity, while achieving superior performance over baseline methods on real-world MolGenBench tasks for bioactive scaffold recovery. Code is available at https://github.com/BLEACH366/EvoEGF-Mol.

---

### Toward Non-Expert Customized Congestion Control: Large Language Model-Assisted CCA Code Generation with eBPF Deployment

Authors: Mingrui Zhang, Hamid Bagheri, Lisong Xu
Published: 2026-01-30
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2601.22461v2

General-purpose congestion control algorithms (CCAs) are designed to achieve general congestion control goals, but they may not meet the specific requirements of certain users. Customized CCAs can meet certain users' specific requirements; however, non-expert users often lack the expertise to implement them. In this paper, we present an exploratory non-expert customized CCA framework, named NECC, which enables non-expert users to easily model, implement, and deploy their customized CCAs by leveraging Large Language Models and the Berkeley Packet Filter (BPF) interface. To the best of our knowledge, we are the first to address the customized CCA implementation problem. Our evaluations using real-world CCAs show that the performance of NECC is very promising, and we discuss the insights that we find and possible future research directions.

---

### AI Decodes Historical Chinese Archives to Reveal Lost Climate History

Authors: Sida He, Lingxi Xie, Xiaopeng Zhang, Qi Tian
Published: 2026-01-30
Categories: physics.ao-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.22458v1

Historical archives contain qualitative descriptions of climate events, yet converting these into quantitative records has remained a fundamental challenge. Here we introduce a paradigm shift: a generative AI framework that inverts the logic of historical chroniclers by inferring the quantitative climate patterns associated with documented events. Applied to historical Chinese archives, it produces the sub-annual precipitation reconstruction for southeastern China over the period 1368-1911 AD. Our reconstruction not only quantifies iconic extremes like the Ming Dynasty's Great Drought but also, crucially, maps the full spatial and seasonal structure of El Ni$ñ$o influence on precipitation in this region over five centuries, revealing dynamics inaccessible in shorter modern records. Our methodology and high-resolution climate dataset are directly applicable to climate science and have broader implications for the historical and social sciences.

---

### Machine Unlearning in Low-Dimensional Feature Subspace

Authors: Kun Fang, Qinghua Tao, Junxu Liu, Yaxin Xiao, Qingqing Ye, Jian Sun, Haibo Hu
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22456v1

Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspective for MU is presented upon low-dimensional feature subspaces, which gives rise to the potentials of separating the remaining and forgetting data herein. This separability motivates our LOFT, a method that proceeds unlearning in a LOw-dimensional FeaTure subspace from the pretrained model skithrough principal projections, which are optimized to maximally capture the information of the remaining data and meanwhile diminish that of the forgetting data. In training, LOFT simply optimizes a small-size projection matrix flexibly plugged into the pretrained model, and only requires one-shot feature fetching from the pretrained backbone instead of repetitively accessing the raw data. Hence, LOFT mitigates two critical issues in mainstream MU methods, i.e., the privacy leakage risk from massive data reload and the inefficiency of updates to the entire pretrained model. Extensive experiments validate the significantly lower computational overhead and superior unlearning performance of LOFT across diverse models, datasets, tasks, and applications. Code is anonymously available at https://anonymous.4open.science/r/4352/.

---

### ScribbleSense: Generative Scribble-Based Texture Editing with Intent Prediction

Authors: Yudi Zhang, Yeming Geng, Lei Zhang
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22455v1

Interactive 3D model texture editing presents enhanced opportunities for creating 3D assets, with freehand drawing style offering the most intuitive experience. However, existing methods primarily support sketch-based interactions for outlining, while the utilization of coarse-grained scribble-based interaction remains limited. Furthermore, current methodologies often encounter challenges due to the abstract nature of scribble instructions, which can result in ambiguous editing intentions and unclear target semantic locations. To address these issues, we propose ScribbleSense, an editing method that combines multimodal large language models (MLLMs) and image generation models to effectively resolve these challenges. We leverage the visual capabilities of MLLMs to predict the editing intent behind the scribbles. Once the semantic intent of the scribble is discerned, we employ globally generated images to extract local texture details, thereby anchoring local semantics and alleviating ambiguities concerning the target semantic locations. Experimental results indicate that our method effectively leverages the strengths of MLLMs, achieving state-of-the-art interactive editing performance for scribble-based texture editing.

---

### Temporal Graph Pattern Machine

Authors: Yijun Ma, Zehong Wang, Weixiang Sun, Yanfang Ye
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2601.22454v3

Temporal graph learning is pivotal for deciphering dynamic systems, where the core challenge lies in explicitly modeling the underlying evolving patterns that govern network transformation. However, prevailing methods are predominantly task-centric and rely on restrictive assumptions -- such as short-term dependency modeling, static neighborhood semantics, and retrospective time usage. These constraints hinder the discovery of transferable temporal evolution mechanisms. To address this, we propose the Temporal Graph Pattern Machine (TGPM), a foundation framework that shifts the focus toward directly learning generalized evolving patterns. TGPM conceptualizes each interaction as an interaction patch synthesized via temporally-biased random walks, thereby capturing multi-scale structural semantics and long-range dependencies that extend beyond immediate neighborhoods. These patches are processed by a Transformer-based backbone designed to capture global temporal regularities while adapting to context-specific interaction dynamics. To further empower the model, we introduce a suite of self-supervised pre-training tasks -- specifically masked token modeling and next-time prediction -- to explicitly encode the fundamental laws of network evolution. Extensive experiments on temporal link prediction and temporal node classification show that TGPM consistently ranks among the top-performing methods, demonstrating exceptional cross-domain transferability. Our code has been released in https://github.com/antman9914/TGPM.

---

### Does My Chatbot Have an Agenda? Understanding Human and AI Agency in Human-Human-like Chatbot Interaction

Authors: Bhada Yun, Evgenia Taranova, April Yi Wang
Published: 2026-01-30
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2601.22452v2

As AI chatbots shift from tools to companions, critical questions arise: who controls the conversation in human-AI chatrooms? This paper explores perceived human and AI agency in sustained conversation. We report a month-long longitudinal study with 22 adults who chatted with Day, an LLM companion we built, followed by a semi-structured interview with post-hoc elicitation of notable moments, cross-participant chat reviews, and a 'strategy reveal' disclosing Day's goal for each conversation. We discover agency manifests as an emergent, shared experience: as participants set boundaries and the AI steered intentions, control was co-constructed turn-by-turn. We introduce a 3-by-4 framework mapping actors (Human, AI, Hybrid) by their action (Intention, Execution, Adaptation, Delimitation), modulated by individual and environmental factors. We argue for translucent design (transparency-on-demand) and provide implications for agency self-aware conversational agents.

---

### Countering the Over-Reliance Trap: Mitigating Object Hallucination for LVLMs via a Self-Validation Framework

Authors: Shiyu Liu, Xinyi Wen, Zhibin Lan, Ante Wang, Jinsong Su
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22451v2

Despite progress in Large Vision Language Models (LVLMs), object hallucination remains a critical issue in image captioning task, where models generate descriptions of non-existent objects, compromising their reliability. Previous work attributes this to LVLMs' over-reliance on language priors and attempts to mitigate it through logits calibration. However, they still lack a thorough analysis of the over-reliance. To gain a deeper understanding of over-reliance, we conduct a series of preliminary experiments, indicating that as the generation length increases, LVLMs' over-reliance on language priors leads to inflated probability of hallucinated object tokens, consequently exacerbating object hallucination. To circumvent this issue, we propose Language-Prior-Free Verification to enable LVLMs to faithfully verify the confidence of object existence. Based on this, we propose a novel training-free Self-Validation Framework to counter the over-reliance trap. It first validates objects' existence in sampled candidate captions and further mitigates object hallucination via caption selection or aggregation. Experiment results demonstrate that our framework mitigates object hallucination significantly in image captioning task (e.g., 65.6% improvement on CHAIRI metric with LLaVA-v1.5-7B), surpassing the previous SOTA methods. This result highlights a novel path towards mitigating hallucination by unlocking the inherent potential within LVLMs themselves.

---

### Tuning the Implicit Regularizer of Masked Diffusion Language Models: Enhancing Generalization via Insights from $k$-Parity

Authors: Jianhao Huang, Baharan Mirzasoleiman
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22450v2

Masked Diffusion Language Models have recently emerged as a powerful generative paradigm, yet their generalization properties remain understudied compared to their auto-regressive counterparts. In this work, we investigate these properties within the setting of the $k$-parity problem (computing the XOR sum of $k$ relevant bits), where neural networks typically exhibit grokking -- a prolonged plateau of chance-level performance followed by sudden generalization. We theoretically decompose the Masked Diffusion (MD) objective into a Signal regime which drives feature learning, and a Noise regime which serves as an implicit regularizer. By training nanoGPT using MD objective on the $k$-parity problem, we demonstrate that MD objective fundamentally alters the learning landscape, enabling rapid and simultaneous generalization without experiencing grokking. Furthermore, we leverage our theoretical insights to optimize the distribution of the mask probability in the MD objective. Our method significantly improves perplexity for 50M-parameter models and achieves superior results across both pre-training from scratch and supervised fine-tuning. Specifically, we observe performance gains peaking at $8.8\%$ and $5.8\%$, respectively, on 8B-parameter models, confirming the scalability and effectiveness of our framework in large-scale masked diffusion language model regimes.

---

### Emergence of Physical Intelligence via Controllable Information Production

Authors: Tristan Shah, Stas Tiomkin
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22449v2

Intrinsic Motivation (IM) aims to train agents without external rewards, enabling useful behavior to emerge from the agent's interaction with its environment alone. However, the dominant IM approaches rely on information-theoretic quantities with designer-chosen variables, introducing bias and lacking a principled connection to dynamics or optimal control (OC). We introduce Controllable Information Production (CIP), a new foundation for IM explicitly grounded in dynamical systems and OC. CIP measures the rate at which an agent produces information, capturing controllable complexity without external knowledge or bias. CIP unifies IM and OC into a single framework, formalizing physical intelligence as the control of information production. It further reveals connections between the structure of the value function and Kolmogorov-Sinai entropy. CIP consistently outperforms prior IM methods on standard benchmarks in robot learning and solves tasks they fail on, including humanoid self-righting. These results support a general organizing principle: physical intelligence emerges from driving systems toward the edge of controllable chaos.

---

### HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

Authors: Weiqi Wang, Xin Liu, Binxuan Huang, Hejie Cui, Rongzhi Zhang, Changlong Yu, Shuowei Jin, Jingfeng Yang, Qingyu Yin, Zhengyang Wang, Zheng Li, Yifan Gao et al.
Published: 2026-01-30
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2601.22448v2

RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when. In practice, prompt pools are often static or only weakly coupled to policy progress, so uniform sampling fails to track the moving capability frontier and wastes rollouts on regions that are already solved or still unreachable. Prior methods improve efficiency via filtering, curricula, adaptive rollout allocation, or teacher guidance, but they often assume a fixed pool, which does not support stable on-policy pool growth, or they introduce additional teacher cost and latency. In this work, we propose HeaPA (Heap Sampling and On-Policy Query Augmentation), which maintains a bounded, evolving pool, tracks the frontier with heap-based boundary sampling, grows the pool via on-policy augmentation under lightweight asynchronous validation, and stabilizes correlated queries via topology-aware pool statistics re-estimation and controlled reinsertion. Across two training corpora, two training recipes, and seven benchmarks, HeaPA consistently improves accuracy and reaches target performance with fewer computations at comparable wall-clock time. Analyses attribute the gains to frontier-focused sampling and on-policy pool growth, with more pronounced improvements at mid-to-large model scales. Our training code is publicly available at https://github.com/horizon-llm/HeaPA.

---

### Beyond Activation Patterns: A Weight-Based Out-of-Context Explanation of Sparse Autoencoder Features

Authors: Yiting Liu, Zhi-Hong Deng
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22447v1

Sparse autoencoders (SAEs) have emerged as a powerful technique for decomposing language model representations into interpretable features. Current interpretation methods infer feature semantics from activation patterns, but overlook that features are trained to reconstruct activations that serve computational roles in the forward pass. We introduce a novel weight-based interpretation framework that measures functional effects through direct weight interactions, requiring no activation data. Through three experiments on Gemma-2 and Llama-3.1 models, we demonstrate that (1) 1/4 of features directly predict output tokens, (2) features actively participate in attention mechanisms with depth-dependent structure, and (3) semantic and non-semantic feature populations exhibit distinct distribution profiles in attention circuits. Our analysis provides the missing out-of-context half of SAE feature interpretability.

---

### Anytime Safe PAC Efficient Reasoning

Authors: Chengyao Yu, Hao Zeng, Youxin Zhu, Jianguo Huang, Huajun Zeng, Bingyi Jing
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22446v2

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks but suffer from high computational costs and latency. While selective thinking strategies improve efficiency by routing easy queries to non-thinking models, existing approaches often incur uncontrollable errors, especially in online settings where the performance loss of a non-thinking model is only partially observed and data are non-stationary. To address this, we propose Betting Probably Approximately Correct (B-PAC) reasoning, a principled method that enables anytime safe and efficient online reasoning under partial feedback. Specifically, we utilize inverse propensity scoring estimators to construct test supermartingales for candidate thresholds, and then dynamically adjust the routing threshold based on the accumulated statistical evidence of safety. Theoretically, we establish the anytime-valid performance loss control and the efficiency of B-PAC reasoning. Extensive experiments demonstrate that B-PAC reasoning significantly reduces computational overhead, decreasing thinking model usage by up to 81.01\%, while controlling the performance loss below the user-specified level.

---

### High-Definition 5MP Stereo Vision Sensing for Robotics

Authors: Leaf Jiang, Matthew Holzel, Bernhard Kaplan, Hsiou-Yuan Liu, Sabyasachi Paul, Karen Rankin, Piotr Swierczynski
Published: 2026-01-30
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2601.22445v1

High-resolution (5MP+) stereo vision systems are essential for advancing robotic capabilities, enabling operation over longer ranges and generating significantly denser and accurate 3D point clouds. However, realizing the full potential of high-angular-resolution sensors requires a commensurately higher level of calibration accuracy and faster processing -- requirements often unmet by conventional methods. This study addresses that critical gap by processing 5MP camera imagery using a novel, advanced frame-to-frame calibration and stereo matching methodology designed to achieve both high accuracy and speed. Furthermore, we introduce a new approach to evaluate real-time performance by comparing real-time disparity maps with ground-truth disparity maps derived from more computationally intensive stereo matching algorithms. Crucially, the research demonstrates that high-pixel-count cameras yield high-quality point clouds only through the implementation of high-accuracy calibration.

---

### Automating Forecasting Question Generation and Resolution for AI Evaluation

Authors: Nikos I. Bosse, Peter Mühlbacher, Jack Wildman, Lawrence Phillips, Dan Schwarz
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22444v2

Forecasting future events is highly valuable in decision-making and is a robust measure of general intelligence. As forecasting is probabilistic, developing and evaluating AI forecasters requires generating large numbers of diverse and difficult questions, and accurately resolving them. Previous efforts to automate this laborious work relied on recurring data sources (e.g., weather, stocks), limiting diversity and utility. In this work, we present a system for generating and resolving high-quality forecasting questions automatically and at scale using LLM-powered web research agents. We use this system to generate 1499 diverse, real-world forecasting questions, and to resolve them several months later. We estimate that our system produces verifiable, unambiguous questions approximately 96% of the time, exceeding the rate of Metaculus, a leading human-curated forecasting platform. We also find that our system resolves questions at approximately 95% accuracy. We verify that forecasting agents powered by more intelligent LLMs perform better on these questions (Brier score of 0.134 for Gemini 3 Pro, 0.149 for GPT-5, and 0.179 for Gemini 2.5 Flash). Finally, we demonstrate how our system can be leveraged to directly improve forecasting, by evaluating a question decomposition strategy on a generated question set, yielding a significant improvement in Brier scores (0.132 vs. 0.141).

---

### Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance

Authors: Jing Jia, Wei Yuan, Sifan Liu, Liyue Shen, Guanyang Wang
Published: 2026-01-30
Categories: cs.LG, cs.CV, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2601.22443v2

Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard approaches usually assume a high-fidelity model trained on data that closely match the unknown signal. In practice, one often must use a mismatched or low-fidelity diffusion prior. Surprisingly, these weak priors often perform nearly as well as full-strength, in-domain baselines. We study when and why inverse solvers are robust to weak diffusion priors. Through extensive experiments, we find that weak priors succeed when measurements are highly informative (e.g., many observed pixels), and we identify regimes where they fail. To explain this behavior, we combine Bayesian-consistency theory with local-correlation analysis: the theory gives conditions under which high-dimensional measurements make the posterior concentrate near the true signal, while the correlation analysis shows that weak and stronger natural-image priors can share similar local spatial structure. These results provide a principled justification on when weak diffusion priors can be used reliably. Code is available at https://github.com/jjia131/weak-diffusion-priors-inverse-problem.

---

### AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism

Authors: Thalaiyasingam Ajanthan, Sameera Ramasinghe, Gil Avraham, Hadi Mohaghegh Dolatabadi, Chamin P Hewa Koneputugodage, Violetta Shevchenko, Yan Zuo, Alexander Long
Published: 2026-01-30
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2601.22442v1

Data and pipeline parallelism are key strategies for scaling neural network training across distributed devices, but their high communication cost necessitates co-located computing clusters with fast interconnects, limiting their scalability. We address this communication bottleneck by introducing asynchronous updates across both parallelism axes, relaxing the co-location requirement at the expense of introducing staleness between pipeline stages and data parallel replicas. To mitigate staleness, for pipeline parallelism, we adopt a weight look-ahead approach, and for data parallelism, we introduce an asynchronous sparse averaging method equipped with an exponential moving average based correction mechanism. We provide convergence guarantees for both sparse averaging and asynchronous updates. Experiments on large-scale language models (up to \em 1B parameters) demonstrate that our approach matches the performance of the fully synchronous baseline, while significantly reducing communication overhead.

---

### Simulation-based Bayesian inference with ameliorative learned summary statistics -- Part I

Authors: Getachew K. Befekadu
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.22441v1

This paper, which is Part 1 of a two-part paper series, considers a simulation-based inference with learned summary statistics, in which such a learned summary statistic serves as an empirical-likelihood with ameliorative effects in the Bayesian setting, when the exact likelihood function associated with the observation data and the simulation model is difficult to obtain in a closed form or computationally intractable. In particular, a transformation technique which leverages the Cressie-Read discrepancy criterion under moment restrictions is used for summarizing the learned statistics between the observation data and the simulation outputs, while preserving the statistical power of the inference. Here, such a transformation of data-to-learned summary statistics also allows the simulation outputs to be conditioned on the observation data, so that the inference task can be performed over certain sample sets of the observation data that are considered as an empirical relevance or believed to be particular importance. Moreover, the simulation-based inference framework discussed in this paper can be extended further, and thus handling weakly dependent observation data. Finally, we remark that such an inference framework is suitable for implementation in distributed computing, i.e., computational tasks involving both the data-to-learned summary statistics and the Bayesian inferencing problem can be posed as a unified distributed inference problem that will exploit distributed optimization and MCMC algorithms for supporting large datasets associated with complex simulation models.

---

### AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations

Authors: Bhada Yun, Renn Su, April Yi Wang
Published: 2026-01-30
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.22440v2

Does AI understand human values? While this remains an open philosophical question, we take a pragmatic stance by introducing VAPT, the Value-Alignment Perception Toolkit, for studying how LLMs reflect people's values and how people judge those reflections. 20 participants texted a chatbot over a month, then completed a 2-hour interview with our toolkit evaluating AI's ability to extract (pull details regarding), embody (make decisions guided by), and explain (provide proof of) their values. 13 participants ultimately left our study convinced that AI can understand human values. Thus, we warn about "weaponized empathy": a design pattern that may arise in interactions with value-aware, yet welfare-misaligned conversational agents. VAPT offers a new way to evaluate value-alignment in AI systems. We also offer design implications to evaluate and responsibly build AI systems with transparency and safeguards as AI capabilities grow more inscrutable, ubiquitous, and posthuman into the future.

---

### Stop Jostling: Adaptive Negative Sampling Reduces the Marginalization of Low-Resource Language Tokens by Cross-Entropy Loss

Authors: Galim Turumtaev
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22439v1

Neural language models often struggle with low-resource languages due to the limited availability of training data, making tokens from these languages rare in the training set. This paper addresses a specific challenge during training: rare tokens are disproportionately affected by marginalization, which prevents them from learning effectively. We propose a thresholding technique that reduces the impact of this marginalization, allowing rare tokens to benefit from more meaningful alignment. Through experiments with a character-level language model, we demonstrate that this method significantly improves performance on low-resource language validation data. This work is the first to show how negative sampling can be applied to improve the representation of rare tokens by limiting the harmful influence of excessive marginalization, offering a new approach to enhancing language model performance for underrepresented languages.

---

### Towards Resiliency in Large Language Model Serving with KevlarFlow

Authors: Shangshu Qian, Kipling Liu, P. C. Sruthi, Lin Tan, Yongle Zhang
Published: 2026-01-30
Categories: cs.DC, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.22438v1

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively slow, often requiring up to 10 minutes to reinitialize resources and reload massive model weights. We introduce KevlarFlow, a fault tolerant serving architecture designed to bridge the gap between hardware unreliability and service availability. KevlarFlow leverages 1) decoupled model parallelism initialization, 2) dynamic traffic rerouting, and 3) background KV cache replication to maintain high throughput during partial failures. Our evaluation demonstrates that KevlarFlow reduces mean-time-to-recovery (MTTR) by 20x and, under failure conditions, improves average latency by 3.1x, 99th percentile (p99) latency by 2.8x, average time-to-first-token (TTFT) by 378.9x, and p99 TTFT by 574.6x with negligible runtime overhead in comparison to state-of-the-art LLM serving systems.

---

### Large Language Model Agents Are Not Always Faithful Self-Evolvers

Authors: Weixiang Zhao, Yingshuo Wang, Yichen Zhang, Yang Deng, Yanyan Zhao, Wanxiang Che, Bing Qin, Ting Liu
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22436v3

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic investigation of experience faithfulness, the causal dependence of an agent's decisions on the experience it is given, in self-evolving LLM agents. Using controlled causal interventions on both raw and condensed forms of experience, we comprehensively evaluate four representative frameworks across 13 LLM backbones and 9 environments. Our analysis uncovers a striking asymmetry: while agents consistently depend on raw experience, they often disregard or misinterpret condensed experience, even when it is the only experience provided. This gap persists across single- and multi-agent configurations and across backbone scales. We trace its underlying causes to three factors: the semantic limitations of condensed content, internal processing biases that suppress experience, and task regimes where pretrained priors already suffice. These findings challenge prevailing assumptions about self-evolving methods and underscore the need for more faithful and reliable approaches to experience integration.

---

### Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective

Authors: Georgi Ganev, Emiliano De Cristofaro
Published: 2026-01-30
Categories: cs.CR, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2601.22434v1

Training generative machine learning models to produce synthetic tabular data has become a popular approach for enhancing privacy in data sharing. As this typically involves processing sensitive personal information, releasing either the trained model or generated synthetic datasets can still pose privacy risks. Yet, recent research, commercial deployments, and privacy regulations like the General Data Protection Regulation (GDPR) largely assess anonymity at the level of an individual dataset. In this paper, we rethink anonymity claims about synthetic data from a model-centric perspective and argue that meaningful assessments must account for the capabilities and properties of the underlying generative model and be grounded in state-of-the-art privacy attacks. This perspective better reflects real-world products and deployments, where trained models are often readily accessible for interaction or querying. We interpret the GDPR's definitions of personal data and anonymization under such access assumptions to identify the types of identifiability risks that must be mitigated and map them to privacy attacks across different threat settings. We then argue that synthetic data techniques alone do not ensure sufficient anonymization. Finally, we compare the two mechanisms most commonly used alongside synthetic data -- Differential Privacy (DP) and Similarity-based Privacy Metrics (SBPMs) -- and argue that while DP can offer robust protections against identifiability risks, SBPMs lack adequate safeguards. Overall, our work connects regulatory notions of identifiability with model-centric privacy attacks, enabling more responsible and trustworthy regulatory assessment of synthetic data systems by researchers, practitioners, and policymakers.

---

### When LLM meets Fuzzy-TOPSIS for Personnel Selection through Automated Profile Analysis

Authors: Shahria Hoque, Ahmed Akib Jawad Karim, Md. Golam Rabiul Alam, Nirjhar Gope
Published: 2026-01-30
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2601.22433v1

In this highly competitive employment environment, the selection of suitable personnel is essential for organizational success. This study presents an automated personnel selection system that utilizes sophisticated natural language processing (NLP) methods to assess and rank software engineering applicants. A distinctive dataset was created by aggregating LinkedIn profiles that include essential features such as education, work experience, abilities, and self-introduction, further enhanced with expert assessments to function as standards. The research combines large language models (LLMs) with multicriteria decision-making (MCDM) theory to develop the LLM-TOPSIS framework. In this context, we utilized the TOPSIS method enhanced by fuzzy logic (Fuzzy TOPSIS) to address the intrinsic ambiguity and subjectivity in human assessments. We utilized triangular fuzzy numbers (TFNs) to describe criteria weights and scores, thereby addressing the ambiguity frequently encountered in candidate evaluations. For candidate ranking, the DistilRoBERTa model was fine-tuned and integrated with the fuzzy TOPSIS method, achieving rankings closely aligned with human expert evaluations and attaining an accuracy of up to 91% for the Experience attribute and the Overall attribute. The study underlines the potential of NLP-driven frameworks to improve recruitment procedures by boosting scalability, consistency, and minimizing prejudice. Future endeavors will concentrate on augmenting the dataset, enhancing model interpretability, and verifying the system in actual recruitment scenarios to better evaluate its practical applicability. This research highlights the intriguing potential of merging NLP with fuzzy decision-making methods in personnel selection, enabling scalable and unbiased solutions to recruitment difficulties.

---

### ReNCE: Learning to Reason by Noise Contrastive Estimation

Authors: Wenzheng Zhang, Karl Stratos
Published: 2026-01-30
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2601.22432v1

GRPO is a standard approach to endowing pretrained LLMs with reasoning capabilities. It estimates the advantage of an outcome from a group of $K$ outcomes, and promotes those with positive advantages inside a trust region. Since GRPO discriminates between good and bad outcomes softly, it benefits from additional refinements such as asymmetric clipping and zero-variance data filtering. While effective, these refinements require significant empirical insight and can be challenging to identify. We instead propose an explicit contrastive learning approach. Instead of estimating advantages, we bifurcate $K$ outcomes into positive and negative sets, then maximize the likelihood of positive outcomes. Our approach can be viewed as an online instantiation of (multi-label) noise contrastive estimation for LLM reasoning. We validate our method by demonstrating competitive performance on a suite of challenging math benchmarks against strong baselines such as DAPO and online DPO.

---

### CoDCL: Counterfactual-Inspired Augmentation Contrastive Learning for Temporal Link Prediction in Social Networks

Authors: Hantong Feng, Duxin Chen, Wenwu Yu
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22427v2

Temporal link prediction is crucial for rapidly growing social networks. Existing methods often overlook the underlying causal mechanisms that drive link formation, making it difficult for algorithms to adapt to complex structures that continuously evolve over time. To enable prediction models to adapt to complex temporal environments, they need to be robust to emerging structural changes. We propose a dynamic network learning framework CoDCL, which combines counterfactual-inspired augmentation with contrastive learning to address this deficiency. Furthermore, we devise a comprehensive strategy to generate high-quality counterfactual data, combining a dynamic treatments design with efficient structural neighborhood exploration to quantify the temporal changes in interaction patterns. Crucially, the entire CoDCL is designed as a plug-and-play universal module that can be seamlessly integrated into various existing temporal graph models without requiring architectural modifications. Extensive experiments conducted on multiple real-world datasets demonstrate that CoDCL significantly outperforms state-of-the-art baselines in temporal link prediction, highlighting the effectiveness of integrating counterfactual-inspired data augmentation into dynamic representation learning.

---

### MetaLead: A Comprehensive Human-Curated Leaderboard Dataset for Transparent Reporting of Machine Learning Experiments

Authors: Roelien C. Timmer, Necva Bölücü, Stephen Wan
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22420v1

Leaderboards are crucial in the machine learning (ML) domain for benchmarking and tracking progress. However, creating leaderboards traditionally demands significant manual effort. In recent years, efforts have been made to automate leaderboard generation, but existing datasets for this purpose are limited by capturing only the best results from each paper and limited metadata. We present MetaLead, a fully human-annotated ML Leaderboard dataset that captures all experimental results for result transparency and contains extra metadata, such as the result experimental type: baseline, proposed method, or variation of proposed method for experiment-type guided comparisons, and explicitly separates train and test dataset for cross-domain assessment. This enriched structure makes MetaLead a powerful resource for more transparent and nuanced evaluations across ML research.

---

### Dynamic Welfare-Maximizing Pooled Testing

Authors: Edwin Lock, Nicholas Lopez, Francisco Marmolejo-Cossío, Jose Roberto Tello Ayala, David C. Parkes
Published: 2026-01-30
Categories: cs.GT, cs.AI
arXiv: https://arxiv.org/abs/2601.22419v2

Pooled testing uses one test to certify several agents as healthy when the pooled result is negative. We study a budget-constrained welfare problem in which agents have heterogeneous utilities and independent prior probabilities of being healthy. Welfare is earned when an agent is certified healthy, and a dynamic policy may choose each pool after observing earlier test outcomes. We ask how much such adaptation can improve over a static allocation that fixes all pools in advance. Our main result proves that the optimal dynamic policy has value at most twice that of the optimal static overlapping allocation, for every population, test budget, and pool-size cap. The proof samples a path through the dynamic policy using an independent health profile, randomly thins the selected pools, and compares the resulting static allocation with the dynamic policy one agent at a time. A Boolean-cube argument proves the comparison on uniform subcubes, and a complementary-profile coupling lifts the result to arbitrary heterogeneous product priors. We also identify regimes in which adaptivity has no value, show that strict adaptive gains require re-pooling agents after positive tests, and give a three-agent instance in which adaptation is strictly beneficial. Exact-Joint Greedy obtains a $1/(e+1)$ fraction of optimal static overlapping welfare. The static non-overlapping Greedy algorithm of Finster et al. has the same guarantee, hence our factor-two theorem newly implies that each is a $2(e+1)$-approximation to the optimal dynamic policy. Finally, a reproducible exact small-instance study compares the dynamic and static benchmarks and greedy policies. The appendix records separate exploratory results for Gibbs-marginal and reinforcement-learning approaches at larger scales.

---

### AI-Enabled Waste Classification as a Data-Driven Decision Support Tool for Circular Economy and Urban Sustainability

Authors: Julius Sechang Mboli, Omolara Aderonke Ogungbemi
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22418v1

Efficient waste sorting is crucial for enabling circular-economy practices and resource recovery in smart cities. This paper evaluates both traditional machine-learning (Random Forest, SVM, AdaBoost) and deep-learning techniques including custom CNNs, VGG16, ResNet50, and three transfer-learning models (DenseNet121, EfficientNetB0, InceptionV3) for binary classification of 25 077 waste images (80/20 train/test split, augmented and resized to 150x150 px). The paper assesses the impact of Principal Component Analysis for dimensionality reduction on traditional models. DenseNet121 achieved the highest accuracy (91 %) and ROC-AUC (0.98), outperforming the best traditional classifier by 20 pp. Principal Component Analysis (PCA) showed negligible benefit for classical methods, whereas transfer learning substantially improved performance under limited-data conditions. Finally, we outline how these models integrate into a real-time Data-Driven Decision Support System for automated waste sorting, highlighting potential reductions in landfill use and lifecycle environmental impacts.)

---

### Structural Segmentation of the Minimum Set Cover Problem: Exploiting Universe Decomposability for Metaheuristic Optimization

Authors: Isidora Hernández, Héctor Ferrada, Cristóbal A. Navarro
Published: 2026-01-29
Categories: cs.AI, math.OC
arXiv: https://arxiv.org/abs/2604.03234v1

The Minimum Set Cover Problem (MSCP) is a classical NP-hard combinatorial optimization problem with numerous applications in science and engineering. Although a wide range of exact, approximate, and metaheuristic approaches have been proposed, most methods implicitly treat MSCP instances as monolithic, overlooking potential intrinsic structural properties of the universe. In this work, we investigate the concept of \emph{universe segmentability} in the MSCP and analyze how intrinsic structural decomposition (universe segmentability) can be exploited to enhance heuristic optimization. We propose an efficient preprocessing strategy based on disjoint-set union (union--find) to detect connected components induced by element co-occurrence within subsets, enabling the decomposition of the original instance into independent subproblems. Each subproblem is solved using the GRASP metaheuristic, and partial solutions are combined without compromising feasibility. Extensive experiments on standard benchmark instances and large-scale synthetic datasets show that exploiting natural universe segmentation consistently improves solution quality and scalability, particularly for large and structurally decomposable instances. These gains are supported by a succinct bit-level set representation that enables efficient set operations, making the proposed approach computationally practical at scale.

---

### Focus360: Guiding User Attention in Immersive Videos for VR

Authors: Paulo Vitor S. Silva, Lucas L. Neves, Rafael A. Goiás, Diogo F. C. Silva, Rafael T. Sousa, Arlindo R. Galvão Filho
Published: 2026-01-29
Categories: cs.HC, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2603.28774v1

This demo introduces Focus360, a system designed to enhance user engagement in 360° VR videos by guiding attention to key elements within the scene. Using natural language descriptions, the system identifies important elements and applies a combination of visual effects to guide attention seamlessly. At the demonstration venue, participants can experience a 360° Safari Tour, showcasing the system's ability to improve user focus while maintaining an immersive experience.

---

### Attention Guidance through Video Script: A Case Study of Object Focusing on 360° VR Video Tours

Authors: Paulo Vitor Santana Silva, Arthur Ricardo Sousa Vitória, Diogo Fernandes Costa Silva, Arlindo Rodrigues Galvão Filho
Published: 2026-01-29
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.16875v1

Within the expansive domain of virtual reality (VR), 360° VR videos immerse viewers in a spherical environment, allowing them to explore and interact with the virtual world from all angles. While this video representation offers unparalleled levels of immersion, it often lacks effective methods to guide viewers' attention toward specific elements within the virtual environment. This paper combines the models Grounding Dino and Segment Anything (SAM) to guide attention by object focusing based on video scripts. As a case study, this work conducts the experiments on a 360° video tour on the University of Reading. The experiment results show that video scripts can improve the user experience in 360° VR Videos Tour by helping in the task of directing the user's attention.

---

### Indic-TunedLens: Interpreting Multilingual Models in Indian Languages

Authors: Mihir Panchal, Deeksha Varshney, Mamta, Asif Ekbal
Published: 2026-01-29
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.15038v2

Multilingual large language models (LLMs) are increasingly deployed in linguistically diverse regions like India, yet most interpretability tools remain tailored to English. Prior work reveals that LLMs often operate in English centric representation spaces, making cross lingual interpretability a pressing concern. We introduce Indic-TunedLens, a novel interpretability framework specifically for Indian languages that learns shared affine transformations. Unlike the standard Logit Lens, which directly decodes intermediate activations, Indic-TunedLens adjusts hidden states for each target language, aligning them with the target output distributions to enable more faithful decoding of model representations. We evaluate our framework on 10 Indian languages using the MMLU benchmark and find that it significantly improves over SOTA interpretability methods, especially for morphologically rich, low resource languages. Our results provide crucial insights into the layer-wise semantic encoding of multilingual transformers. Our model is available at https://huggingface.co/spaces/MihirRajeshPanchal/IndicTunedLens. Our code is available at https://github.com/MihirRajeshPanchal/IndicTunedLens.

---

### CircuChain: Disentangling Competence and Compliance in LLM Circuit Analysis

Authors: Mayank Ravishankara
Published: 2026-01-29
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.15037v1

As large language models (LLMs) advance toward expert-level performance in engineering domains, reliable reasoning under user-specified constraints becomes critical. In circuit analysis, for example, a numerically correct solution is insufficient if it violates established methodological conventions such as mesh directionality or polarity assignments, errors that can propagate in safety-critical systems. Yet it remains unclear whether frontier models truly apply first-principles reasoning or rely on entrenched training priors that conflict with explicit instructions. We introduce CircuChain, a diagnostic benchmark designed to disentangle instruction compliance from physical reasoning competence in electrical circuit analysis. CircuChain consists of counterbalanced Control/Trap problem pairs across five canonical circuit topologies, augmented with systematic variations in sign conventions, current orientations, and polarity definitions. A multi-stage verification pipeline, combining symbolic solvers, SPICE simulation, and an LLM-based error taxonomy, enables fine-grained attribution of failures to convention errors, physics errors, arithmetic mistakes, or hallucinations. Across 100 tasks per model, we observe a consistent Compliance-Competence Divergence. The strongest model evaluated exhibits near-perfect physical reasoning but a high rate of convention violations when Trap conditions deliberately invert natural sign patterns. Conversely, weaker models display lower physical fidelity yet superior adherence to explicit instructions. These results suggest that increased model capability does not guarantee improved constraint alignment and highlight the need for new evaluation frameworks that stress instruction-following under mathematically rigid domains. CircuChain provides one such framework and offers actionable insights for both engineering education and AI alignment research.

---

### Securing SIM-Assisted Wireless Networks via Quantum Reinforcement Learning

Authors: Le-Hung Hoang, Quang-Trung Luu, Dinh Thai Hoang, Diep N. Nguyen, Van-Dinh Nguyen
Published: 2026-01-29
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2602.13238v2

Stacked intelligent metasurfaces (SIMs) have recently emerged as a powerful wave-domain technology that enables multi-stage manipulation of electromagnetic signals through multilayer programmable architectures. While SIMs offer unprecedented degrees of freedom for enhancing physical-layer security, their extremely large number of meta-atoms leads to a high-dimensional and strongly coupled optimization space, making conventional design approaches inefficient and difficult to scale. Moreover, existing deep reinforcement learning (DRL) techniques suffer from slow convergence and performance degradation in dynamic wireless environments with imperfect knowledge of passive eavesdroppers. To address these challenges, we propose a hybrid quantum proximal policy optimization (QPPO) framework for SIM-assisted secure communications that jointly optimizes transmit power allocation and SIM phase shifts to maximize the average secrecy rate under power and quality-of-service constraints. Specifically, a parameterized quantum circuit is embedded into the actor network, forming a hybrid classical-quantum policy architecture that enhances policy representation capability and exploration efficiency in high-dimensional continuous action spaces. Extensive simulations demonstrate that the proposed Q-PPO scheme consistently outperforms DRL baselines, achieving approximately 15% higher secrecy rates and 30% faster convergence under imperfect eavesdropper channel state information. These results establish Q-PPO as a powerful optimization paradigm for SIM-enabled secure wireless networks.

---

### NL2LOGIC: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models

Authors: Rizky Ramadhana Putra, Raihan Sultan Pasha Basuki, Yutong Cheng, Peng Gao
Published: 2026-01-29
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13237v1

Automated reasoning is critical in domains such as law and governance, where verifying claims against facts in documents requires both accuracy and interpretability. Recent work adopts structured reasoning pipelines that translate natural language into first-order logic and delegate inference to automated solvers. With the rise of large language models, approaches such as GCD and CODE4LOGIC leverage their reasoning and code generation capabilities to improve logic parsing. However, these methods suffer from fragile syntax control due to weak enforcement of global grammar constraints and low semantic faithfulness caused by insufficient clause-level semantic understanding. We propose NL2LOGIC, a first-order logic translation framework that introduces an abstract syntax tree as an intermediate representation. NL2LOGIC combines a recursive large language model based semantic parser with an abstract syntax tree guided generator that deterministically produces solver-ready logic code. Experiments on the FOLIO, LogicNLI, and ProofWriter benchmarks show that NL2LOGIC achieves 99 percent syntactic accuracy and improves semantic correctness by up to 30 percent over state-of-the-art baselines. Furthermore, integrating NL2LOGIC into Logic-LM yields near-perfect executability and improves downstream reasoning accuracy by 31 percent compared to Logic-LM's original few-shot unconstrained translation module.

---

### Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains

Authors: Yuqi Xiong, Chunyi Peng, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu
Published: 2026-01-29
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.13235v2

Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a given query. Existing VRAG frameworks usually depend on rigid, pre-defined external tools to extend the perceptual capabilities of VLMs, typically by explicitly separating visual perception from subsequent reasoning processes. However, this decoupled design can lead to unnecessary loss of visual information, particularly when image-based operations such as cropping are applied. In this paper, we propose Lang2Act, which enables fine-grained visual perception and reasoning through self-emergent linguistic toolchains. Rather than invoking fixed external engines, Lang2Act collects self-emergent actions as linguistic tools and leverages them to enhance the visual perception capabilities of VLMs. To support this mechanism, we design a two-stage Reinforcement Learning (RL)-based training framework. Specifically, the first stage optimizes VLMs to self-explore high-quality actions for constructing a reusable linguistic toolbox, and the second stage further optimizes VLMs to exploit these linguistic tools for downstream reasoning effectively. Experimental results demonstrate the effectiveness of Lang2Act in substantially enhancing the visual perception capabilities of VLMs, achieving performance improvements of over 4%. All code and data are available at https://github.com/NEUIR/Lang2Act.

---

### Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents

Authors: Mingyang Liao, Yichen Wan, shuchen wu, Chenxi Miao, Xin Shen, Weikang Li, Yang Li, Deguo Xia, Jizhou Huang
Published: 2026-01-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.13234v1

LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky or negative personas. Most prior work mitigates this issue with training-time solutions (e.g., data curation or alignment-oriented regularization). However, these approaches are costly to maintain as personas and attack strategies evolve, can degrade in-character behavior, and are typically infeasible for frontier closed-weight LLMs. We propose a training-free Dual-Cycle Adversarial Self-Evolution framework with two coupled cycles. A Persona-Targeted Attacker Cycle synthesizes progressively stronger jailbreak prompts, while a Role-Playing Defender Cycle distills observed failures into a hierarchical knowledge base of (i) global safety rules, (ii) persona-grounded constraints, and (iii) safe in-character exemplars. At inference time, the Defender retrieves and composes structured knowledge from this hierarchy to guide generation, producing responses that remain faithful to the target persona while satisfying safety constraints. Extensive experiments across multiple proprietary LLMs show consistent gains over strong baselines on both role fidelity and jailbreak resistance, and robust generalization to unseen personas and attack prompts.

---

### PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading

Authors: Mayank Ravishankara
Published: 2026-01-29
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2602.13232v1

We present PlotChain, a deterministic, generator-based benchmark for evaluating multimodal large language models (MLLMs) on engineering plot reading-recovering quantitative values from classic plots (e.g., Bode/FFT, step response, stress-strain, pump curves) rather than OCR-only extraction or free-form captioning. PlotChain contains 15 plot families with 450 rendered plots (30 per family), where every item is produced from known parameters and paired with exact ground truth computed directly from the generating process. A central contribution is checkpoint-based diagnostic evaluation: in addition to final targets, each item includes intermediate 'cp_' fields that isolate sub-skills (e.g., reading cutoff frequency or peak magnitude) and enable failure localization within a plot family. We evaluate four state-of-the-art MLLMs under a standardized, deterministic protocol (temperature = 0 and a strict JSON-only numeric output schema) and score predictions using per-field tolerances designed to reflect human plot-reading precision. Under the 'plotread' tolerance policy, the top models achieve 80.42% (Gemini 2.5 Pro), 79.84% (GPT-4.1), and 78.21% (Claude Sonnet 4.5) overall field-level pass rates, while GPT-4o trails at 61.59%. Despite strong performance on many families, frequency-domain tasks remain brittle: bandpass response stays low (<= 23%), and FFT spectrum remains challenging. We release the generator, dataset, raw model outputs, scoring code, and manifests with checksums to support fully reproducible runs and retrospective rescoring under alternative tolerance policies.

---

### MolLIBRA: Genetic Molecular Optimization with Multi-Fingerprint Surrogates and Text-Molecule Aligned Critic

Authors: Masahi Okada, Kazuki Sakai, Hiroaki Yoshida, Masaki Okoshi, Tadahiro Taniguchi
Published: 2026-01-29
Categories: cs.NE, cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2602.07002v1

We study sample-efficient molecular optimization under a limited budget of oracle evaluations. We propose MolLIBRA (MultimOdaLity and Language Integrated Bayesian and evolutionaRy optimizAtion), a genetic algorithm based framework that pre-ranks candidate molecules using multiple critics before oracle calls: (i) an ensemble of Gaussian process (GP) surrogates defined over multiple molecular fingerprints and (ii) a pretrained text-molecule aligned encoder CLAMP. The GP ensemble enables adaptive selection of task-appropriate fingerprints, while CLAMP provides a zero-shot scoring signal from task descriptions by measuring the similarity between molecular and text embeddings. On the Practical Molecular Optimization (PMO) benchmark with a budget of 1,000 evaluations (PMO-1K), MolLIBRA-L, our variant with a language-model-based candidate generator, attains the best Top-10 AUC on 14/22 tasks and the highest overall sum of Top-10 AUC across tasks among prior methods.

---

### Towards Agentic Intelligence for Materials Science

Authors: Huan Zhang, Yizhan Li, Wenhao Huang, Ziyu Hou, Yu Song, Xuye Liu, Farshid Effaty, Jinya Jiang, Sifan Wu, Qianggang Ding, Izumi Takahara, Leonard R. MacGillivray et al.
Published: 2026-01-29
Categories: cond-mat.mtrl-sci, cs.AI
arXiv: https://arxiv.org/abs/2602.00169v2

The convergence of artificial intelligence and materials science presents a transformative opportunity, but achieving true acceleration in discovery requires moving beyond task-isolated, fine-tuned models toward agentic systems that plan, act, and learn across the full discovery loop. This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining, through domain adaptation and instruction tuning, to goal-conditioned agents interfacing with simulation and experimental platforms. Unlike prior reviews, we treat the entire process as an end-to-end system to be optimized for tangible discovery outcomes rather than proxy benchmarks. This perspective allows us to trace how upstream design choices-such as data curation and training objectives-can be aligned with downstream experimental success through effective credit assignment. To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science. We then analyze the field through two focused lenses: From the AI perspective, the survey details LLM strengths in pattern recognition, predictive analytics, and natural language processing for literature mining, materials characterization, and property prediction; from the materials science perspective, it highlights applications in materials design, process optimization, and the acceleration of computational workflows via integration with external tools (e.g., DFT, robotic labs). Finally, we contrast passive, reactive approaches with agentic design, cataloging current contributions while motivating systems that pursue long-horizon goals with autonomy, memory, and tool use. This survey charts a practical roadmap towards autonomous, safety-aware LLM agents aimed at discovering novel and useful materials.

---

### YOLOE-26: Integrating YOLO26 with YOLOE for Real-Time Open-Vocabulary Instance Segmentation

Authors: Ranjan Sapkota, Manoj Karkee
Published: 2026-01-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.00168v1

This paper presents YOLOE-26, a unified framework that integrates the deployment-optimized YOLO26(or YOLOv26) architecture with the open-vocabulary learning paradigm of YOLOE for real-time open-vocabulary instance segmentation. Building on the NMS-free, end-to-end design of YOLOv26, the proposed approach preserves the hallmark efficiency and determinism of the YOLO family while extending its capabilities beyond closed-set recognition. YOLOE-26 employs a convolutional backbone with PAN/FPN-style multi-scale feature aggregation, followed by end-to-end regression and instance segmentation heads. A key architectural contribution is the replacement of fixed class logits with an object embedding head, which formulates classification as similarity matching against prompt embeddings derived from text descriptions, visual examples, or a built-in vocabulary. To enable efficient open-vocabulary reasoning, the framework incorporates Re-Parameterizable Region-Text Alignment (RepRTA) for zero-overhead text prompting, a Semantic-Activated Visual Prompt Encoder (SAVPE) for example-guided segmentation, and Lazy Region Prompt Contrast for prompt-free inference. All prompting modalities operate within a unified object embedding space, allowing seamless switching between text-prompted, visual-prompted, and fully autonomous segmentation. Extensive experiments demonstrate consistent scaling behavior and favorable accuracy-efficiency trade-offs across model sizes in both prompted and prompt-free settings. The training strategy leverages large-scale detection and grounding datasets with multi-task optimization and remains fully compatible with the Ultralytics ecosystem for training, validation, and deployment. Overall, YOLOE-26 provides a practical and scalable solution for real-time open-vocabulary instance segmentation in dynamic, real-world environments.

---

### Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints

Authors: Evan Chen, Wenzhi Fang, Shiqiang Wang, Christopher Brinton
Published: 2026-01-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.00166v2

Locally deployed Small Language Models (SLMs) must continually support diverse tasks under strict memory and computation constraints, making selective reliance on cloud Large Language Models (LLMs) unavoidable. Regulating cloud assistance during continual learning is challenging, as naive reward-based reinforcement learning often yields unstable offloading behavior and exacerbates catastrophic forgetting as task distributions shift. We propose DA-GRPO, a dual-advantage extension of Group Relative Policy Optimization that incorporates cloud-usage constraints directly into advantage computation, avoiding fixed reward shaping and external routing models. This design enables the local model to jointly learn task competence and collaboration behavior, allowing cloud requests to emerge naturally during post-training while respecting a prescribed assistance budget. Experiments on mathematical reasoning and code generation benchmarks show that DA-GRPO improves post-switch accuracy, substantially reduces forgetting, and maintains stable cloud usage compared to prior collaborative and routing-based approaches.

---

### Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models

Authors: Arthur Negrão, Pedro Silva, Vander L. S. Freitas, Gladston Moreira, Eduardo Luz
Published: 2026-01-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00165v2

Post-training quantization (PTQ) is a practical way to reduce the memory footprint of large language models, but low-bit quantization is sensitive to mismatches between the quantization codebook and the empirical weight/activation distributions. We revisit Benford-like leading-digit statistics as a lightweight diagnostic of scale-broad behavior in transformer tensors. Across several model families, we observe a consistent functional dichotomy: transformational nn.Linear weights tend to be Benford-like, whereas LayerNorm parameters systematically deviate. Motivated by this observation, we propose BenQ, a data-free PTQ codebook that uses a simple log-spaced grid as a proxy for scale-broad distributions and applies it selectively to transformational layers while keeping stability-critical parameters in higher precision. In 4-bit group-wise PTQ, BenQ consistently improves over uniform RTN and trades wins with NF4 across architectures and tasks, while remaining substantially simpler than optimization-based methods. We additionally report dynamic activation quantization as an exploratory stress test: the results show that log-spaced grids can reduce RTN failures in some families, but also reveal that outlier handling remains essential for reliable low-bit activation PTQ. Code is available at https://github.com/ufopcsilab/benford-quant.

---

### Why Are AI Agent Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical Study

Authors: Khairul Alam, Saikat Mondal, Banani Roy
Published: 2026-01-29
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.00164v1

Autonomous coding agents (e.g., OpenAI Codex, Devin, GitHub Copilot) are increasingly used to generate fix-related pull requests (PRs) in real world software repositories. However, their practical effectiveness depends on whether these contributions are accepted and merged by project maintainers. In this paper, we present an empirical study of AI agent involved fix related PRs, examining both their integration outcomes, latency, and the factors that hinder successful merging. We first analyze 8,106 fix related PRs authored by five widely used AI coding agents from the AIDEV POP dataset to quantify the proportions of PRs that are merged, closed without merging, or remain open. We then conduct a manual qualitative analysis of a statistically significant sample of 326 closed but unmerged PRs, spending approximately 100 person hours to construct a structured catalog of 12 failure reasons. Our results indicate that test case failures and prior resolution of the same issues by other PRs are the most common causes of non integration, whereas build or deployment failures are comparatively rare. Overall, our findings expose key limitations of current AI coding agents in real world settings and highlight directions for their further improvement and for more effective human AI collaboration in software maintenance.

---