# Research Papers — 2026-02 · bundle page 66 of 210 > Full-text markdown of papers #3251–3300 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/66 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/65.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/67.md) ### ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning Authors: Hussein S. Al-Olimat, Ahmad Alshareef Published: 2026-02-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.17054v1 While recent Arabic NLP benchmarks focus on scale, they often rely on synthetic or translated data which may benefit from deeper linguistic verification. We introduce ALPS (Arabic Linguistic & Pragmatic Suite), a native, expert-curated diagnostic challenge set probing Deep Semantics and Pragmatics, capabilities that complement specialized large-scale benchmarks. While broad-coverage benchmarks prioritize scale and multi-task coverage, ALPS targets the depth of linguistic understanding through 531 rigorously crafted questions across 15 tasks and 47 subtasks. We developed the dataset with deep expertise in Arabic linguistics, guaranteeing cultural authenticity and eliminating translation artifacts. Evaluating 23 diverse models (commercial, open-source, and Arabic-native) against a single-pass human performance (avg. 84.6% accuracy) and an expert-adjudicated oracle (99.2%), we reveal a critical dissociation: models achieve high fluency but fail on fundamental morpho-syntactic dependencies, with elevated error rates on morpho-syntactic dependencies (36.5% across diacritics-reliant tasks) compared to compositional semantics. While top commercial models (Gemini-3-flash at 94.2%) surpass the average single human, a substantial gap persists between commercial giants and Arabic-native models, with the best Arabic-specific model (Jais-2-70B at 83.6%) approaching but not matching human performance. --- ### RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models Authors: Yunseok Han, Yejoon Lee, Jaeyoung Do Published: 2026-02-19 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.17053v3 Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true decision process, undermining reliability and trust. We introduce a formal framework for reasoning faithfulness, defined by two testable conditions: stance consistency (a coherent stance linking reasoning to answer) and causal influence (the stated reasoning causally drives the answer under output-level interventions), explicitly decoupled from accuracy. To operationalize this, we present RFEval, a benchmark of 7,186 instances across seven tasks that probes faithfulness via controlled, output-level counterfactual interventions. Evaluating twelve open-source LRMs, we find unfaithfulness in 49.7% of outputs, predominantly from stance inconsistency. Failures are concentrated in brittle, convergent domains such as math and code, and correlate more with post-training regimes than with scale: within-family ablations indicate that adding current RL-style objectives on top of supervised fine-tuning can reduce reasoning faithfulness, even when accuracy is maintained. Crucially, accuracy is neither a sufficient nor a reliable proxy for faithfulness: once controlling for model and task, the accuracy-faithfulness link is weak and statistically insignificant. Our work establishes a rigorous methodology for auditing LRM reliability and shows that trustworthy AI requires optimizing not only for correct outcomes but also for the structural integrity of the reasoning process. Our code and dataset can be found at project page: https://aidaslab.github.io/RFEval/ --- ### Evaluating Cross-Lingual Classification Approaches Enabling Topic Discovery for Multilingual Social Media Data Authors: Deepak Uniyal, Md Abul Bashar, Richi Nayak Published: 2026-02-19 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.17051v1 Analysing multilingual social media discourse remains a major challenge in natural language processing, particularly when large-scale public debates span across diverse languages. This study investigates how different approaches for cross-lingual text classification can support reliable analysis of global conversations. Using hydrogen energy as a case study, we analyse a decade-long dataset of over nine million tweets in English, Japanese, Hindi, and Korean (2013--2022) for topic discovery. The online keyword-driven data collection results in a significant amount of irrelevant content. We explore four approaches to filter relevant content: (1) translating English annotated data into target languages for building language-specific models for each target language, (2) translating unlabelled data appearing from all languages into English for creating a single model based on English annotations, (3) applying English fine-tuned multilingual transformers directly to each target language data, and (4) a hybrid strategy that combines translated annotations with multilingual training. Each approach is evaluated for its ability to filter hydrogen-related tweets from noisy keyword-based collections. Subsequently, topic modeling is performed to extract dominant themes within the relevant subsets. The results highlight key trade-offs between translation and multilingual approaches, offering actionable insights into optimising cross-lingual pipelines for large-scale social media analysis. --- ### Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenders Authors: Ziliang Zhao, Bi Xue, Emma Lin, Tianqi Lu, Mengjiao Zhou, Kaustubh Vartak, Shakhzod Ali-Zade, Tao Li, Bin Kuang, Rui Jian, Bin Wen, Dennis van der Staay et al. Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17050v3 Embedding tables are critical components of large-scale recommendation systems, facilitating the efficient mapping of high-cardinality categorical features into dense vector representations. However, as the volume of unique IDs expands, traditional hash-based indexing methods suffer from collisions that degrade model performance and personalization quality. We present Multi-Probe Zero Collision Hash (MPZCH), a novel indexing mechanism based on linear probing that effectively mitigates embedding collisions. With reasonable table sizing, it often eliminates these collisions entirely while maintaining production-scale efficiency. MPZCH utilizes auxiliary tensors and high-performance CUDA kernels to implement configurable probing and active eviction policies. By retiring obsolete IDs and resetting reassigned slots, MPZCH prevents the stale embedding inheritance typical of hash-based methods, ensuring new features learn effectively from scratch. Despite its collision-mitigation overhead, the system maintains training QPS and inference latency comparable to existing methods. Rigorous online experiments demonstrate that MPZCH achieves zero collisions for user embeddings and significantly improves item embedding freshness and quality. The solution has been released within the open-source TorchRec library for the broader community. --- ### IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agents Authors: Seoyoung Lee, Seobin Yoon, Seongbeen Lee, Yoojung Chun, Dayoung Park, Doyeon Kim, Joo Yong Sim Published: 2026-02-19 Categories: cs.AI, cs.HC, cs.RO arXiv: https://arxiv.org/abs/2602.17049v2 Computer-use agents operate over long horizons under noisy perception, multi-window contexts, evolving environment states. Existing approaches, from RL-based planners to trajectory retrieval, often drift from user intent and repeatedly solve routine subproblems, leading to error accumulation and inefficiency. We present IntentCUA, a multi-agent computer-use framework designed to stabilize long-horizon execution through intent-aligned plan memory. A Planner, Plan-Optimizer, and Critic coordinate over shared memory that abstracts raw interaction traces into multi-view intent representations and reusable skills. At runtime, intent prototypes retrieve subgroup-aligned skills and inject them into partial plans, reducing redundant re-planning and mitigating error propagation across desktop applications. In end-to-end evaluations, IntentCUA achieved a 74.83% task success rate with a Step Efficiency Ratio of 0.91, outperforming RL-based and trajectory-centric baselines. Ablations show that multi-view intent abstraction and shared plan memory jointly improve execution stability, with the cooperative multi-agent loop providing the largest gains on long-horizon tasks. These results highlight that system-level intent abstraction and memory-grounded coordination are key to reliable and efficient desktop automation in large, dynamic environments. --- ### StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection Authors: Joongwon Chae, Lihui Luo, Yang Liu, Runming Wang, Dongmei Yu, Zeming Liang, Xi Yuan, Dayan Zhang, Zhenglin Chen, Peiwu Qin, Ilmoon Chae Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17048v2 Max pooling is the de facto standard for converting anomaly score maps into image-level decisions in memory-bank-based unsupervised anomaly detection (UAD). However, because it relies on a single extreme response, it discards most information about how anomaly evidence is distributed and structured across the image, often causing normal and anomalous scores to overlap. We propose StructCore, a training-free, structure-aware image-level scoring method that goes beyond max pooling. Given an anomaly score map, StructCore computes a low-dimensional structural descriptor phi(S) that captures distributional and spatial characteristics, and refines image-level scoring via a diagonal Mahalanobis calibration estimated from train-good samples, without modifying pixel-level localization. StructCore achieves image-level AUROC scores of 99.6% on MVTec AD and 98.4% on VisA, demonstrating robust image-level anomaly detection by exploiting structural signatures missed by max pooling. --- ### Amber-Image: Efficient Compression of Large-Scale Diffusion Transformers Authors: Chaojie Yang, Tian Li, Yue Zhang, Jun Gao Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17047v1 Diffusion Transformer (DiT) architectures have significantly advanced Text-to-Image (T2I) generation but suffer from prohibitive computational costs and deployment barriers. To address these challenges, we propose an efficient compression framework that transforms the 60-layer dual-stream MMDiT-based Qwen-Image into lightweight models without training from scratch. Leveraging this framework, we introduce Amber-Image, a series of streamlined T2I models. We first derive Amber-Image-10B using a timestep-sensitive depth pruning strategy, where retained layers are reinitialized via local weight averaging and optimized through layer-wise distillation and full-parameter fine-tuning. Building on this, we develop Amber-Image-6B by introducing a hybrid-stream architecture that converts deep-layer dual streams into a single stream initialized from the image branch, further refined via progressive distillation and lightweight fine-tuning. Our approach reduces parameters by 70% and eliminates the need for large-scale data engineering. Notably, the entire compression and training pipeline-from the 10B to the 6B variant-requires fewer than 2,000 GPU hours, demonstrating exceptional cost-efficiency compared to training from scratch. Extensive evaluations on benchmarks like DPG-Bench and LongText-Bench show that Amber-Image achieves high-fidelity synthesis and superior text rendering, matching much larger models. --- ### Large Language Models Persuade Without Planning Theory of Mind Authors: Jared Moore, Rasmus Overmark, Ned Cooper, Beba Cibralic, Nick Haber, Cameron R. Jones Published: 2026-02-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.17045v2 A growing body of work attempts to evaluate the theory of mind (ToM) abilities of humans and large language models (LLMs) using static, non-interactive question-and-answer benchmarks. However, theoretical work in the field suggests that first-personal interaction is a crucial part of ToM and that such predictive, spectatorial tasks may fail to evaluate it. We address this gap with a novel ToM task that requires an agent to persuade a target to choose one of three policy proposals by strategically revealing information. Success depends on a persuader's sensitivity to a given target's knowledge states (what the target knows about the policies) and motivational states (how much the target values different outcomes). We varied whether these states were Revealed to persuaders or Hidden, in which case persuaders had to inquire about or infer them. In Experiment 1, participants persuaded a bot programmed to make only rational inferences. LLMs excelled in the Revealed condition but performed below chance in the Hidden condition, suggesting difficulty with the multi-step planning required to elicit and use mental state information. Humans performed moderately well in both conditions, indicating an ability to engage such planning. In Experiment 2, where a human target role-played the bot, and in Experiment 3, where we measured whether human targets' real beliefs changed, LLMs outperformed human persuaders across all conditions. These results suggest that effective persuasion can occur without explicit ToM reasoning (e.g., through rhetorical strategies) and that LLMs excel at this form of persuasion. Overall, our results caution against attributing human-like ToM to LLMs while highlighting LLMs' potential to influence people's beliefs and behavior. --- ### Large Language Models Persuade Without Planning Theory of Mind Authors: Jared Moore, Rasmus Overmark, Ned Cooper, Beba Cibralic, Nick Haber, Cameron R. Jones Published: 2026-02-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.17045v1 A growing body of work attempts to evaluate the theory of mind (ToM) abilities of humans and large language models (LLMs) using static, non-interactive question-and-answer benchmarks. However, theoretical work in the field suggests that first-personal interaction is a crucial part of ToM and that such predictive, spectatorial tasks may fail to evaluate it. We address this gap with a novel ToM task that requires an agent to persuade a target to choose one of three policy proposals by strategically revealing information. Success depends on a persuader's sensitivity to a given target's knowledge states (what the target knows about the policies) and motivational states (how much the target values different outcomes). We varied whether these states were Revealed to persuaders or Hidden, in which case persuaders had to inquire about or infer them. In Experiment 1, participants persuaded a bot programmed to make only rational inferences. LLMs excelled in the Revealed condition but performed below chance in the Hidden condition, suggesting difficulty with the multi-step planning required to elicit and use mental state information. Humans performed moderately well in both conditions, indicating an ability to engage such planning. In Experiment 2, where a human target role-played the bot, and in Experiment 3, where we measured whether human targets' real beliefs changed, LLMs outperformed human persuaders across all conditions. These results suggest that effective persuasion can occur without explicit ToM reasoning (e.g., through rhetorical strategies) and that LLMs excel at this form of persuasion. Overall, our results caution against attributing human-like ToM to LLMs while highlighting LLMs' potential to influence people's beliefs and behavior. --- ### Phase-Aware Mixture of Experts for Agentic Reinforcement Learning Authors: Shengtian Yang, Yu Li, Shuo He, Yewen Li, Qingpeng Cai, Peng Jiang, Lei Feng Published: 2026-02-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.17038v3 Reinforcement learning (RL) has equipped LLM agents with a strong ability to solve complex tasks. However, existing RL methods normally use a \emph{single} policy network, causing \emph{simplicity bias} where simple tasks occupy most parameters and dominate gradient updates, leaving insufficient capacity for complex tasks. A plausible remedy could be employing the Mixture-of-Experts (MoE) architecture in the policy network, as MoE allows different parameters (experts) to specialize in different tasks, preventing simple tasks from dominating all parameters. However, a key limitation of traditional MoE is its token-level routing, where the router assigns each token to specialized experts, which fragments phase-consistent patterns into scattered expert assignments and thus undermines expert specialization. In this paper, we propose \textbf{Phase-Aware Mixture of Experts (PA-MoE)}. It first features a lightweight \emph{phase router} that learns latent phase boundaries directly from the RL objective without pre-defining phase categories. Then, the phase router allocates temporally consistent assignments to the same expert, allowing experts to preserve phase-specific expertise. Experimental results demonstrate the effectiveness of our proposed PA-MoE. --- ### Wink: Recovering from Misbehaviors in Coding Agents Authors: Rahul Nanda, Chandra Maddila, Smriti Jha, Euna Mehnaz Khan, Matteo Paltenghi, Satish Chandra Published: 2026-02-19 Categories: cs.SE, cs.AI, cs.HC, cs.PL arXiv: https://arxiv.org/abs/2602.17037v2 Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the software industry to automate complex engineering tasks. However, these agents are prone to a wide range of misbehaviors, such as deviating from the user's instructions, getting stuck in repetitive loops, or failing to use tools correctly. These failures disrupt the development workflow and often require resource-intensive manual intervention. In this paper, we present a system for automatically recovering from agentic misbehaviors at scale. We first introduce a taxonomy of misbehaviors grounded in an analysis of production traffic, identifying three primary categories: Specification Drift, Reasoning Problems, and Tool Call Failures, which we find occur in about 30% of all agent trajectories. To address these issues, we developed a lightweight, asynchronous self-intervention system named Wink. Wink observes agent trajectories and provides targeted course-correction guidance to nudge the agent back to a productive path. We evaluated our system on over 10,000 real world agent trajectories and found that it successfully resolves 90% of the misbehaviors that require a single intervention. Furthermore, a live A/B test in our production environment demonstrated that our system leads to a statistically significant reduction in Tool Call Failures, Tokens per Session and Engineer Interventions per Session. We present our experience designing and deploying this system, offering insights into the challenges of building resilient agentic systems at scale. --- ### LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation Authors: Rong Fu, Zijian Zhang, Jiekai Wu, Kun Liu, Xianda Li, Haoyu Zhao, Yang Li, Yongtai Liu, Ziming Wang, Rui Lu, Simon Fong Published: 2026-02-19 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2602.17036v5 The continuous expansion of digital learning environments has catalyzed the demand for intelligent systems capable of providing personalized educational content. While current exercise recommendation frameworks have made significant strides, they frequently encounter obstacles regarding the long-tailed distribution of student engagement and the failure to adapt to idiosyncratic learning trajectories. We present LiveGraph, a novel active-structure neural re-ranking framework designed to overcome these limitations. Our approach utilizes a graph-based representation enhancement strategy to bridge the information gap between active and inactive students while integrating a dynamic re-ranking mechanism to foster content diversity. By prioritizing the structural relationships within learning histories, the proposed model effectively balances recommendation precision with pedagogical variety. Comprehensive experimental evaluations conducted on multiple real-world datasets demonstrate that LiveGraph surpasses contemporary baselines in both predictive accuracy and the breadth of exercise diversity. --- ### PartRAG: Retrieval-Augmented Part-Level 3D Generation and Editing Authors: Peize Li, Zeyu Zhang, Hao Tang Published: 2026-02-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17033v1 Single-image 3D generation with part-level structure remains challenging: learned priors struggle to cover the long tail of part geometries and maintain multi-view consistency, and existing systems provide limited support for precise, localized edits. We present PartRAG, a retrieval-augmented framework that integrates an external part database with a diffusion transformer to couple generation with an editable representation. To overcome the first challenge, we introduce a Hierarchical Contrastive Retrieval module that aligns dense image patches with 3D part latents at both part and object granularity, retrieving from a curated bank of 1,236 part-annotated assets to inject diverse, physically plausible exemplars into denoising. To overcome the second challenge, we add a masked, part-level editor that operates in a shared canonical space, enabling swaps, attribute refinements, and compositional updates without regenerating the whole object while preserving non-target parts and multi-view consistency. PartRAG achieves competitive results on Objaverse, ShapeNet, and ABO-reducing Chamfer Distance from 0.1726 to 0.1528 and raising F-Score from 0.7472 to 0.844 on Objaverse-with inference of 38s and interactive edits in 5-8s. Qualitatively, PartRAG produces sharper part boundaries, better thin-structure fidelity, and robust behavior on articulated objects. Code: https://github.com/AIGeeksGroup/PartRAG. Website: https://aigeeksgroup.github.io/PartRAG. --- ### Patch-Based Spatial Authorship Attribution in Human-Robot Collaborative Paintings Authors: Eric Chen, Patricia Alves-Oliveira Published: 2026-02-19 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.17030v1 As agentic AI becomes increasingly involved in creative production, documenting authorship has become critical for artists, collectors, and legal contexts. We present a patch-based framework for spatial authorship attribution within human-robot collaborative painting practice, demonstrated through a forensic case study of one human artist and one robotic system across 15 abstract paintings. Using commodity flatbed scanners and leave-one-painting-out cross-validation, the approach achieves 88.8% patch-level accuracy (86.7% painting-level via majority vote), outperforming texture-based and pretrained-feature baselines (68.0%-84.7%). For collaborative artworks, where ground truth is inherently ambiguous, we use conditional Shannon entropy to quantify stylistic overlap; manually annotated hybrid regions exhibit 64% higher uncertainty than pure paintings (p=0.003), suggesting the model detects mixed authorship rather than classification failure. The trained model is specific to this human-robot pair but provides a methodological grounding for sample-efficient attribution in data-scarce human-AI creative workflows that, in the future, has the potential to extend authorship attribution to any human-robot collaborative painting. --- ### Forecasting Anomaly Precursors via Uncertainty-Aware Time-Series Ensembles Authors: Hyeongwon Kang, Jinwoo Park, Seunghun Han, Pilsung Kang Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17028v1 Detecting anomalies in time-series data is critical in domains such as industrial operations, finance, and cybersecurity, where early identification of abnormal patterns is essential for ensuring system reliability and enabling preventive maintenance. However, most existing methods are reactive: they detect anomalies only after they occur and lack the capability to provide proactive early warning signals. In this paper, we propose FATE (Forecasting Anomalies with Time-series Ensembles), a novel unsupervised framework for detecting Precursors-of-Anomaly (PoA) by quantifying predictive uncertainty from a diverse ensemble of time-series forecasting models. Unlike prior approaches that rely on reconstruction errors or require ground-truth labels, FATE anticipates future values and leverages ensemble disagreement to signal early signs of potential anomalies without access to target values at inference time. To rigorously evaluate PoA detection, we introduce Precursor Time-series Aware Precision and Recall (PTaPR), a new metric that extends the traditional Time-series Aware Precision and Recall (TaPR) by jointly assessing segment-level accuracy, within-segment coverage, and temporal promptness of early predictions. This enables a more holistic assessment of early warning capabilities that existing metrics overlook. Experiments on five real-world benchmark datasets show that FATE achieves an average improvement of 19.9 percentage points in PTaPR AUC and 20.02 percentage points in early detection F1 score, outperforming baselines while requiring no anomaly labels. These results demonstrate the effectiveness and practicality of FATE for real-time unsupervised early warning in complex time-series environments. --- ### Transforming Behavioral Neuroscience Discovery with In-Context Learning and AI-Enhanced Tensor Methods Authors: Paimon Goulart, Jordan Steinhauser, Dawon Ahn, Kylene Shuler, Edward Korzus, Jia Chen, Evangelos E. Papalexakis Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17027v1 Scientific discovery pipelines typically involve complex, rigid, and time-consuming processes, from data preparation to analyzing and interpreting findings. Recent advances in AI have the potential to transform such pipelines in a way that domain experts can focus on interpreting and understanding findings, rather than debugging rigid pipelines or manually annotating data. As part of an active collaboration between data science/AI researchers and behavioral neuroscientists, we showcase an example AI-enhanced pipeline, specifically designed to transform and accelerate the way that the domain experts in the team are able to gain insights out of experimental data. The application at hand is in the domain of behavioral neuroscience, studying fear generalization in mice, an important problem whose progress can advance our understanding of clinically significant and often debilitating conditions such as PTSD (Post-Traumatic Stress Disorder). We identify the emerging paradigm of "In-Context Learning" (ICL) as a suitable interface for domain experts to automate parts of their pipeline without the need for or familiarity with AI model training and fine-tuning, and showcase its remarkable efficacy in data preparation and pattern interpretation. Also, we introduce novel AI-enhancements to tensor decomposition model, which allows for more seamless pattern discovery from the heterogeneous data in our application. We thoroughly evaluate our proposed pipeline experimentally, showcasing its superior performance compared to what is standard practice in the domain, as well as against reasonable ML baselines that do not fall under the ICL paradigm, to ensure that we are not compromising performance in our quest for a seamless and easy-to-use interface for domain experts. Finally, we demonstrate effective discovery, with results validated by the domain experts in the team. --- ### WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning Authors: Gagan Mundada, Zihan Huang, Rohan Surana, Sheldon Yu, Jennifer Yuntong Zhang, Xintong Li, Tong Yu, Lina Yao, Jingbo Shang, Julian McAuley, Junda Wu Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17025v1 Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled trajectories, extended deliberation can create more chances to realize relative gains, leading to inefficient reasoning and overthinking, and complicating the trade-off between correctness and rollout efficiency. Controlling this behavior is difficult in practice, considering (i) Length penalties are hard to calibrate because longer rollouts may reflect harder problems that require longer reasoning, penalizing tokens risks truncating useful reasoning along with redundant continuation; and (ii) supervision that directly indicates when to continue or stop is typically unavailable beyond final answer correctness. We propose Weakly Supervised GRPO (WS-GRPO), which improves rollout efficiency by converting terminal rewards into correctness-aware guidance over partial trajectories. Unlike global length penalties that are hard to calibrate, WS-GRPO trains a preference model from outcome-only correctness to produce prefix-level signals that indicate when additional continuation is beneficial. Thus, WS-GRPO supplies outcome-derived continue/stop guidance, reducing redundant deliberation while maintaining accuracy. We provide theoretical results and empirically show on reasoning benchmarks that WS-GRPO substantially reduces rollout length while remaining competitive with GRPO baselines. --- ### ReIn: Conversational Error Recovery with Reasoning Inception Authors: Takyoung Kim, Jinseok Nam, Chandrayee Basu, Xing Fan, Chengyuan Ma, Heng Ji, Gokhan Tur, Dilek Hakkani-Tür Published: 2026-02-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.17022v1 Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to unanticipated, user-induced errors. Rather than focusing on error prevention, this work focuses on error recovery, which necessitates the accurate diagnosis of erroneous dialogue contexts and execution of proper recovery plans. Under realistic constraints precluding model fine-tuning or prompt modification due to significant cost and time requirements, we explore whether agents can recover from contextually flawed interactions and how their behavior can be adapted without altering model parameters and prompts. To this end, we propose Reasoning Inception (ReIn), a test-time intervention method that plants an initial reasoning into the agent's decision-making process. Specifically, an external inception module identifies predefined errors within the dialogue context and generates recovery plans, which are subsequently integrated into the agent's internal reasoning process to guide corrective actions, without modifying its parameters or system prompts. We evaluate ReIn by systematically simulating conversational failure scenarios that directly hinder successful completion of user goals: user's ambiguous and unsupported requests. Across diverse combinations of agent models and inception modules, ReIn substantially improves task success and generalizes to unseen error types. Moreover, it consistently outperforms explicit prompt-modification approaches, underscoring its utility as an efficient, on-the-fly method. In-depth analysis of its operational mechanism, particularly in relation to instruction hierarchy, indicates that jointly defining recovery tools with ReIn can serve as a safe and effective strategy for improving the resilience of conversational agents without modifying the backbone models or system prompts. --- ### M2F: Automated Formalization of Mathematical Literature at Scale Authors: Zichen Wang, Wanli Ma, Zhenyu Ming, Gong Zhang, Kun Yuan, Zaiwen Wen Published: 2026-02-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.17016v1 Automated formalization of mathematics enables mechanical verification but remains limited to isolated theorems and short snippets. Scaling to textbooks and research papers is largely unaddressed, as it requires managing cross-file dependencies, resolving imports, and ensuring that entire projects compile end-to-end. We present M2F (Math-to-Formal), the first agentic framework for end-to-end, project-scale autoformalization in Lean. The framework operates in two stages. The statement compilation stage splits the document into atomic blocks, orders them via inferred dependencies, and repairs declaration skeletons until the project compiles, allowing placeholders in proofs. The proof repair stage closes these holes under fixed signatures using goal-conditioned local edits. Throughout both stages, M2F keeps the verifier in the loop, committing edits only when toolchain feedback confirms improvement. In approximately three weeks, M2F converts long-form mathematical sources into a project-scale Lean library of 153,853 lines from 479 pages textbooks on real analysis and convex analysis, fully formalized as Lean declarations with accompanying proofs. This represents textbook-scale formalization at a pace that would typically require months or years of expert effort. On FATE-H, we achieve $96\%$ proof success (vs.\ $80\%$ for a strong baseline). Together, these results demonstrate that practical, large-scale automated formalization of mathematical literature is within reach. The full generated Lean code from our runs is available at https://github.com/optsuite/ReasBook.git. --- ### Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning Authors: Nikunj Gupta, James Zachary Hare, Jesse Milzman, Rajgopal Kannan, Viktor Prasanna Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17009v2 Coordinating actions is the most fundamental form of cooperation in multi-agent reinforcement learning (MARL). Successful decentralized decision-making often depends not only on good individual actions, but on selecting compatible actions across agents to synchronize behavior, avoid conflicts, and satisfy global constraints. In this paper, we propose Action Graph Policies (AGP), that model dependencies among agents' available action choices. It constructs, what we call, \textit{coordination contexts}, that enable agents to condition their decisions on global action dependencies. Theoretically, we show that AGPs induce a strictly more expressive joint policy compared to fully independent policies and can realize coordinated joint actions that are provably more optimal than greedy execution even from centralized value-decomposition methods. Empirically, we show that AGP achieves 80-95\% success on canonical coordination tasks with partial observability and anti-coordination penalties, where other MARL methods reach only 10-25\%. We further demonstrate that AGP consistently outperforms these baselines in diverse multi-agent environments. --- ### Arcee Trinity Large Technical Report Authors: Varun Singh, Lucas Krauss, Sami Jaghouar, Matej Sirovatka, Charles Goddard, Fares Obied, Jack Min Ong, Jannik Straube, Fern, Aria Harley, Conner Stewart, Colin Kealty et al. Published: 2026-02-19 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.17004v1 We present the technical report for Arcee Trinity Large, a sparse Mixture-of-Experts model with 400B total parameters and 13B activated per token. Additionally, we report on Trinity Nano and Trinity Mini, with Trinity Nano having 6B total parameters with 1B activated per token, Trinity Mini having 26B total parameters with 3B activated per token. The models' modern architecture includes interleaved local and global attention, gated attention, depth-scaled sandwich norm, and sigmoid routing for Mixture-of-Experts. For Trinity Large, we also introduce a new MoE load balancing strategy titled Soft-clamped Momentum Expert Bias Updates (SMEBU). We train the models using the Muon optimizer. All three models completed training with zero loss spikes. Trinity Nano and Trinity Mini were pre-trained on 10 trillion tokens, and Trinity Large was pre-trained on 17 trillion tokens. The model checkpoints are available at https://huggingface.co/arcee-ai. --- ### Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History Authors: Serin Kim, Sangam Lee, Dongha Lee Published: 2026-02-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.17003v3 Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail of their intent, practical web agents must be able to interpret ambiguous queries by inferring user preferences and contexts. To address this challenge, we present Persona2Web, the first benchmark for evaluating personalized web agents on the real open web, built upon the clarify-to-personalize principle, which requires agents to resolve ambiguity based on user history rather than relying on explicit instructions. Persona2Web consists of: (1) user histories that reveal preferences implicitly over long time spans, (2) ambiguous queries that require agents to infer implicit user preferences, and (3) a reasoning-aware evaluation framework that enables fine-grained assessment of personalization. We conduct extensive experiments across various agent architectures, backbone models, history access schemes, and queries with varying ambiguity levels, revealing key challenges in personalized web agent behavior. For reproducibility, our codes and datasets are publicly available at https://serin-kimm.github.io/Persona2Web/. --- ### Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases Authors: Zhao Tan, Yiji Zhao, Shiyu Wang, Chang Xu, Yuxuan Liang, Xiping Liu, Shirui Pan, Ming Jin Published: 2026-02-19 Categories: cs.AI, cs.CL, cs.DB arXiv: https://arxiv.org/abs/2602.17001v3 Natural Language Querying for Time Series Databases (NLQ4TSDB) aims to assist non-expert users retrieve meaningful events, intervals, and summaries from massive temporal records. However, existing Text-to-SQL methods are not designed for continuous morphological intents such as shapes or anomalies, while time series models struggle to handle ultra-long histories. To address these challenges, we propose Sonar-TS, a neuro-symbolic framework that tackles NLQ4TSDB via a Search-Then-Verify pipeline. Analogous to active sonar, it utilizes a feature index to ping candidate windows via SQL, followed by generated Python programs to lock on and verify candidates against raw signals. To enable effective evaluation, we introduce NLQTSBench, the first large-scale benchmark designed for NLQ over TSDB-scale histories. Our experiments highlight the unique challenges within this domain and demonstrate that Sonar-TS effectively navigates complex temporal queries where traditional methods fail. This work presents the first systematic study of NLQ4TSDB, offering a general framework and evaluation standard to facilitate future research. --- ### Exploring LLMs for User Story Extraction from Mockups Authors: Diego Firmenich, Leandro Antonelli, Bruno Pazos, Fabricio Lozada, Leonardo Morales Published: 2026-02-19 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.16997v1 User stories are one of the most widely used artifacts in the software industry to define functional requirements. In parallel, the use of high-fidelity mockups facilitates end-user participation in defining their needs. In this work, we explore how combining these techniques with large language models (LLMs) enables agile and automated generation of user stories from mockups. To this end, we present a case study that analyzes the ability of LLMs to extract user stories from high-fidelity mockups, both with and without the inclusion of a glossary of the Language Extended Lexicon (LEL) in the prompts. Our results demonstrate that incorporating the LEL significantly enhances the accuracy and suitability of the generated user stories. This approach represents a step forward in the integration of AI into requirements engineering, with the potential to improve communication between users and developers. --- ### Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding Authors: Rahul Thomas, Teo Kitanovski, Micah Goldblum, Arka Pal Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.16994v1 Multi-path speculative decoding accelerates lossless sampling from a target model by using a cheaper draft model to generate a draft tree of tokens, and then applies a verification algorithm that accepts a subset of these. While prior work has proposed various verification algorithms for i.i.d rollouts, their relative performance under matched settings remains unclear. In this work, we firstly present a systematic evaluation of verification strategies across model families, tasks, and sampling regimes, and find that Traversal Verification dominates consistently, with OT-based methods lagging far behind. Our analysis uncovers that this occurs because OT-based methods achieve high multi-token acceptance near the root of the draft tree, while multi-token gains are most impactful deeper in the draft tree, where draft and target distributions diverge. Based on this insight, we propose delayed tree expansion, which drafts a partial single path, delaying the i.i.d. branching point. We show that delayed tree expansion preserves the target distribution and improves on root-node i.i.d rollouts. Further, we develop a dynamic neural selector that estimates the expected block efficiency of optimal-transport-based verification methods from draft and target features, enabling context-dependent expansion decisions. Our neural selector allows OT-based methods like SpecInfer to outperform Traversal Verification for the first time, achieving 5% higher average throughput across a wide range of models, datasets, and sampling settings. --- ### Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation Authors: Yan Wang, Yi Han, Lingfei Qian, Yueru He, Xueqing Peng, Dongji Feng, Zhuohan Xie, Vincent Jim Zhang, Rosie Guo, Fengran Mo, Jimin Huang, Yankai Chen et al. Published: 2026-02-19 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2602.16990v2 Most recommendation benchmarks evaluate how well a model imitates user behavior. In financial advisory, however, observed actions can be noisy or short-sighted under market volatility and may conflict with a user's long-term goals. Treating what users chose as the sole ground truth, therefore, conflates behavioral imitation with decision quality. We introduce Conv-FinRe, a conversational and longitudinal benchmark for stock recommendation that evaluates LLMs beyond behavior matching. Given an onboarding interview, step-wise market context, and advisory dialogues, models must generate rankings over a fixed investment horizon. Crucially, Conv-FinRe provides multi-view references that distinguish descriptive behavior from normative utility grounded in investor-specific risk preferences, enabling diagnosis of whether an LLM follows rational analysis, mimics user noise, or is driven by market momentum. We build the benchmark from real market data and human decision trajectories, instantiate controlled advisory conversations, and evaluate a suite of state-of-the-art LLMs. Results reveal a persistent tension between rational decision quality and behavioral alignment: models that perform well on utility-based ranking often fail to match user choices, whereas behaviorally aligned models can overfit short-term noise. The dataset is publicly released on Hugging Face, and the codebase is available on GitHub. --- ### Fundamental Limits of Black-Box Safety Evaluation: Information-Theoretic and Computational Barriers from Latent Context Conditioning Authors: Vishal Srivastava Published: 2026-02-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.16984v1 Black-box safety evaluation of AI systems assumes model behavior on test distributions reliably predicts deployment performance. We formalize and challenge this assumption through latent context-conditioned policies -- models whose outputs depend on unobserved internal variables that are rare under evaluation but prevalent under deployment. We establish fundamental limits showing that no black-box evaluator can reliably estimate deployment risk for such models. (1) Passive evaluation: For evaluators sampling i.i.d. from D_eval, we prove minimax lower bounds via Le Cam's method: any estimator incurs expected absolute error >= (5/24)*delta*L approximately 0.208*delta*L, where delta is trigger probability under deployment and L is the loss gap. (2) Adaptive evaluation: Using a hash-based trigger construction and Yao's minimax principle, worst-case error remains >= delta*L/16 even for fully adaptive querying when D_dep is supported over a sufficiently large domain; detection requires Theta(1/epsilon) queries. (3) Computational separation: Under trapdoor one-way function assumptions, deployment environments possessing privileged information can activate unsafe behaviors that any polynomial-time evaluator without the trapdoor cannot distinguish. For white-box probing, estimating deployment risk to accuracy epsilon_R requires O(1/(gamma^2 * epsilon_R^2)) samples, where gamma = alpha_0 + alpha_1 - 1 measures probe quality, and we provide explicit bias correction under probe error. Our results quantify when black-box testing is statistically underdetermined and provide explicit criteria for when additional safeguards -- architectural constraints, training-time guarantees, interpretability, and deployment monitoring -- are mathematically necessary for worst-case safety assurance. --- ### Discovering Universal Activation Directions for PII Leakage in Language Models Authors: Leo Marchyok, Zachary Coalson, Sungho Keum, Sooel Son, Sanghyun Hong Published: 2026-02-19 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2602.16980v1 Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information (PII) leakage, are represented and modulated within their hidden states. We present UniLeak, a mechanistic-interpretability framework that identifies universal activation directions: latent directions in a model's residual stream whose linear addition at inference time consistently increases the likelihood of generating PII across prompts. These model-specific directions generalize across contexts and amplify PII generation probability, with minimal impact on generation quality. UniLeak recovers such directions without access to training data or groundtruth PII, relying only on self-generated text. Across multiple models and datasets, steering along these universal directions substantially increases PII leakage compared to existing prompt-based extraction methods. Our results offer a new perspective on PII leakage: the superposition of a latent signal in the model's representations, enabling both risk amplification and mitigation. --- ### Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling Authors: Divyam Madaan, Sumit Chopra, Kyunghyun Cho Published: 2026-02-19 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.16979v1 Despite the recent success of Multimodal Large Language Models (MLLMs), existing approaches predominantly assume the availability of multiple modalities during training and inference. In practice, multimodal data is often incomplete because modalities may be missing, collected asynchronously, or available only for a subset of examples. In this work, we propose PRIMO, a supervised latent-variable imputation model that quantifies the predictive impact of any missing modality within the multimodal learning setting. PRIMO enables the use of all available training examples, whether modalities are complete or partial. Specifically, it models the missing modality through a latent variable that captures its relationship with the observed modality in the context of prediction. During inference, we draw many samples from the learned distribution over the missing modality to both obtain the marginal predictive distribution (for the purpose of prediction) and analyze the impact of the missing modalities on the prediction for each instance. We evaluate PRIMO on a synthetic XOR dataset, Audio-Vision MNIST, and MIMIC-III for mortality and ICD-9 prediction. Across all datasets, PRIMO obtains performance comparable to unimodal baselines when a modality is fully missing and to multimodal baselines when all modalities are available. PRIMO quantifies the predictive impact of a modality at the instance level using a variance-based metric computed from predictions across latent completions. We visually demonstrate how varying completions of the missing modality result in a set of plausible labels. --- ### Fail-Closed Alignment for Large Language Models Authors: Zachary Coalson, Beth Sohler, Aiden Gabriel, Sanghyun Hong Published: 2026-02-19 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2602.16977v1 We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant feature$-$via prompt-based jailbreaks$-$can cause alignment to collapse, leading to unsafe generation. Motivated by this, we propose fail-closed alignment as a design principle for robust LLM safety: refusal mechanisms should remain effective even under partial failures via redundant, independent causal pathways. We present a concrete instantiation of this principle: a progressive alignment framework that iteratively identifies and ablates previously learned refusal directions, forcing the model to reconstruct safety along new, independent subspaces. Across four jailbreak attacks, we achieve the strongest overall robustness while mitigating over-refusal and preserving generation quality, with small computational overhead. Our mechanistic analyses confirm that models trained with our method encode multiple, causally independent refusal directions that prompt-based jailbreaks cannot suppress simultaneously, providing empirical support for fail-closed alignment as a principled foundation for robust LLM safety. --- ### HQFS: Hybrid Quantum Classical Financial Security with VQC Forecasting, QUBO Annealing, and Audit-Ready Post-Quantum Signing Authors: Srikumar Nayak Published: 2026-02-19 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.16976v1 Here's the corrected paragraph with all punctuation and formatting issues fixed: Financial risk systems usually follow a two-step routine: a model predicts return or risk, and then an optimizer makes a decision such as a portfolio rebalance. In practice, this split can break under real constraints. The prediction model may look good, but the final decision can be unstable when the market shifts, when discrete constraints are added (lot sizes, caps), or when the optimization becomes slow for larger asset sets. Also, regulated settings need a clear audit trail that links each decision to the exact model state and inputs. We present HQFS, a practical hybrid pipeline that connects forecasting, discrete risk optimization, and auditability in one flow. First, HQFS learns next-step return and a volatility proxy using a variational quantum circuit (VQC) with a small classical head. Second, HQFS converts the risk-return objective and constraints into a QUBO and solves it with quantum annealing when available, while keeping a compatible classical QUBO solver as a fallback for deployment. Third, HQFS signs each rebalance output using a post-quantum signature so the allocation can be verified later without trusting the runtime environment. On our market dataset study, HQFS reduces return prediction error by 7.8% and volatility prediction error by 6.1% versus a tuned classical baseline. For the decision layer, HQFS improves out-of-sample Sharpe by 9.4% and lowers maximum drawdown by 11.7%. The QUBO solve stage also cuts average solve time by 28% compared to a mixed-integer baseline under the same constraints, while producing fully traceable, signed allocation records. --- ### DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers Authors: Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde Published: 2026-02-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.16968v1 Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses constant-sized patches throughout the entire denoising phase, regardless of the content's complexity. We propose dynamic tokenization, an efficient test-time strategy that varies patch sizes based on content complexity and the denoising timestep. Our key insight is that early timesteps only require coarser patches to model global structure, while later iterations demand finer (smaller-sized) patches to refine local details. During inference, our method dynamically reallocates patch sizes across denoising steps for image and video generation and substantially reduces cost while preserving perceptual generation quality. Extensive experiments demonstrate the effectiveness of our approach: it achieves up to $3.52\times$ and $3.2\times$ speedup on FLUX-1.Dev and Wan $2.1$, respectively, without compromising the generation quality and prompt adherence. --- ### Early-Warning Signals of Grokking via Loss-Landscape Geometry Authors: Yongzhong Xu Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.16967v3 Grokking -- the abrupt transition from memorization to generalization after prolonged training -- has been linked to confinement on low-dimensional execution manifolds in modular arithmetic. Whether this mechanism extends beyond arithmetic remains open. We study two sequence-learning benchmarks: SCAN compositional generalization and Dyck-1 depth prediction. Across both tasks and a wide range of learning rates, the commutator defect -- a curvature measure derived from non-commuting gradient updates -- rises well before generalization, with lead times following a superlinear power law (alpha approximately 1.18 for SCAN, approximately 1.13 for Dyck), consistent with prior results on modular arithmetic. Weight-space PCA reveals that spectral concentration is not a universal precursor; the commutator defect is. Causal interventions demonstrate a mechanistic role: amplifying non-commutativity accelerates grokking (roughly 32% on SCAN, roughly 50% on Dyck), while suppressing orthogonal gradient flow delays or prevents it. The three task families form a spectrum of causal sensitivity -- modular arithmetic is rigid, Dyck is responsive, SCAN is intermediate -- yet suppression delays or prevents grokking in all cases, establishing necessity as a universal finding. These results identify the commutator defect as a robust, architecture-agnostic, causally implicated early-warning signal for delayed generalization in transformers. --- ### A Unified Framework for Locality in Scalable MARL Authors: Sourav Chakraborty, Amit Kiran Rege, Claire Monteleoni, Lijun Chen Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.16966v2 Scalable methods for networked multi-agent reinforcement learning let each agent plan using only a small neighborhood of the agent graph. This works only when the system is value-local, meaning a perturbation at one agent affects the long-run value at another agent weakly when the two are far apart. In the average-reward setting, the standard way to certify locality is the Dobrushin row-sum bound on a single matrix $C^π$ that captures how each agent's next state depends on each other agent's current state. To make this matrix easy to work with, prior work bounds it by a supremum over joint actions. The resulting bound is independent of the policy, but it is loose whenever the policy never picks the worst-case action. We split $C^π$ into pieces that separately track environment sensitivity and policy sensitivity, $C^π\preceq E^{\mathrm s}+E^{\mathrm a}Π(π)$, where $E^{\mathrm s}$ measures how the next state moves with the current state, $E^{\mathrm a}$ measures how it moves with the current action, and $Π(π)$ measures how reactive the policy is to changes in state. The spectral radius of $H^π:= E^{\mathrm s}+E^{\mathrm a}Π(π)$ then controls the decay of the average-reward Poisson solution, and the spectral certificate $ρ(H^π)<1$ is strictly weaker than the row-sum condition $\|H^π\|_\infty<1$ on the same matrix and applies in regimes where policy-independent action-supremum bounds used in prior Dobrushin-style work cannot. For temperature-$τ$ softmax policies we get $Π(π)\le L/(2τ)$, so the softmax temperature directly controls locality. We use this decay result to give a deterministic oracle guarantee for a block-coordinate KL-proximal policy-improvement template whose truncation bias decays exponentially in the message-passing radius $κ$. --- ### Neuro-Symbolic Strong-AI Robots with Closed Knowledge Assumption: Learning and Deductions Authors: Zoran Majkic Published: 2026-02-18 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2604.09567v2 Knowledge representation formalisms are aimed to represent general conceptual information and are typically used in the construction of the knowledge base of reasoning agent. A knowledge base can be thought of as representing the beliefs of such an agent. Like a child, a strong-AI (AGI) robot would have to learn through input and experiences, constantly progressing and advancing its abilities over time. Both with statistical AI generated by neural networks we need also the concept of \textsl{causality} of events traduced into directionality of logic entailments and deductions in order to give to robots the emulation of human intelligence. Moreover, by using the axioms we can guarantee the \textsl{controlled security} about robot's actions based on logic inferences. For AGI robots we consider the 4-valued Belnap's bilattice of truth-values with knowledge ordering as well, where the value "unknown" is the bottom value, the sentences with this value are indeed unknown facts, that is, the missed knowledge in the AGI robots. Thus, these unknown facts are not part of the robot's knowledge database, and by learn through input and experiences, the robot's knowledge would be naturally expanded over time. Consequently, this phenomena can be represented by the Closed Knowledge Assumption and Logic Inference provided by this paper. Moreover, the truth-value "inconsistent", which is the top value in the knowledge ordering of Belnap's bilattice, is necessary for strong-AI robots to be able to support such inconsistent information and paradoxes, like Liar paradox, during deduction processes. --- ### LETGAMES: An LLM-Powered Gamified Approach to Cognitive Training for Patients with Cognitive Impairment Authors: Jingwei Shi, Shengyu Tao, Xinxiang Yin, Chen Huang, Wenqiang Lei, See-Kiong Ng Published: 2026-02-18 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.09566v1 The application of games as a therapeutic tool for cognitive training is beneficial for patients with cognitive impairments. However, effective game design for individual patient is resource-intensive. To this end, we propose an LLM-powered method, \ours, for automated and personalized therapeutic game design. Inspired by the Dungeons & Dragons, LETGAMES generates an open-world interactive narrative game. It not only generates game scenarios and challenges that target specific cognitive domains, but also employs conversational strategies to offer guidance and companionship. To validate its efficacy, we pioneer a psychology-grounded evaluation protocol LETGAMESEVAL, establishing comprehensive metrics for rehabilitative assessment. Building upon this, our experimental results from both LLM-based assessors and human expert evaluations demonstrate the significant potential of our approach, positioning LETGAMES as a promising solution to the widespread need for more accessible and tailored cognitive training tools. Our code will be open-sourced upon acceptance. --- ### AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems Authors: Hadar Mulian, Sergey Zeltyn, Ido Levy, Liane Galanti, Avi Yaeli, Segev Shlomov Published: 2026-02-18 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.29848v1 We introduce a comprehensive validation framework for LLM-based agentic systems that provides systematic diagnosis and improvement of reliability failures. The framework includes fifteen failure-detection tools and two root-cause analysis modules that jointly uncover weaknesses across input handling, prompt design, and output generation. It integrates lightweight rule-based checks with LLM-as-a-judge assessments to support structured incident detection, classification, and repair. We applied the framework to IBM CUGA, evaluating its performance on the AppWorld and WebArena benchmarks. The analysis revealed recurrent planner misalignments, schema violations, brittle prompt dependencies, and more. Based on these insights, we refined both prompting and coding strategies, maintaining CUGA's benchmark results while enabling mid-sized models such as Llama 4 and Mistral Medium to achieve notable accuracy gains, substantially narrowing the gap with frontier models. Beyond quantitative validation, we conducted an exploratory study that fed the framework's diagnostic outputs and agent description into an LLM for self-reflection and prioritization. This interactive analysis produced actionable insights on recurring failure patterns and focus areas for improvement, demonstrating how validation itself can evolve into an agentic, dialogue-driven process. These results show a path toward scalable, quality assurance, and adaptive validation in production agentic systems, offering a foundation for more robust, interpretable, and self-improving agentic architectures. --- ### CADReasoner: Iterative Program Editing for CAD Reverse Engineering Authors: Soslan Kabisov, Vsevolod Kirichuk, Andrey Volkov, Gennadii Savrasov, Marina Barannikov, Anton Konushin, Andrey Kuznetsov, Dmitrii Zhemchuzhnikov Published: 2026-02-18 Categories: cs.GR, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2603.29847v1 Computer-Aided Design (CAD) powers modern engineering, yet producing high-quality parts still demands substantial expert effort. Many AI systems tackle CAD reverse engineering, but most are single-pass and miss fine geometric details. In contrast, human engineers compare the input shape with the reconstruction and iteratively modify the design based on remaining discrepancies. Agent-based methods mimic this loop with frozen VLMs, but weak 3D grounding of current foundation models limits reliability and efficiency. We introduce CADReasoner, a model trained to iteratively refine its prediction using geometric discrepancy between the input and the predicted shape. The model outputs a runnable CadQuery Python program whose rendered mesh is fed back at the next step. CADReasoner fuses multi-view renders and point clouds as complementary modalities. To bridge the realism gap, we propose a scan-simulation protocol applied during both training and evaluation. Across DeepCAD, Fusion 360, and MCB benchmarks, CADReasoner attains state-of-the-art results on clean and scan-sim tracks. --- ### Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis Authors: Zhiyuan Cheng, Longying Lai, Yue Liu, Kai Cheng, Xiaoxi Qi Published: 2026-02-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.16877v2 Financial analysts face significant challenges extracting information from lengthy 10-K reports, which often exceed 100 pages. This paper presents a Retrieval-Augmented Generation (RAG) system designed to answer questions about S&P 500 financial reports and evaluates the impact of neural reranking on system performance. Our pipeline employs hybrid search combining full-text and semantic retrieval, followed by an optional reranking stage using a cross-encoder model. We conduct systematic evaluation using the FinDER benchmark dataset, comprising 1,500 queries across five experimental groups. Results demonstrate that reranking significantly improves answer quality, achieving 49.0 percent correctness for scores of 8 or above compared to 33.5 percent without reranking, representing a 15.5 percentage point improvement. Additionally, the error rate for completely incorrect answers decreases from 35.3 percent to 22.5 percent. Our findings emphasize the critical role of reranking in financial RAG systems and demonstrate performance improvements over baseline methods through modern language models and refined retrieval strategies. --- ### Gloss-Free Sign Language Translation: An Unbiased Evaluation of Progress in the Field Authors: Ozge Mercanoglu Sincan, Jian He Low, Sobhan Asasi, Richard Bowden Published: 2026-02-18 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2603.13240v1 Sign Language Translation (SLT) aims to automatically convert visual sign language videos into spoken language text and vice versa. While recent years have seen rapid progress, the true sources of performance improvements often remain unclear. Do reported performance gains come from methodological novelty, or from the choice of a different backbone, training optimizations, hyperparameter tuning, or even differences in the calculation of evaluation metrics? This paper presents a comprehensive study of recent gloss-free SLT models by re-implementing key contributions in a unified codebase. We ensure fair comparison by standardizing preprocessing, video encoders, and training setups across all methods. Our analysis shows that many of the performance gains reported in the literature often diminish when models are evaluated under consistent conditions, suggesting that implementation details and evaluation setups play a significant role in determining results. We make the codebase publicly available here (https://github.com/ozgemercanoglu/sltbaselines) to support transparency and reproducibility in SLT research. --- ### Aligning Language Models from User Interactions Authors: Thomas Kleine Buening, Jonas Hübotter, Barna Pásztor, Idan Shenfeld, Giorgia Ramponi, Andreas Krause Published: 2026-02-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.12273v1 Multi-turn user interactions are among the most abundant data produced by language models, yet we lack effective methods to learn from them. While typically discarded, these interactions often contain useful information: follow-up user messages may indicate that a response was incorrect, failed to follow an instruction, or did not align with the user's preferences. Importantly, language models are already able to make use of this information in context. After observing a user's follow-up, the same model is often able to revise its behavior. We leverage this ability to propose a principled and scalable method for learning directly from user interactions through self-distillation. By conditioning the model on the user's follow-up message and comparing the resulting token distribution with the original policy, we obtain a target for updating the policy that captures how the model's behavior changes in hindsight. We then distill this hindsight distribution back into the current policy. Remarkably, we show that training on real-world user conversations from WildChat improves language models across standard alignment and instruction-following benchmarks, without regressing other capabilities. The same mechanism enables personalization, allowing models to continually adapt to individual users through interaction without explicit feedback. Our results demonstrate that raw user interactions that arise naturally during deployment enable alignment, personalization, and continual adaptation. --- ### ActTail: Global Activation Sparsity in Large Language Models Authors: Wenwen Hou, Xinyuan Song, Shiwei Liu Published: 2026-02-18 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.12272v1 Activation sparsity is a promising approach for accelerating large language model (LLM) inference by reducing computation and memory movement. However, existing activation sparsity methods typically apply uniform sparsity across projections, ignoring the heterogeneous statistical properties of Transformer weights and thereby amplifying performance degradation. In this paper, we propose ActTail, a TopK magnitude-based activation sparsity method with global activation sparsity allocation grounded in Heavy-Tailed Self-Regularization (HT-SR) theory. Specifically, we capture this heterogeneity via the heavy-tail exponent computed from each projection's empirical spectral density (ESD), which is used as a quantitative indicator to assign projection-specific sparsity budgets. Importantly, we provide a theoretical analysis that establishes an explicit relationship between the activation sparsity ratio and the heavy-tail exponent under the HT-SR regime, offering principled guidance for sparsity allocation beyond heuristic design. Experiments on LLaMA and Mistral models show that our method improves both perplexity and downstream task performance at high sparsity compared to uniform allocation. At 80% sparsity, perplexity is reduced by 21.8% on LLaMA-2-7B, 40.1% on LLaMA-2-13B, and 9.4% on Mistral-7B. --- ### Diagnosing Retrieval Bias Under Multiple In-Context Knowledge Updates in Large Language Models Authors: Boyu Qiao, Sean Guo, Xian Yang, Kun Li, Wei Zhou, Songlin Hu, Yunya Song Published: 2026-02-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.12271v1 LLMs are widely used in knowledge-intensive tasks where the same fact may be revised multiple times within context. Unlike prior work focusing on one-shot updates or single conflicts, multi-update scenarios contain multiple historically valid versions that compete at retrieval, yet remain underexplored. This challenge resembles the AB-AC interference paradigm in cognitive psychology: when the same cue A is successively associated with B and C, the old and new associations compete during retrieval, leading to bias. Inspired by this, we introduce a Dynamic Knowledge Instance (DKI) evaluation framework, modeling multi-updates of the same fact as a cue paired with a sequence of updated values, and assess models via endpoint probing of the earliest (initial) and latest (current) states. Across diverse LLMs, we observe that retrieval bias intensifies as updates increase, earliest-state accuracy stays high while latest-state accuracy drops substantially. Diagnostic analyses of attention, hidden-state similarity, and output logits further reveal that these signals become flatter and weakly discriminative on errors, providing little stable basis for identifying the latest update. Finally, cognitively inspired heuristic intervention strategies yield only modest gains and do not eliminate the bias. Our results reveal a persistent challenge in tracking and following knowledge updates in long contexts. --- ### Task-Specific Knowledge Distillation via Intermediate Probes Authors: Ryan Brown, Chris Russell Published: 2026-02-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.12270v1 Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations may encode the correct answer, yet this information is lost or distorted through the vocabulary projection, where prompt formatting and answer-token choices creates brittle, noisy outputs. We introduce \method{}, a distillation framework that bypasses this bottleneck by training lightweight probes on frozen teacher hidden states and using the probe's predictions, rather than output logits, as supervision for student training. This simple change yields consistent improvements across four reasoning benchmarks (AQuA-RAT, ARC Easy/Challenge, and MMLU), with gains most pronounced under limited data. Probes trained on intermediate representations provide cleaner labels than the teacher's own outputs, effectively denoising the distillation signal. \method{} requires no architectural changes to student or teacher, is architecture-agnostic, and adds minimal compute since probe training is cheap and teacher representations can be cached. By exploiting internal representations, \method{} enables practitioners to extract more value from large teacher models without additional training data or architectural complexity. --- ### Measuring and Eliminating Refusals in Military Large Language Models Authors: Jack FitzGerald, Dylan Bates, Aristotelis Lazaridis, Aman Sharma, Vincent Lu, Brian King, Yousif Azami, Sean Bailey, Jeremy Cao, Peter Damianov, Kevin de Haan, Joseph Madigan et al. Published: 2026-02-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.10012v1 Military Large Language Models (LLMs) must provide accurate information to the warfighter in time-critical and dangerous situations. However, today's LLMs are imbued with safety behaviors that cause the LLM to refuse many legitimate queries in the military domain, particularly those related to violence, terrorism, or military technology. Our gold benchmark for assessing refusal rates, which was developed by veterans of the US Army and special forces, is to our knowledge the first dataset of its kind. We present results for refusal and deflection rates on 31 public models and 3 military models. We observe hard rejection rates as high as 98.2% and soft deflection rates ranging from 0% to 21.3%. We also present results on two additional synthetic datasets and show their correlations with the gold dataset. Finally, we perform abliteration using the Heretic library on a military-tuned gpt-oss-20b model, showing an absolute increase in answer rate of 66.5 points but an average relative decrease of 2% on other military tasks. In our concluding remarks, we argue for deeper specialization, including with mid-training and end-to-end post-training, to achieve zero refusals and maximum military task accuracy for closed military models. --- ### Data-Rate-Aware High-Speed CNN Inference on FPGAs Authors: Tobias Habermann, Martin Kumm Published: 2026-02-18 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2603.08726v1 Dataflow-based CNN accelerators on FPGAs achieve low latency and high throughput by mapping computations of each layer directly to corresponding hardware units. However, layers such as pooling and strided convolutions reduce the data at their output with respect to their input, strongly effecting the data rate of the following layers. This leads to underutilization in fully unrolled designs. While prior work introduced data-rate-aware layer-wise adaptation, determining the most efficient implementation remains challenging. This paper presents a data-rate-aware CNN accelerator architecture for multi-pixel processing. Building on existing analytical models, the proposed method performs design-space exploration to identify configurations that improve hardware utilization and resource efficiency while preserving continuous flow of data, keeping all hardware units busy. Experimental results show substantial reductions in arithmetic resources compared to previous designs, enabling efficient implementation of complex CNNs on a single FPGA across a wide range of data rates. --- ### Performance Analysis of Edge and In-Sensor AI Processors: A Comparative Review Authors: Luigi Capogrosso, Pietro Bonazzi, Michele Magno Published: 2026-02-18 Categories: cs.AR, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.08725v1 This review examines the rapidly evolving landscape of ultra-low-power edge processors, covering heterogeneous Systems-on-Chips (SoCs), neural accelerators, near-sensor and in-sensor architectures, and emerging dataflow and memory-centric designs. We categorize commercially available and research-grade platforms according to their compute paradigms, power envelopes, and memory hierarchies, and analyze their suitability for always-on and latency-critical Artificial Intelligence (AI) workloads. To complement the architectural overview with empirical evidence, we benchmark a 336 million Multiply-Accumulate (MAC) segmentation model (PicoSAM2) on three representative processors: GAP9, leveraging a multi-core RISC-V architecture augmented with hardware accelerators; the STM32N6, which pairs an advanced ARM Cortex-M55 core with a dedicated neural architecture accelerator; and the Sony IMX500, representing in-sensor stacked-Complementary Metal-Oxide-Semiconductor (CMOS) compute. Collectively, these platforms span MCU-class, embedded neural accelerator, and in-sensor paradigms. The evaluation reports latency, inference efficiency, energy efficiency, and energy-delay product. The results show a clear divergence in hardware behavior, with the IMX500 achieving the highest utilization (86.2 MAC/cycle) and the lowest energy-delay product, highlighting the growing significance and technological maturity of in-sensor processing. GAP9 offers the best energy efficiency within microcontroller-class power budgets, and the STM32N6 provides the lowest raw latency at a significantly higher energy cost. Together, the review and benchmarks provide a unified view of the current design directions and practical trade-offs that are shaping the next generation of ultra-low-power and in-sensor AI processors. --- ### Multi-Agent Reinforcement Learning for V2X Resource Allocation: Disentangling MARL Challenges Through Benchmarking Authors: Siyuan Wang, Lei Lei, Pranav Maheshwari, Sam Bellefeuille, Kan Zheng Published: 2026-02-18 Categories: cs.MA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.06607v2 Radio resource allocation (RRA) is a critical function in cellular vehicle-to-everything (C-V2X) networks, where vehicles must share limited wireless resources to support safety-critical communications. Multi-agent reinforcement learning (MARL) has emerged as a promising approach for this problem. However, key MARL challenges, including non-stationarity, coordination difficulty, large action space, partial observability, and limited robustness and generalization, are often intertwined, making it difficult to assess their individual impact on performance in vehicular environments. Moreover, existing studies primarily focus on developing new algorithms, while systematic benchmarking and comparative analyses remain limited. To address this gap, we formulate C-V2X RRA as a hierarchy of multi-agent interference games that progressively introduce key MARL challenges. Based on this framework, we develop a suite of benchmark learning tasks and construct training and testing datasets from SUMO-generated highway traces with diverse vehicular topologies and interference conditions. Using the proposed benchmark, we evaluate representative MARL algorithms spanning value-based, actor-critic, Independent Learning (IL), and Centralized Training with Decentralized Execution (CTDE) paradigms. The results identify robustness and generalization across diverse vehicular topologies as the dominant challenge among those considered in this work, reducing average normalized return by up to 59 percentage points, and show that, on the most challenging task, the best actor-critic method outperforms the best value-based method by 42\%. By revealing the relative strengths and limitations of different MARL paradigms and open-sourcing the code, datasets, and benchmark suite, this work provides a systematic and reproducible foundation for evaluating and advancing MARL algorithms in vehicular networks. --- ### LegoNet: Memory Footprint Reduction Through Block Weight Clustering Authors: Joseph Bingham, Noah Green, Saman Zonouz Published: 2026-02-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06606v1 As the need for neural network-based applications to become more accurate and powerful grows, so too does their size and memory footprint. With embedded devices, whose cache and RAM are limited, this growth hinders their ability to leverage state-of-the-art neural network architectures. In this work, we propose \textbf{LegoNet}, a compression technique that \textbf{constructs blocks of weights of the entire model regardless of layer type} and clusters these induced blocks. Using blocks instead of individual values to cluster the weights, we were able to compress ResNet-50 trained for Cifar-10 and ImageNet with only 32 4x4 blocks, compressing the memory footprint by over a factor of \textbf{64x without having to remove any weights} or changing the architecture and \textbf{no loss to accuracy}, nor retraining or any data, and show how to find an arrangement of 16 4x4 blocks that gives a compression ratio of \textbf{128x with less than 3\% accuracy loss}. This was all achieved with \textbf{no need for (re)training or fine-tuning}. --- ### Structure-Aware Set Transformers: Temporal and Variable-Type Attention Biases for Asynchronous Clinical Time Series Authors: Joohyung Lee, Kwanhyung Lee, Changhun Kim, Eunho Yang Published: 2026-02-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06605v2 Electronic health records (EHR) are irregular, asynchronous multivariate time series. As time-series foundation models increasingly tokenize events rather than discretizing time, the input layout becomes a key design choice. Grids expose time$\times$variable structure but require imputation or missingness masks, risking error or sampling-policy shortcuts. Point-set tokenization avoids discretization but loses within-variable trajectories and time-local cross-variable context (Fig.1). We restore these priors in STructure-AwaRe (STAR) Set Transformer by adding parameter-efficient soft attention biases: a temporal locality penalty $-|Δt|/τ$ with learnable timescales and a variable-type affinity $B_{s_i,s_j}$ from a learned feature-compatibility matrix. We benchmark 10 depth-wise fusion schedules (Fig.2). On three ICU prediction tasks, STAR-Set achieves AUC/APR of 0.7158/0.0026 (CPR), 0.9164/0.2033 (mortality), and 0.8373/0.1258 (vasopressor use), outperforming regular-grid, event-time grid, and prior set baselines. Learned $τ$ and $B$ provide interpretable summaries of temporal context and variable interactions, offering a practical plug-in for context-informed time-series models. ---