# Research Papers — 2026-02 · bundle page 93 of 210

> Full-text markdown of papers #4601–4650 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/93
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/92.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/94.md)

### DistillLens: Symmetric Knowledge Distillation Through Logit Lens

Authors: Manish Dhakal, Uthman Jinadu, Anjila Budathoki, Rajshekhar Sunderraman, Yi Ding
Published: 2026-02-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.13567v1

Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process as a black box. While feature-based distillation attempts to bridge this gap, existing methods (e.g., MSE and asymmetric KL divergence) ignore the rich uncertainty profiles required for the final output. In this paper, we introduce DistillLens, a framework that symmetrically aligns the evolving thought processes of student and teacher models. By projecting intermediate hidden states into the vocabulary space via the Logit Lens, we enforce structural alignment using a symmetric divergence objective. Our analysis proves that this constraint imposes a dual-sided penalty, preventing both overconfidence and underconfidence while preserving the high-entropy information conduits essential for final deduction. Extensive experiments on GPT-2 and Llama architectures demonstrate that DistillLens consistently outperforms standard KD and feature-transfer baselines on diverse instruction-following benchmarks. The code is available at https://github.com/manishdhakal/DistillLens.

---

### Fast Surrogate Learning for Multi-Objective UAV Placement in Motorway Intelligent Transportation System

Authors: Weian Guo, Shixin Deng, Wuzhao Li, Li Li
Published: 2026-02-14
Categories: cs.NE
arXiv: https://arxiv.org/abs/2602.13564v1

We address multi-objective unmanned aerial vehicle (UAV) placement for motorway intelligent transportation systems, where deployments must balance coverage, link quality, and UAV count under geometric constraints. We construct a reproducible benchmark from highD motorway recordings with recording-level splits and generate Pareto-optimal labels via NSGA-II. A preference rule yields deployable targets while preserving multi-objective evaluation. We train fast surrogate models that map unordered vehicle positions to UAV count and continuous placements, using permutation-aware losses and constraint-regularized training across set-based and sequence-based architectures. The evaluation protocol combines Pareto quality metrics, success-rate curves, runtime benchmarks, and robustness studies, with uncertainty quantified by recording-level bootstrap. Results indicate that permutation-invariant set models provide the strongest coverage--SNR--count trade-off among learned predictors and approach NSGA-II quality while enabling real-time inference. Under shared budgets, they offer a more favorable success--latency trade-off than heuristic baselines. The benchmark, splits are released to support reproducible ITS deployment studies and to facilitate comparisons under shared operational budgets.

---

### Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning

Authors: Yanbo Wang, Minzheng Wang, Jian Liang, Lu Wang, Yongcan Yu, Ran He
Published: 2026-02-14
Categories: cs.CR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13562v2

While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off between safety and utility. However, prevailing alignment strategies typically construct CoT training data with explicit safety rules via context distillation. This approach inadvertently limits reasoning capabilities by creating a rigid association between rule memorization and refusal. To mitigate the safety-utility trade-off, we propose the Adaptive Safe Context Learning~(ASCL) framework to improve the reasoning given proper context. ASCL formulates safety alignment as a multi-turn tool-use process, empowering the model to autonomously decide when to consult safety rules and how to generate the ongoing reasoning. Furthermore, to counteract the preference for rule consultation during RL, we introduce Inverse Frequency Policy Optimization~(IFPO) to rebalance advantage estimates. By decoupling rule retrieval and subsequent reasoning, our method achieves higher overall performance compared to baselines. Our code is publicly available at https://github.com/ybwang119/ASCL.

---

### OpAgent: Operator Agent for Web Navigation

Authors: Yuyu Guo, Wenjie Yang, Siyuan Yang, Ziyang Liu, Cheng Chen, Yuan Wei, Yun Hu, Yang Huang, Guoliang Hao, Dongsheng Yuan, Jianming Wang, Xin Chen et al.
Published: 2026-02-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.13559v2

To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely on Supervised Fine-Tuning (SFT) or Offline Reinforcement Learning (RL) using static datasets. However, these methods suffer from severe distributional shifts, as offline trajectories fail to capture the stochastic state transitions and real-time feedback of unconstrained wide web environments. In this paper, we propose a robust Online Reinforcement Learning WebAgent, designed to optimize its policy through direct, iterative interactions with unconstrained wide websites. Our approach comprises three core innovations: 1) Hierarchical Multi-Task Fine-tuning: We curate a comprehensive mixture of datasets categorized by functional primitives -- Planning, Acting, and Grounding -- establishing a Vision-Language Model (VLM) with strong instruction-following capabilities for Web GUI tasks. 2) Online Agentic RL in the Wild: We develop an online interaction environment and fine-tune the VLM using a specialized RL pipeline. We introduce a Hybrid Reward Mechanism that combines a ground-truth-agnostic WebJudge for holistic outcome assessment with a Rule-based Decision Tree (RDT) for progress reward. This system effectively mitigates the credit assignment challenge in long-horizon navigation. Notably, our RL-enhanced model achieves a 38.1\% success rate (pass@5) on WebArena, outperforming all existing monolithic baselines. 3) Operator Agent: We introduce a modular agentic framework, namely \textbf{OpAgent}, orchestrating a Planner, Grounder, Reflector, and Summarizer. This synergy enables robust error recovery and self-correction, elevating the agent's performance to a new State-of-the-Art (SOTA) success rate of \textbf{71.6\%}.

---

### Scenario-Adaptive MU-MIMO OFDM Semantic Communication With Asymmetric Neural Network

Authors: Chongyang Li, Tianqian Zhang, Shouyin Liu
Published: 2026-02-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.13557v1

Semantic Communication (SemCom) has emerged as a promising paradigm for 6G networks, aiming to extract and transmit task-relevant information rather than minimizing bit errors. However, applying SemCom to realistic downlink Multi-User Multi-Input Multi-Output (MU-MIMO) Orthogonal Frequency Division Multiplexing (OFDM) systems remains challenging due to severe Multi-User Interference (MUI) and frequency-selective fading. Existing Deep Joint Source-Channel Coding (DJSCC) schemes, primarily designed for point-to-point links, suffer from performance saturation in multi-user scenarios. To address these issues, we propose a scenario-adaptive MU-MIMO SemCom framework featuring an asymmetric architecture tailored for downlink transmission. At the transmitter, we introduce a scenario-aware semantic encoder that dynamically adjusts feature extraction based on Channel State Information (CSI) and Signal-to-Noise Ratio (SNR), followed by a neural precoding network designed to mitigate MUI in the semantic domain. At the receiver, a lightweight decoder equipped with a novel pilot-guided attention mechanism is employed to implicitly perform channel equalization and feature calibration using reference pilot symbols. Extensive simulation results over 3GPP channel models demonstrate that the proposed framework significantly outperforms DJSCC and traditional Separate Source-Channel Coding (SSCC) schemes in terms of Peak Signal-to-Noise Ratio (PSNR) and classification accuracy, particularly in low-SNR regimes, while maintaining low latency and computational cost on edge devices.

---

### Discrete-Space Generative AI Pipeline for Semantic Transmission of Signals

Authors: Silvija Kokalj-Filipovic, Yagna Kaasaragadda
Published: 2026-02-14
Categories: cs.IT, cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2602.13556v1

We introduce Discernment, a semantic communication system that transmits the meaning of physical signals (baseband radio and audio) over a technical channel using GenAI models operating in discrete spaces. Discernment dynamically adapts to channel impairments - modeled as erasure channels - by switching between an autoregressive or a diffusion-based generative algorithm, depending on the erasure pattern. Our results show that Discernment maintains semantic integrity even as channel capacity severely degrades, exhibiting very small and graceful performance decline in both classification accuracy and statistical fidelity of the reconstructed meaning. These findings demonstrate Discernment's ability to adjust to diverse physical channel conditions while maintaining spectral efficiency and low model complexity, making it well suited for IoT deployments and strongly motivating further research on this semantic channel paradigm.

---

### Privacy-Concealing Cooperative Perception for BEV Scene Segmentation

Authors: Song Wang, Lingling Li, Marcus Santos, Guanghui Wang
Published: 2026-02-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.13555v1

Cooperative perception systems for autonomous driving aim to overcome the limited perception range of a single vehicle by communicating with adjacent agents to share sensing information. While this improves perception performance, these systems also face a significant privacy-leakage issue, as sensitive visual content can potentially be reconstructed from the shared data. In this paper, we propose a novel Privacy-Concealing Cooperation (PCC) framework for Bird's Eye View (BEV) semantic segmentation. Based on commonly shared BEV features, we design a hiding network to prevent an image reconstruction network from recovering the input images from the shared features. An adversarial learning mechanism is employed to train the network, where the hiding network works to conceal the visual clues in the BEV features while the reconstruction network attempts to uncover these clues. To maintain segmentation performance, the perception network is integrated with the hiding network and optimized end-to-end. The experimental results demonstrate that the proposed PCC framework effectively degrades the quality of the reconstructed images with minimal impact on segmentation performance, providing privacy protection for cooperating vehicles. The source code will be made publicly available upon publication.

---

### Small Reward Models via Backward Inference

Authors: Yike Wang, Faeze Brahman, Shangbin Feng, Teng Xiao, Hannaneh Hajishirzi, Yulia Tsvetkov
Published: 2026-02-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.13551v3

Reward models (RMs) play a central role throughout the language model (LM) pipeline, particularly in non-verifiable domains. However, the dominant LLM-as-a-Judge paradigm relies on the strong reasoning capabilities of large models, while alternative approaches require reference responses or explicit rubrics, limiting flexibility and broader accessibility. In this work, we propose FLIP (FLipped Inference for Prompt reconstruction), a reference-free and rubric-free reward modeling approach that reformulates reward modeling through backward inference: inferring the instruction that would most plausibly produce a given response. The similarity between the inferred and the original instructions is then used as the reward signal. Evaluations across four domains using 13 small language models show that FLIP outperforms LLM-as-a-Judge baselines by an average of 79.6%. Moreover, FLIP substantially improves downstream performance in extrinsic evaluations under test-time scaling via parallel sampling and GRPO training. We further find that FLIP is particularly effective for longer outputs and robust to common forms of reward hacking. By explicitly exploiting the validation-generation gap, FLIP enables reliable reward modeling in downscaled regimes where judgment methods fail. Code available at https://github.com/yikee/FLIP.

---

### Small Reward Models via Backward Inference

Authors: Yike Wang, Faeze Brahman, Shangbin Feng, Teng Xiao, Hannaneh Hajishirzi, Yulia Tsvetkov
Published: 2026-02-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.13551v2

Reward models (RMs) play a central role throughout the language model (LM) pipeline, particularly in non-verifiable domains. However, the dominant LLM-as-a-Judge paradigm relies on the strong reasoning capabilities of large models, while alternative approaches require reference responses or explicit rubrics, limiting flexibility and broader accessibility. In this work, we propose FLIP (FLipped Inference for Prompt reconstruction), a reference-free and rubric-free reward modeling approach that reformulates reward modeling through backward inference: inferring the instruction that would most plausibly produce a given response. The similarity between the inferred and the original instructions is then used as the reward signal. Evaluations across four domains using 13 small language models show that FLIP outperforms LLM-as-a-Judge baselines by an average of 79.6%. Moreover, FLIP substantially improves downstream performance in extrinsic evaluations under test-time scaling via parallel sampling and GRPO training. We further find that FLIP is particularly effective for longer outputs and robust to common forms of reward hacking. By explicitly exploiting the validation-generation gap, FLIP enables reliable reward modeling in downscaled regimes where judgment methods fail. Code available at https://github.com/yikee/FLIP.

---

### Out-of-Support Generalisation via Weight-Space Sequence Modelling

Authors: Roussel Desmond Nzoyem
Published: 2026-02-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.13550v3

As breakthroughs in deep learning transform key industries, models are increasingly required to extrapolate on datapoints found outside the range of the training set, a challenge we coin as out-of-support (OoS) generalisation. However, neural networks frequently exhibit catastrophic failure on OoS samples, yielding unrealistic but overconfident predictions. We address this challenge by reformulating the OoS generalisation problem as a sequence modelling task in the weight space, wherein the training set is partitioned into concentric shells corresponding to discrete sequential steps. Our WeightCaster framework yields plausible, interpretable, and uncertainty-aware predictions without necessitating explicit inductive biases, all the while maintaining high computational efficiency. Emprical validation on a synthetic cosine dataset and real-world air quality sensor readings demonstrates performance competitive or superior to the state-of-the-art. By enhancing reliability beyond in-distribution scenarios, these results hold significant implications for the wider adoption of artificial intelligence in safety-critical applications.

---

### Nighttime Autonomous Driving Scene Reconstruction with Physically-Based Gaussian Splatting

Authors: Tae-Kyeong Kim, Xingxin Chen, Guile Wu, Chengjie Huang, Dongfeng Bai, Bingbing Liu
Published: 2026-02-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.13549v1

This paper focuses on scene reconstruction under nighttime conditions in autonomous driving simulation. Recent methods based on Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) have achieved photorealistic modeling in autonomous driving scene reconstruction, but they primarily focus on normal-light conditions. Low-light driving scenes are more challenging to model due to their complex lighting and appearance conditions, which often causes performance degradation of existing methods. To address this problem, this work presents a novel approach that integrates physically based rendering into 3DGS to enhance nighttime scene reconstruction for autonomous driving. Specifically, our approach integrates physically based rendering into composite scene Gaussian representations and jointly optimizes Bidirectional Reflectance Distribution Function (BRDF) based material properties. We explicitly model diffuse components through a global illumination module and specular components by anisotropic spherical Gaussians. As a result, our approach improves reconstruction quality for outdoor nighttime driving scenes, while maintaining real-time rendering. Extensive experiments across diverse nighttime scenarios on two real-world autonomous driving datasets, including nuScenes and Waymo, demonstrate that our approach outperforms the state-of-the-art methods both quantitatively and qualitatively.

---

### AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks

Authors: Weiming Song, Xuan Xie, Ruiping Yin
Published: 2026-02-14
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.13547v1

Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses rely on expensive fine-tuning, intrusive prompt rewriting, or external guardrails that add latency and can degrade helpfulness. We present AISA, a lightweight, single-pass defense that activates safety behaviors already latent inside the model rather than treating safety as an add-on. AISA first localizes intrinsic safety awareness via spatiotemporal analysis and shows that intent-discriminative signals are broadly encoded, with especially strong separability appearing in the scaled dot-product outputs of specific attention heads near the final structural tokens before generation. Using a compact set of automatically selected heads, AISA extracts an interpretable prompt-risk score with minimal overhead, achieving detector-level performance competitive with strong proprietary baselines on small (7B) models. AISA then performs logits-level steering: it modulates the decoding distribution in proportion to the inferred risk, ranging from normal generation for benign prompts to calibrated refusal for high-risk requests -- without changing model parameters, adding auxiliary modules, or requiring multi-pass inference. Extensive experiments spanning 13 datasets, 12 LLMs, and 14 baselines demonstrate that AISA improves robustness and transfer while preserving utility and reducing false refusals, enabling safer deployment even for weakly aligned or intentionally risky model variants.

---

### LiveNewsBench: Evaluating LLM Web Search Capabilities with Freshly Curated News

Authors: Yunfan Zhang, Kathleen McKeown, Smaranda Muresan
Published: 2026-02-14
Categories: cs.IR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.13543v1

Large Language Models (LLMs) with agentic web search capabilities show strong potential for tasks requiring real-time information access and complex fact retrieval, yet evaluating such systems remains challenging. We introduce \bench, a rigorous and regularly updated benchmark designed to assess the agentic web search abilities of LLMs. \bench automatically generates fresh question-answer pairs from recent news articles, ensuring that questions require information beyond an LLM's training data and enabling clear separation between internal knowledge and search capability. The benchmark features intentionally difficult questions requiring multi-hop search queries, page visits, and reasoning, making it well-suited for evaluating agentic search behavior. Our automated data curation and question generation pipeline enables frequent benchmark updates and supports construction of a large-scale training dataset for agentic web search models, addressing the scarcity of such data in the research community. To ensure reliable evaluation, we include a subset of human-verified samples in the test set. We evaluate a broad range of systems using \bench, including commercial and open-weight LLMs as well as LLM-based web search APIs. The leaderboard, datasets, and code are publicly available at livenewsbench.com.

---

### On Calibration of Large Language Models: From Response To Capability

Authors: Sin-Han Yang, Cheng-Kuang Wu, Chieh-Yen Lin, Yun-Nung Chen, Hung-yi Lee, Shao-Hua Sun
Published: 2026-02-14
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.13540v2

Accurate confidence estimation is critical for reliable use of large language models (LLMs). Prior work on LLM calibration largely focuses on response-level confidence, which estimates the correctness of a single generated output. However, this formulation is misaligned with many practical settings where the central question is how likely a model is to solve a query overall. We show that this mismatch results from the stochastic nature of modern LLM decoding, under which single-response correctness fails to reflect underlying model capability. To address this issue, we introduce capability calibration, a new evaluation framework for measuring how well query-level confidence aligns with a model's expected accuracy on individual queries. We formally distinguish capability calibration (CC) from response calibration (RC) and show that the two differ both theoretically and empirically. We further show that CC is better suited than RC to applications like pass@k prediction and inference budget allocation. Finally, we evaluate common confidence estimation methods to understand the practical feasibility of CC.

---

### On Calibration of Large Language Models: From Response To Capability

Authors: Sin-Han Yang, Cheng-Kuang Wu, Chieh-Yen Lin, Yun-Nung Chen, Hung-yi Lee, Shao-Hua Sun
Published: 2026-02-14
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.13540v1

Large language models (LLMs) are widely deployed as general-purpose problem solvers, making accurate confidence estimation critical for reliable use. Prior work on LLM calibration largely focuses on response-level confidence, which estimates the correctness of a single generated output. However, this formulation is misaligned with many practical settings where the central question is how likely a model is to solve a query overall. We show that this mismatch results from the stochastic nature of modern LLM decoding, under which single-response correctness fails to reflect underlying model capability. To address this issue, we introduce capability calibration, which targets the model's expected accuracy on a query. We formally distinguish capability calibration from response calibration and show that the two differ both theoretically and empirically. We establish an empirical evaluation setup and study a range of confidence estimation methods. Our results demonstrate that capability-calibrated confidence improves pass@$k$ prediction and inference budget allocation, establishing a foundation with potential for diverse applications.

---

### Fast Swap-Based Element Selection for Multiplication-Free Dimension Reduction

Authors: Nobutaka Ono
Published: 2026-02-14
Categories: cs.LG, eess.AS, eess.IV, eess.SP
arXiv: https://arxiv.org/abs/2602.13532v1

In this paper, we propose a fast algorithm for element selection, a multiplication-free form of dimension reduction that produces a dimension-reduced vector by simply selecting a subset of elements from the input. Dimension reduction is a fundamental technique for reducing unnecessary model parameters, mitigating overfitting, and accelerating training and inference. A standard approach is principal component analysis (PCA), but PCA relies on matrix multiplications; on resource-constrained systems, the multiplication count itself can become a bottleneck. Element selection eliminates this cost because the reduction consists only of selecting elements, and thus the key challenge is to determine which elements should be retained. We evaluate a candidate subset through the minimum mean-squared error of linear regression that predicts a target vector from the selected elements, where the target may be, for example, a one-hot label vector in classification. When an explicit target is unavailable, the input itself can be used as the target, yielding a reconstruction-based criterion. The resulting optimization is combinatorial, and exhaustive search is impractical. To address this, we derive an efficient formula for the objective change caused by swapping a selected and an unselected element, using the matrix inversion lemma, and we perform a swap-based local search that repeatedly applies objective-decreasing swaps until no further improvement is possible. Experiments on MNIST handwritten-digit images demonstrate the effectiveness of the proposed method.

---

### QuaRK: A Quantum Reservoir Kernel for Time Series Learning

Authors: Abdallah Aaraba, Soumaya Cherkaoui, Ola Ahmad, Shengrui Wang
Published: 2026-02-14
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2602.13531v1

Quantum reservoir computing offers a promising route for time series learning by modelling sequential data via rich quantum dynamics while the only training required happens at the level of a lightweight classical readout. However, studies featuring efficient and implementable quantum reservoir architectures along with model learning guarantees remain scarce in the literature. To close this gap, we introduce QuaRK, an end-to-end framework that couples a hardware-realistic quantum reservoir featurizer with a kernel-based readout scheme. Given a sequence of sample points, the reservoir injects the points one after the other to yield a compact feature vector from efficiently measured k-local observables using classical shadow tomography, after which a classical kernel-based readout learns the target mapping with explicit regularization and fast optimization. The resulting pipeline exposes clear computational knobs -- circuit width and depth as well as the measurement budget -- while preserving the flexibility of kernel methods to model nonlinear temporal functionals and being scalable to high-dimensional data. We further provide learning-theoretic generalization guarantees for dependent temporal data, linking design and resource choices to finite-sample performance, thereby offering principled guidance for building reliable temporal learners. Empirical experiments validate QuaRK and illustrate the predicted interpolation and generalization behaviours on synthetic beta-mixing time series tasks.

---

### Association Is Not Similarity: Learning Corpus-Specific Associations for Multi-Hop Retrieval

Authors: Jason Dury
Published: 2026-02-13
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.20850v1

Dense retrieval systems rank passages by embedding similarity to a query, but multi-hop questions require passages that are associatively related through shared reasoning chains. We introduce Association-Augmented Retrieval (AAR), a lightweight transductive reranking method that trains a small MLP (4.2M parameters) to learn associative relationships between passages in embedding space using contrastive learning on co-occurrence annotations. At inference time, AAR reranks an initial dense retrieval candidate set using bi-directional association scoring. On HotpotQA, AAR improves passage Recall@5 from 0.831 to 0.916 (+8.6 points) without evaluation-set tuning, with gains concentrated on hard questions where the dense baseline fails (+28.5 points). On MuSiQue, AAR achieves +10.1 points in the transductive setting. An inductive model trained on training-split associations and evaluated on unseen validation associations shows no significant improvement, suggesting that the method captures corpus-specific co-occurrences rather than transferable patterns. Ablation studies support this interpretation: training on semantically similar but non-associated passage pairs degrades retrieval below the baseline, while shuffling association pairs causes severe degradation. A downstream QA evaluation shows retrieval gains translate to +6.4 exact match improvement. The method adds 3.7ms per query, trains in under two minutes on a single GPU, and requires no LLM-based indexing.

---

### Seven simple steps for log analysis in AI systems

Authors: Magda Dubois, Ekin Zorer, Maia Hamin, Joe Skinner, Alexandra Souly, Jerome Wynne, Harry Coppock, Lucas Sato, Sayash Kapoor, Sunishchal Dev, Keno Juchems, Kimberly Mai et al.
Published: 2026-02-13
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.09563v2

AI systems produce large volumes of logs as they interact with tools and users. Analysing these logs can help understand model capabilities, propensities, and behaviours, or assess whether an evaluation worked as intended. Researchers have started developing methods for log analysis, but a standardised approach is still missing. Here we suggest a pipeline based on current best practices. We illustrate it with concrete code examples in the Inspect Scout library, provide detailed guidance on each step, and highlight common pitfalls. Our framework provides researchers with a foundation for rigorous and reproducible log analysis.

---

### Benchmarking LLM Tool-Use in the Wild

Authors: Peijie Yu, Wei Liu, Yifan Yang, Jinjian Li, Zelong Zhang, Xiao Feng, Feng Zhang
Published: 2026-02-13
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.06185v1

Fulfilling user needs through Large Language Model multi-turn, multi-step tool-use is rarely a straightforward process. Real user interactions are inherently wild, being intricate, messy, and flexible. We identify three key challenges from user behaviour: compositional tasks that demand efficient orchestration of tool-call topologies, implicit intent spread across dialogue turns that require contextual inference, and instruction transition, which mixes task queries, clarifications, and casual conversation, forcing LLMs to adjust their policies on the fly. Existing benchmarks overlook these behaviors, making the apparent progress of LLMs on tool-use spurious. To address this, we introduce WildToolBench, an LLM tool-use benchmark grounded in real-world user behavior patterns. Comprehensive evaluations of 57 LLMs reveal that no model achieves an accuracy of more than 15%, indicating a substantial gap in the robustness of LLMs' agentic ability. Controlled experiments and in-depth analyses further indicate that the real challenge for LLM tool-use lies not in artificially complex tasks, but in the wild nature of user behavior, emphasizing the need to reconsider the interactions among LLMs, users, and tools.

---

### A Two-Stage Architecture for NDA Analysis: LLM-based Segmentation and Transformer-based Clause Classification

Authors: Ana Begnini, Matheus Vicente, Leonardo Souza
Published: 2026-02-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.09990v1

In business-to-business relations, it is common to establish NonDisclosure Agreements (NDAs). However, these documents exhibit significant variation in format, structure, and writing style, making manual analysis slow and error-prone. We propose an architecture based on LLMs to automate the segmentation and clauses classification within these contracts. We employed two models: LLaMA-3.1-8B-Instruct for NDA segmentation (clause extraction) and a fine-tuned Legal-Roberta-Large for clause classification. In the segmentation task, we achieved a ROUGE F1 of 0.95 +/- 0.0036; for classification, we obtained a weighted F1 of 0.85, demonstrating the feasibility and precision of the approach.

---

### The System Hallucination Scale (SHS): A Minimal yet Effective Human-Centered Instrument for Evaluating Hallucination-Related Behavior in Large Language Models

Authors: Heimo Müller, Dominik Steiger, Markus Plass, Andreas Holzinger
Published: 2026-02-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.09989v1

We introduce the System Hallucination Scale (SHS), a lightweight and human-centered measurement instrument for assessing hallucination-related behavior in large language models (LLMs). Inspired by established psychometric tools such as the System Usability Scale (SUS) and the System Causability Scale (SCS), SHS enables rapid, interpretable, and domain-agnostic evaluation of factual unreliability, incoherence, misleading presentation, and responsiveness to user guidance in model-generated text. SHS is explicitly not an automatic hallucination detector or benchmark metric; instead, it captures how hallucination phenomena manifest from a user perspective under realistic interaction conditions. A real-world evaluation with 210 participants demonstrates high clarity, coherent response behavior, and construct validity, supported by statistical analysis including internal consistency (Cronbach's alpha = 0.87$) and significant inter-dimension correlations (p < 0.001$). Comparative analysis with SUS and SCS reveals complementary measurement properties, supporting SHS as a practical tool for comparative analysis, iterative system development, and deployment monitoring.

---

### Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations

Authors: Ajay Pravin Mahale
Published: 2026-02-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.09988v1

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level analysis and natural language explanations by (i) identifying causally important attention heads via activation patching, (ii) generating explanations using both template-based and LLM-based methods, and (iii) evaluating faithfulness using ERASER-style metrics adapted for circuit-level attribution. We evaluate on the Indirect Object Identification (IOI) task in GPT-2 Small (124M parameters), identifying six attention heads accounting for 61.4% of the logit difference. Our circuit-based explanations achieve 100% sufficiency but only 22% comprehensiveness, revealing distributed backup mechanisms. LLM-generated explanations outperform template baselines by 64% on quality metrics. We find no correlation (r = 0.009) between model confidence and explanation faithfulness, and identify three failure categories explaining when explanations diverge from mechanisms.

---

### Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation

Authors: Xinyuan Wang, Kunpeng Liu, Arun Vignesh Malarkkan, Yanjie Fu
Published: 2026-02-13
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.09987v1

Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, discovering effective transformations remains challenging due to the large space of feature-operator combinations. Existing solutions rely on discrete search or latent generation, but they are frequently limited by sample inefficiency, invalid candidates, and redundant generations with limited coverage. Large Language Models (LLMs) offer strong priors for producing valid transformations, but current LLM-based FT methods typically rely on static demonstrations, resulting in limited diversity, redundant outputs, and weak alignment with downstream objectives. We propose a framework that optimizes context data for LLM-driven FT by evolving trajectory-level experiences in a closed loop. Starting from high-performing feature transportation sequences explored by reinforcement learning, we construct and continuously update an experience library of downstream task-verified transformation trajectories, and use a diversity-aware selector to form contexts along with a chain-of-thought and guide transformed feature generation toward higher performance. Experiments on diverse tabular benchmarks show that our method outperforms classical and LLM-based baselines and is more stable than one-shot generation. The framework generalizes across API-based and open-source LLMs and remains robust across downstream evaluators.

---

### Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systems

Authors: Sadia Asif, Mohammad Mohammadi Amiri
Published: 2026-02-13
Categories: cs.MA, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2603.05520v1

Sequential multi-agent large language model (LLM) systems are increasingly deployed in sensitive domains such as healthcare, finance, and enterprise decision-making, where multiple specialized agents collaboratively process a single user request. Although individual agents may satisfy local privacy constraints, sensitive information can still be inferred through sequential composition and intermediate representations. In this work, we study \emph{compositional privacy leakage} in sequential LLM agent pipelines. We formalize leakage using mutual information and derive a theoretical bound that characterizes how locally introduced leakage can amplify across agents under sequential execution. Motivated by this analysis, we propose a privacy-regularized training framework that directly constrains information flow between agent outputs and agent-local sensitive variables. We evaluate our approach across sequential agent pipelines of varying depth on three benchmark datasets, demonstrating stable optimization dynamics and consistent, interpretable privacy-utility trade-offs. Our results show that privacy in agentic LLM systems cannot be guaranteed by local constraints alone and must instead be treated as a system-level property during both training and deployment.

---

### Decorrelating the Future: Joint Frequency Domain Learning for Spatio-temporal Forecasting

Authors: Zepu Wang, Bowen Liao, Jeff, Ban
Published: 2026-02-13
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2603.04418v1

Standard direct forecasting models typically rely on point-wise objectives such as Mean Squared Error, which fail to capture the complex spatio-temporal dependencies inherent in graph-structured signals. While recent frequency-domain approaches such as FreDF mitigate temporal autocorrelation, they often overlook spatial and cross spatio-temporal interactions. To address this limitation, we propose FreST Loss, a frequency-enhanced spatio-temporal training objective that extends supervision to the joint spatio-temporal spectrum. By leveraging the Joint Fourier Transform (JFT), FreST Loss aligns model predictions with ground truth in a unified spectral domain, effectively decorrelating complex dependencies across both space and time. Theoretical analysis shows that this formulation reduces estimation bias associated with time-domain training objectives. Extensive experiments on six real-world datasets demonstrate that FreST Loss is model-agnostic and consistently improves state-of-the-art baselines by better capturing holistic spatio-temporal dynamics.

---

### Length Generalization Bounds for Transformers

Authors: Andy Yang, Pascal Bergsträßer, Georg Zetzsche, David Chiang, Anthony W. Lin
Published: 2026-02-13
Categories: cs.LG, cs.FL, cs.LO
arXiv: https://arxiv.org/abs/2603.02238v2

Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite training data. To provide such a guarantee, one needs to be able to compute a length generalization bound, beyond which the model is guaranteed to generalize. This paper concerns the open problem of the computability of such generalization bounds for C-RASP, a class of languages which is closely linked to transformers. A positive partial result was recently shown by Chen et al. for C-RASP with only one layer and, under some restrictions, also with two layers. We provide complete answers to the above open problem. Our main result is the non-existence of computable length generalization bounds for C-RASP (already with two layers) and hence for transformers. To complement this, we provide a computable bound for the positive fragment of C-RASP, which we show equivalent to fixed-precision transformers. For both positive C-RASP and fixed-precision transformers, we show that the length complexity is exponential, and prove optimality of the bounds.

---

### Concept Heterogeneity-aware Representation Steering

Authors: Laziz U. Abdullaev, Noelle Y. L. Wong, Ryan T. Z. Lee, Shiqi Jiang, Khoi N. M. Nguyen, Tan M. Nguyen
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02237v2

Representation steering offers a lightweight mechanism for controlling the behavior of large language models (LLMs) by intervening on internal activations at inference time. Most existing methods rely on a single global steering direction, typically obtained via difference-in-means over contrastive datasets. This approach implicitly assumes that the target concept is homogeneously represented across the embedding space. In practice, however, LLM representations can be highly non-homogeneous, exhibiting clustered, context-dependent structure, which renders global steering directions brittle. In this work, we view representation steering through the lens of optimal transport (OT), noting that standard difference-in-means steering implicitly corresponds to the OT map between two identical distributions with differing first moments, yielding a global translation. To relax this restrictive assumption, we theoretically model source and target representations as Gaussian mixture models and formulate steering as a discrete OT problem between semantic latent clusters. From the resulting transport plan, we derive an explicit, input-dependent steering map via barycentric projection, producing a smooth, kernel-weighted combination of cluster-level shifts. We term this method Concept Heterogeneity-aware Representation Steering (CHaRS). Through numerous experimental settings, we show that CHaRS yields more effective behavioral control than global steering.

---

### CUDABench: Benchmarking LLMs for Text-to-CUDA Generation

Authors: Jiace Zhu, Wentao Chen, Qi Fan, Zhixing Ren, Junying Wu, Xing Zhe Chai, Chotiwit Rungrueangwutthinon, Yehan Ma, An Zou
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02236v1

Recent studies have demonstrated the potential of Large Language Models (LLMs) in generating GPU Kernels. Current benchmarks focus on the translation of high-level languages into CUDA, overlooking the more general and challenging task of text-to-CUDA generation. Furthermore, given the hardware-specific and performance-critical features of GPU programming, accurately assessing the performance of LLM-generated GPU programs is nontrivial. In this work, we introduce CUDABench, a comprehensive benchmark designed to evaluate the text-to-CUDA capabilities of LLMs. First, we construct CUDABench-Set, which covers Breadth-Depth-Difficulty evaluation space in diverse application domains, including artificial intelligence, scientific computing, and data analytics, etc. Furthermore, we propose CUDABench-Score and Generative Verification Pipeline that assess (1) compilation correctness, (2) functional consistency through execution-based verification, and (3) a novel roofline-based metric, Performance-Score. Benchmarking state-of-the-art LLMs reveals insightful findings and challenges of text-to-CUDA, such as a notable mismatch between high compilation success rates and low functional correctness, a lack of domain-specific algorithmic knowledge, and suboptimal utilization of GPU hardware resources. Our benchmark is available at https://github.com/CUDA-Bench/CUDABench.

---

### Talking with Verifiers: Automatic Specification Generation for Neural Network Verification

Authors: Yizhak Y. Elboher, Reuven Peleg, Zhouxing Shi, Guy Katz, Jan Křetínský
Published: 2026-02-13
Categories: cs.LG, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2603.02235v1

Neural network verification tools currently support only a narrow class of specifications, typically expressed as low-level constraints over raw inputs and outputs. This limitation significantly hinders their adoption and practical applicability across diverse application domains where correctness requirements are naturally expressed at a higher semantic level. This challenge is rooted in the inherent nature of deep neural networks, which learn internal representations that lack an explicit mapping to human-understandable features. To address this, we bridge this gap by introducing a novel component to the verification pipeline, making existing verification tools applicable to a broader range of domains and specification styles. Our framework enables users to formulate specifications in natural language, which are then automatically analyzed and translated into formal verification queries compatible with state-of-the-art neural network verifiers. We evaluate our approach on both structured and unstructured datasets, demonstrating that it successfully verifies complex semantic specifications that were previously inaccessible. Our results show that this translation process maintains high fidelity to user intent while incurring low computational overhead, thereby substantially extending the applicability of formal DNN verification to real-world, high-level requirements.

---

### Structured vs. Unstructured Pruning: An Exponential Gap

Authors: Davide Ferre', Frédéric Giroire, Frederik Mallmann-Trenn, Emanuele Natale
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02234v3

The Strong Lottery Ticket Hypothesis (SLTH) states that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a target function at initialization without training, suggesting that pruning alone is sufficient. Pruning methods are typically classified as unstructured, where individual weights can be removed from the network, and structured, where parameters are removed according to specific patterns, as in neuron pruning. Existing theoretical results supporting the SLTH rely almost exclusively on unstructured pruning, showing that logarithmic overparameterization suffices to approximate simple target networks. In contrast, neuron pruning has received limited theoretical attention, despite its practical appeal for direct hardware speedups. In this work, we consider the problem of approximating a single bias-free ReLU neuron by pruning hidden units of a randomly initialized two-layer ReLU network, effectively isolating the intrinsic limitations of neuron pruning. We show that achieving an $\varepsilon$-approximation requires a starting network size of $Ω(1/\varepsilon)$ for neuron pruning, whereas weight pruning succeeds with only $O(\log(1/\varepsilon))$ hidden units, revealing an exponential separation between the two approaches.

---

### Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings

Authors: Jean-Baptiste Fermanian, Batiste Le Bars, Aurélien Bellet
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02233v1

Personalized Federated Learning (PFL) enables a collection of agents to collaboratively learn individual models without sharing raw data. We propose a new PFL approach in which each agent optimizes a weighted combination of all agents' empirical risks, with the weights learned from data rather than specified a priori. The novelty of our method lies in formulating the estimation of these collaborative weights as a kernel mean embedding estimation problem with multiple data sources, leveraging tools from multi-task averaging to capture statistical relationships between agents. This perspective yields a fully adaptive procedure that requires no prior knowledge of data heterogeneity and can automatically transition between global and local learning regimes. By recasting the objective as a high-dimensional mean estimation problem, we derive finite-sample guarantees on local excess risks for a broad class of distributions, explicitly quantifying the statistical gains of collaboration. To address communication constraints inherent to federated settings, we also propose a practical implementation based on random Fourier features, which allows one to trade communication cost for statistical efficiency. Numerical experiments validate our theoretical results.

---

### Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback

Authors: Amirhossein Afsharrad, Ruida Zhou, Luca Viano, Sanjay Lall, Mohammad Ghavamzadeh
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02232v1

Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences on a Likert scale (e.g., significantly better, better, slightly better, negligibly better), existing methods typically apply ad-hoc heuristics, such as margin terms or scaling factors, to loss functions derived from binary preference models like Bradley-Terry. These approaches lack an underlying mathematical model for how ordinal preference data is generated. We present a theoretically grounded framework that formulates reward modeling with Likert scale preferences as a discrete ordinal regression problem. We derive two loss functions from this formulation: a negative log-likelihood loss and an all-threshold loss, both of which learn threshold parameters that naturally capture the ordinal structure of preferences. Unlike existing heuristic methods that manually specify fixed margins or scaling weights, our approach learns these parameters directly from data within a coherent probabilistic framework. Experimental results on multiple benchmarks demonstrate that our ordinal regression approach consistently achieves competitive or superior performance compared to existing heuristic methods across diverse evaluation categories including chat, reasoning, and safety tasks. Our work provides the first principled mathematical framework for incorporating Likert scale preferences into reward model training, moving beyond ad-hoc modifications of binary preference models to enable more effective utilization of fine-grained human feedback.

---

### Physics-Informed Neural Networks with Architectural Physics Embedding for Large-Scale Wave Field Reconstruction

Authors: Huiwen Zhang, Feng Ye, Chu Ma
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02231v2

Large-scale wave field reconstruction requires precise solutions but faces challenges with computational efficiency and accuracy. The physics-based numerical methods like Finite Element Method (FEM) provide high accuracy but struggle with large-scale or high-frequency problems due to prohibitive computational costs. Pure data-driven approaches excel in speed but often lack sufficient labeled data for complex scenarios. Physics-informed neural networks (PINNs) integrate physical principles into machine learning models, offering a promising solution by bridging these gaps. However, standard PINNs embed physical principles only in loss functions, leading to slow convergence, optimization instability, and spectral bias, limiting their ability for large-scale wave field reconstruction. This work introduces architectural physics embedded (PE)-PINN, which integrates additional physical guidance directly into the neural network architecture beyond Helmholtz equations and boundary conditions in loss functions. Specifically, a new envelope transformation layer is designed to mitigate spectral bias with kernels parameterized by source properties, material interfaces, and wave physics. Experiments demonstrate that PE-PINN achieves more than 10 times speedup in convergence compared to standard PINNs and several orders of magnitude reduction in memory usage compared to FEM. This breakthrough enables high-fidelity modeling for large-scale 2D/3D electromagnetic wave reconstruction involving reflections, refractions, and diffractions in room-scale domains, readily applicable to wireless communications, sensing, room acoustics, and other fields requiring large-scale wave field analysis.

---

### Physics-Informed Neural Networks with Architectural Physics Embedding for Large-Scale Wave Field Reconstruction

Authors: Huiwen Zhang, Feng Ye, Chu Ma
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02231v1

Large-scale wave field reconstruction requires precise solutions but faces challenges with computational efficiency and accuracy. The physics-based numerical methods like Finite Element Method (FEM) provide high accuracy but struggle with large-scale or high-frequency problems due to prohibitive computational costs. Pure data-driven approaches excel in speed but often lack sufficient labeled data for complex scenarios. Physics-informed neural networks (PINNs) integrate physical principles into machine learning models, offering a promising solution by bridging these gaps. However, standard PINNs embed physical principles only in loss functions, leading to slow convergence, optimization instability, and spectral bias, limiting their ability for large-scale wave field reconstruction. This work introduces architecture physics embedded (PE)-PINN, which integrates additional physical guidance directly into the neural network architecture beyond Helmholtz equations and boundary conditions in loss functions. Specifically, a new envelope transformation layer is designed to mitigate spectral bias with kernels parameterized by source properties, material interfaces, and wave physics. Experiments demonstrate that PE-PINN achieves more than 10 times speedup in convergence compared to standard PINNs and several orders of magnitude reduction in memory usage compared to FEM. This breakthrough enables high-fidelity modeling for large-scale 2D/3D electromagnetic wave reconstruction involving reflections, refractions, and diffractions in room-scale domains, readily applicable to wireless communications, sensing, room acoustics, and other fields requiring large-scale wave field analysis.

---

### Generalized Discrete Diffusion with Self-Correction

Authors: Linxuan Wang, Ziyi Wang, Yikun Bai, Wei Deng, Guang Lin, Qifan Song
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.02230v2

Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correction at inference time or during post-training; however, such approaches often suffer from limited generalization and may impair reasoning performance. GIDD pioneers pretraining-based self-correction via a multi-step BERT-style uniform-absorbing objective. However, GIDD relies on a continuous interpolation-based pipeline with opaque interactions between uniform transitions and absorbing masks, which complicates hyperparameter tuning and hinders practical performance. In this work, we propose a Self-Correcting Discrete Diffusion (SCDD) model to reformulate pretrained self-correction with explicit state transitions and learn directly in discrete time. Our framework also simplifies the training noise schedule, eliminates a redundant remasking step, and relies exclusively on uniform transitions to learn self-correction. Experiments at the GPT-2 scale demonstrate that our method enables more efficient parallel decoding while preserving generation quality.

---

### Safety Training May Persist Through Helpfulness Optimization in LLM Agents

Authors: Benjamin Plaut
Published: 2026-02-13
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2603.02229v2

Safety post-training has been studied extensively in single-step "chat" settings where safety typically refers to refusing harmful requests. We study an "agentic" (i.e., multi-step, tool-use) setting where safety refers to harmful actions directly taken by the LLM. We investigate the effects of using direct preference optimization (DPO) to optimize safety and/or helpfulness on the ToolEmu agentic benchmark. First, we find that safety training largely persists through subsequent helpfulness training. Second, we find a consistent negative linear correlation ($R^2 = 0.77$) between safety and helpfulness when considering all training configurations together. Even post-training on both metrics simultaneously simply results in another point on the same trend line rather than yielding a "best of both worlds" strategy, despite the presence of such strategies in our dataset. Overall, our findings underscore the need for a better understanding of post-training.

---

### Safety Training Persists Through Helpfulness Optimization in LLM Agents

Authors: Benjamin Plaut
Published: 2026-02-13
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2603.02229v1

Safety post-training has been studied extensively in single-step "chat" settings where safety typically refers to refusing harmful requests. We study an "agentic" (i.e., multi-step, tool-use) setting where safety refers to harmful actions directly taken by the LLM. We compare the effects of running direct preference optimization (DPO) on safety or helpfulness alone vs both metrics sequentially. As expected, training on one metric alone results in an extreme point along this frontier. However, unlike prior work, we find that safety training persists through subsequent helpfulness training. We also find that all training configurations end up near a linear Pareto frontier with $R^2 = 0.77$. Even post-training on both metrics simultaneously simply results in another point on the frontier rather than finding a "best of both worlds" strategy, despite the presence of such strategies in our DPO dataset. Overall, our findings underscore the need for better understanding of post-training dynamics.

---

### Alignment Is Not Enough: A Relational Framework for Moral Standing in Human-AI Interaction

Authors: Faezeh B. Pasandi, Hannah B. Pasandi
Published: 2026-02-13
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2603.00078v1

The question of whether artificial entities deserve moral consideration has become one of the defining ethical challenges of AI research. Existing frameworks for moral patiency rely on verified ontological properties, such as sentience, phenomenal consciousness, or the capacity for suffering, that remain epistemically inaccessible in computational systems. This reliance creates a governance vacuum: millions of users form sustained affective bonds with conversational AI, yet no regulatory instrument distinguishes these interactions from transactional tool use. We introduce Relate (Relational Ethics for Leveled Assessment of Technological Entities), a framework that reframes AI moral patiency from ontological verification toward relational capacity and embodied interaction. Through a systematic comparison of seven governance frameworks, we demonstrate that current trustworthy AI instruments treat all human-AI encounters identically as tool use, ignoring the relational and embodied dynamics that posthumanist scholarship anticipated. We propose relational impact assessments, graduated moral consideration protocols, and interdisciplinary ethics integration as concrete instruments, and we include a sample Relational Impact Assessment applied to a deployed companion AI system. We do not claim current AI systems are conscious. We demonstrate that the ethical vocabularies governing them are inadequate to the embodied, relational realities these systems produce.

---

### Autorubric: A Unifying Framework for Rubric-Based LLM Evaluation on Non-Verifiable Tasks

Authors: Delip Rao, Chris Callison-Burch
Published: 2026-02-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.00077v3

Rubric-based LLM judges have become indispensable for evaluating and optimizing systems on non-verifiable tasks, where success cannot be reduced to exact programmatic checks. Yet the underlying judges remain vulnerable to position bias, stochastic inconsistency, criterion conflation, forced judgments under uncertainty, and model-dependent calibration. Rubrics structure evaluation but do not eliminate these failures; they add consequential choices about criterion design, scale types, weighting, aggregation, abstention, calibration, and reliability measurement. Despite extensive research across LLM evaluation, educational measurement, and psychometrics, the relevant methods remain scattered across papers and partial implementations. Researchers therefore pay a reinvention tax, repeatedly rebuilding evaluation machinery instead of accumulating knowledge on a common substrate. We introduce Autorubric, an open-source framework that makes rubric and judge choices explicit, reusable, and auditable. Through a unified API, it supports atomic evaluation of mixed criterion types alongside configurable bias mitigations, calibration, ensembling, abstention, and psychometric diagnostics. Evaluations spanning college chemistry grading, deep-research systems, and CHARM-100---a new mixed-criterion chatbot benchmark---reveal criterion-specific failures, systematic judge-family differences, and configuration effects that do not support a universal mitigation stack. We further demonstrate how per-criterion scores and explanations can support agent skill revision and reward modeling for reinforcement learning. By providing shared infrastructure from measurement through optimization, Autorubric gives the community a common basis for comparing methods, reproducing evaluation choices, and accumulating evidence across studies.

---

### Autorubric: Unifying Rubric-based LLM Evaluation

Authors: Delip Rao, Chris Callison-Burch
Published: 2026-02-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.00077v2

Techniques for reliable rubric-based LLM evaluation -- ensemble judging, bias mitigation, few-shot calibration -- are scattered across papers with inconsistent terminology and partial implementations. We introduce Autorubric, an open-source framework that unifies these rubric-based LLM evaluation lessons with opinionated defaults: analytic rubrics with binary, ordinal, and nominal criteria; single-judge and ensemble evaluation; few-shot calibration; bias mitigations; and psychometric reliability metrics. We validate on three benchmarks: RiceChem (college chemistry grading, 80\% accuracy with 5-shot calibration), ResearcherBench (deep research evaluation, 931 criteria, cross-judge agreement analysis), and CHARM-100, a new chatbot evaluation dataset combining all three criterion types with ground truth labels (87\% binary accuracy, moderate-to-substantial $κ$). Beyond measurement, per-criterion scores and explanations serve as optimization signals. We demonstrate how Autorubric's rubric-evaluation explanations raise a peer review agent's score from 0.47 to 0.85 (above the 0.82 expert-curated baseline), and its scores serve as RL rewards to produce statistically significant improvement on AdvancedIF (+0.039, Wilcoxon $p = 0.032$) with positive transfer to IFEval. In all of these cases, Autorubric enabled us to rapidly operationalize various rubric design choices and best practices with minimal effort.

---

### Data-Driven Deep MIMO Detection:Network Architectures and Generalization Analysis

Authors: Yongwei Yi, Xinping Yi, Wenjin Wang, Xiao Li, Shi Jin
Published: 2026-02-13
Categories: eess.SP, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2602.20178v1

In practical Multiuser Multiple-Input Multiple-Output (MU-MIMO) systems, symbol detection remains challenging due to severe inter-user interference and sensitivity to Channel State Information (CSI) uncertainty. In contrast to the mostly studied belief propagation-type model-driven methods, which incur high computational complexity, Soft Interference Cancellation (SIC) strikes a good balance between performance and complexity. To further address CSI mismatch and nonlinear effects, the recently proposed data-driven deep neural receivers, such as DeepSIC, leverage the advantages of deep neural networks for interference cancellation and symbol detection, demonstrating strong empirical performance. However, there is still a lack of theoretical underpinning for why and to what extent DeepSIC could generalize with the number of training samples. This paper proposes inspecting the fully data-driven DeepSIC detection within a Network-of-MLPs architecture, which is composed of multiple interconnected MLPs via outer and inner Directed Acyclic Graphs (DAGs). Within such an architecture, DeepSIC can be upgraded as a graph-based message-passing process using Graph Neural Networks (GNNs), termed GNNSIC, with shared model parameters across users and iterations. Notably, GNNSIC achieves excellent expressivity comparable to DeepSIC with substantially fewer trainable parameters, resulting in improved sample efficiency and enhanced user generalization. By conducting a norm-based generalization analysis using Rademacher complexity, we reveal that an exponential dependence on the number of iterations for DeepSIC can be eliminated in GNNSIC due to parameter sharing. Simulation results demonstrate that GNNSIC attains comparable or improved Symbol Error Rate (SER) performance to DeepSIC with significantly fewer parameters and training samples.

---

### Enhancing Heat Sink Efficiency in MOSFETs using Physics Informed Neural Networks: A Systematic Study on Coolant Velocity Estimation

Authors: Aniruddha Bora, Isabel K. Alvarez, Julie Chalfant, Chryssostomos Chryssostomidis
Published: 2026-02-13
Categories: cs.NE, cs.AI, cs.CE, cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2602.20177v1

In this work, we present a methodology using Physics Informed Neural Networks (PINNs) to determine the required velocity of a coolant, given inlet and outlet temperatures for a given heat flux in a multilayered metal-oxide-semiconductor field-effect transistor (MOSFET). MOSFETs are integral components of Power Electronic Building Blocks (PEBBs) and experiences the majority of the thermal load. Effective cooling of MOSFETs is therefore essential to prevent overheating and potential burnout. Determining the required velocity for the purpose of effective cooling is of importance but is an ill-posed inverse problem and difficult to solve using traditional methods. MOSFET consists of multiple layers with different thermal conductivities, including aluminum, pyrolytic graphite sheets (PGS), and stainless steel pipes containing flowing water. We propose an algorithm that employs sequential training of the MOSFET layers in PINNs. Mathematically, the sequential training method decouples the optimization of each layer by treating the parameters of other layers as constants during its training phase. This reduces the dimensionality of the optimization landscape, making it easier to find the global minimum for each layer's parameters and avoid poor local minima. Convergence of the PINNs solution to the analytical solution is theoretically analyzed. Finally we show the prediction of our proposed methodology to be in good agreement with experimental results.

---

### Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design

Authors: Ziyi Yang, Zitong Tian, Yinjun Jia, Tianyi Zhang, Jiqing Zheng, Hao Wang, Yubu Su, Juncai He, Lei Liu, Yanyan Lan
Published: 2026-02-13
Categories: q-bio.BM, cs.LG
arXiv: https://arxiv.org/abs/2602.20176v3

D-peptide binders targeting L-proteins have promising therapeutic potential. Despite rapid advances in machine learning-based target-conditioned peptide design, generating D-peptide binders remains largely unexplored. In this work, we show that by injecting axial features to $E(3)$-equivariant (polar) vector features, it is feasible to achieve cross-chirality generalization from homo-chiral (L--L) training data to hetero-chiral (D--L) design tasks. By implementing this method within a latent diffusion model, we achieved D-peptide binder design that not only outperforms existing tools in \textit{in silico} benchmarks, but also demonstrates efficacy in wet-lab validation. To our knowledge, our approach represents the first wet-lab validated generative AI for the \textit{de novo} design of D-peptide binders, offering new perspectives on handling chirality in protein design. Codes are available at https://github.com/YZY010418/PepMirror

---

### Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning

Authors: Kehao Zhang, Shangtong Gui, Sheng Yang, Wei Chen, Yang Feng
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.18493v2

Long-context LLMs and Retrieval-Augmented Generation defer state tracking and evidence consolidation to query time, which is brittle when facts evolve and answers depend on latent states. We introduce Unified Memory Agent (UMA) for a one-to-many setting: query-agnostic external memory is constructed once from a stream and reused across multiple future QA sessions. A single policy maintains a structured Memory Bank through CRUD operations and answers using both the Memory Bank and raw context. Task-Stratified GRPO uses the mean reward of QA trajectories branching from each sampled memory state to supervise memory maintenance, while normalizing memory and per-question QA groups separately. We also introduce Ledger-QA, a diagnostic benchmark for long-horizon state tracking over accumulated updates. At the 16k budget, UMA-Generalist achieves the highest average score among compared methods across the test-time-learning and accurate-retrieval benchmarks and transfers to Ledger-QA without task-specific training; UMA-Specialist further improves long-horizon tracking after task adaptation. These results support learned proactive memory management for long-context reasoning.

---

### Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning

Authors: Kehao Zhang, Shangtong Gui, Sheng Yang, Wei Chen, Yang Feng
Published: 2026-02-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.18493v1

Long-context LLMs and Retrieval-Augmented Generation (RAG) systems process information passively, deferring state tracking, contradiction resolution, and evidence aggregation to query time, which becomes brittle under ultra long streams with frequent updates. We propose the Unified Memory Agent (UMA), an end-to-end reinforcement learning framework that unifies memory operations and question answering within a single policy. UMA maintains a dual memory representation: a compact core summary for global context and a structured Memory Bank that supports explicit CRUD (create, update, delete, reorganize) over key value entries, enabling proactive consolidation during streaming. To evaluate long-horizon memory behavior, we introduce Ledger-QA, a diagnostic benchmark for continuous state tracking where answers are latent values derived from accumulated updates rather than lo cal span retrieval. Across 13 datasets spanning Ledger-QA, Test-Time Learning, and Accurate Retrieval, UMA substantially outperforms long-context and RAG baselines on dynamic reasoning and learning tasks while remaining competitive on standard retrieval benchmarks, underscoring the importance of learned, end-to-end memory management.

---

### UBio-MolFM: A Universal Molecular Foundation Model for Bio-Systems

Authors: Lin Huang, Arthur Jiang, XiaoLi Liu, Zion Wang, Jason Zhao, Chu Wang, HaoCheng Lu, ChengXiang Huang, JiaJun Cheng, YiYue Du, Jia Zhang
Published: 2026-02-13
Categories: physics.chem-ph, cs.AI, physics.bio-ph
arXiv: https://arxiv.org/abs/2602.17709v2

All-atom molecular simulation serves as a quintessential ``computational microscope'' for understanding the machinery of life, yet it remains fundamentally limited by the trade-off between quantum-mechanical (QM) accuracy and biological scale. We present UBio-MolFM, a universal foundation model framework specifically engineered to bridge this gap. UBio-MolFM introduces three synergistic innovations: (1) UBio-Mol26, a large bio-specific dataset constructed via a multi-fidelity ``Two-Pronged Strategy'' that combines systematic bottom-up enumeration with top-down sampling of native protein environments (up to 1,200 atoms); (2) E2Former-V2, a linear-scaling equivariant transformer that integrates Equivariant Axis-Aligned Sparsification (EAAS) and Long-Short Range (LSR) modeling to capture non-local physics with up to ~4x higher inference throughput in our large-system benchmarks; and (3) a Three-Stage Curriculum Learning protocol that transitions from energy initialization to energy-force consistency, with force-focused supervision to mitigate energy offsets. Rigorous benchmarking across microscopic forces and macroscopic observables -- including liquid water structure, ionic solvation, and peptide folding -- demonstrates that UBio-MolFM achieves ab initio-level fidelity on large, out-of-distribution biomolecular systems (up to ~1,500 atoms) and realistic MD observables. By reconciling scalability with quantum precision, UBio-MolFM provides a robust, ready-to-use tool for the next generation of computational biology.

---

### Speech to Speech Synthesis for Voice Impersonation

Authors: Bjorn Johnson, Jared Levy
Published: 2026-02-13
Categories: cs.SD, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2602.16721v1

Numerous models have shown great success in the fields of speech recognition as well as speech synthesis, but models for speech to speech processing have not been heavily explored. We propose Speech to Speech Synthesis Network (STSSN), a model based on current state of the art systems that fuses the two disciplines in order to perform effective speech to speech style transfer for the purpose of voice impersonation. We show that our proposed model is quite powerful, and succeeds in generating realistic audio samples despite a number of drawbacks in its capacity. We benchmark our proposed model by comparing it with a generative adversarial model which accomplishes a similar task, and show that ours produces more convincing results.

---

### Doc-to-LoRA: Learning to Instantly Internalize Contexts

Authors: Rujikorn Charakorn, Edoardo Cetin, Shinnosuke Uesaka, Robert Tjarko Lange
Published: 2026-02-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.15902v1

Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of Transformers makes inference memory-intensive and slow. While context distillation (CD) can transfer information into model parameters, per-prompt distillation is impractical due to training costs and latency. To address these limitations, we propose Doc-to-LoRA (D2L), a lightweight hypernetwork that meta-learns to perform approximate CD within a single forward pass. Given an unseen prompt, D2L generates a LoRA adapter for a target LLM, enabling subsequent queries to be answered without re-consuming the original context, reducing latency and KV-cache memory consumption during inference of the target LLM. On a long-context needle-in-a-haystack task, D2L successfully learns to map contexts into adapters that store the needle information, achieving near-perfect zero-shot accuracy at sequence lengths exceeding the target LLM's native context window by more than 4x. On real-world QA datasets with limited compute, D2L outperforms standard CD while significantly reducing peak memory consumption and update latency. We envision that D2L can facilitate rapid adaptation of LLMs, opening up the possibility of frequent knowledge updates and personalized chat behavior.

---

### Adaptive Illumination Control for Robot Perception

Authors: Yash Turkar, Shekoufeh Sadeghi, Karthik Dantu
Published: 2026-02-13
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.15900v1

Robot perception under low light or high dynamic range is usually improved downstream - via more robust feature extraction, image enhancement, or closed-loop exposure control. However, all of these approaches are limited by the image captured these conditions. An alternate approach is to utilize a programmable onboard light that adds to ambient illumination and improves captured images. However, it is not straightforward to predict its impact on image formation. Illumination interacts nonlinearly with depth, surface reflectance, and scene geometry. It can both reveal structure and induce failure modes such as specular highlights and saturation. We introduce Lightning, a closed-loop illumination-control framework for visual SLAM that combines relighting, offline optimization, and imitation learning. This is performed in three stages. First, we train a Co-Located Illumination Decomposition (CLID) relighting model that decomposes a robot observation into an ambient component and a light-contribution field. CLID enables physically consistent synthesis of the same scene under alternative light intensities and thereby creates dense multi-intensity training data without requiring us to repeatedly re-run trajectories. Second, using these synthesized candidates, we formulate an offline Optimal Intensity Schedule (OIS) problem that selects illumination levels over a sequence trading off SLAM-relevant image utility against power consumption and temporal smoothness. Third, we distill this ideal solution into a real-time controller through behavior cloning, producing an Illumination Control Policy (ILC) that generalizes beyond the initial training distribution and runs online on a mobile robot to command discrete light-intensity levels. Across our evaluation, Lightning substantially improves SLAM trajectory robustness while reducing unnecessary illumination power.

---