February 2026

arXiv:2602.15206v1 Announce Type: new Abstract: Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as demonstrations, comparisons, ratings, and stops that provide qualitatively different signals. We address this challenge by formulating reward learning from multiple feedback types as Bayesian inference over a shared latent reward function, where each feedback type contributes information through […]

Ver mais

arXiv:2602.15204v1 Announce Type: new Abstract: This paper presents a distributed memory method for anisotropic mesh adaptation that is designed to avoid the use of collective communication and global synchronization techniques. In the presented method, meshing functionality is separated from performance aspects by utilizing a separate entity for each – a multicore cc-NUMA-based (shared memory) mesh generation software and a parallel runtime system that is designed to help applications leverage the concurrency offered by emerging high-performance computing (HPC) architectures. […]

Ver mais

arXiv:2602.15201v1 Announce Type: new Abstract: Dexterous grasping is fundamental to robotics, yet data-driven grasp prediction heavily relies on large, diverse datasets that are costly to generate and typically limited to a narrow set of gripper morphologies. Analytical grasp synthesis can be used to scale data collection, but necessary simplifying assumptions often yield physically infeasible grasps that need to be filtered in high-fidelity simulators, significantly reducing the total number of grasps and their diversity. We propose a scalable generate-and-refine […]

Ver mais

arXiv:2602.15200v1 Announce Type: new Abstract: Post-training compression of Transformer models commonly relies on truncated singular value decomposition (SVD). However, enforcing a single shared subspace can degrade accuracy even at moderate compression. Sparse dictionary learning provides a more flexible union-of-subspaces representation, but existing approaches often suffer from iterative dictionary and coefficient updates. We propose COMPOT (Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers), a training-free compression framework that uses a small calibration dataset to estimate a sparse weight factorization. COMPOT employs […]

Ver mais

arXiv:2602.15198v1 Announce Type: new Abstract: Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety problem when individual agents form a coalition and emph{collude} to pursue secondary goals and degrade the joint objective. In this paper, we present Colosseum, a framework for auditing LLM agents’ collusive behavior in multi-agent settings. We ground how agents cooperate through a Distributed Constraint Optimization Problem (DCOP) and measure collusion via […]

Ver mais

arXiv:2602.15197v1 Announce Type: new Abstract: Tool-calling is essential for Large Language Model (LLM) agents to complete real-world tasks. While most existing benchmarks assume simple, perfectly documented tools, real-world tools (e.g., general “search” APIs) are often opaque, lacking clear best practices or failure modes. Can LLM agents improve their performance in environments with opaque tools by interacting and subsequently improving documentation? To study this, we create OpaqueToolsBench, a benchmark consisting of three distinct task-oriented environments: general function calling, interactive […]

Ver mais

arXiv:2602.15195v1 Announce Type: new Abstract: LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub citep{huggingface_hub_docs}, making them vulnerable to backdoor attacks. Current detection methods require running the model with test input data — making them impractical for screening thousands of adapters where the trigger for backdoor behavior is unknown. We detect poisoned adapters by analyzing their weight matrices directly, without running the model — making […]

Ver mais

arXiv:2602.15193v1 Announce Type: new Abstract: We study equivalence, in the context of a variable diffusion problem, between (conforming) mixed methods and (primal) nonconforming methods defined on potentially general polytopal partitions. In this first paper of a series of two, we focus on multiscale and projection methods. For multiscale methods, we establish the first-level equivalence between four different (oversampling-free) approaches, thereby broadening the results of [Chaumont-Frelet, Ern, Lemaire, Valentin; M2AN, 2022]. For projection methods, in turn, we provide a […]

Ver mais

arXiv:2602.15190v1 Announce Type: new Abstract: In this paper, we present our 3rd place system in the AVerImaTeC shared task, which combines our last year’s retrieval-augmented generation (RAG) pipeline with a reverse image search (RIS) module. Despite its simplicity, our system delivers competitive performance with a single multimodal LLM call per fact-check at just $0.013 on average using GPT5.1 via OpenAI Batch API. Our system is also easy to reproduce and tweak, consisting of only three decoupled modules – […]

Ver mais

arXiv:2602.15189v1 Announce Type: new Abstract: The use of large language models for web information extraction is becoming increasingly fundamental to modern web information retrieval pipelines. However, existing datasets tend to be small, synthetic or text-only, failing to capture the structural context of the web. We introduce ScrapeGraphAI-100k, a large-scale dataset comprising real-world LLM extraction events, collected via opt-in ScrapeGraphAI telemetry during Q2 and Q3 of 2025. Starting from 9M events, we deduplicate and balance by schema to produce […]

Ver mais