Scaling View Synthesis Transformers
arXiv:2602.21341v1 Announce Type: cross Abstract: Geometry-free view synthesis transformers have recently achieved state-of-the-art performance in Novel View Synthesis (NVS), outperforming traditional approaches that rely on explicit geometry modeling. Yet the factors governing their scaling with compute remain unclear. We present...
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
arXiv:2602.21346v1 Announce Type: cross Abstract: Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However, these LLMs remain vulnerable...
Towards Controllable Video Synthesis of Routine and Rare OR Events
arXiv:2602.21365v1 Announce Type: cross Abstract: Purpose: Curating large-scale datasets of operating room (OR) workflow, encompassing rare, safety-critical, or atypical events, remains operationally and ethically challenging. This data bottleneck complicates the development of ambient intelligence for detecting, understanding, and mitigating rare...
Black-Box Reliability Certification for AI Agents via Self-Consistency Sampling and Conformal Calibration
arXiv:2602.21368v1 Announce Type: cross Abstract: Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We answer with a reliability level -- a single number per system-task pair, derived from self-consistency...
MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation
arXiv:2602.21379v1 Announce Type: cross Abstract: We introduce MrBERT, a family of 150M-300M parameter encoders built on the ModernBERT architecture and pre-trained on 35 languages and code. Through targeted adaptation, this model family achieves state-of-the-art results on Catalan- and Spanish-specific tasks,...
FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning
arXiv:2602.21399v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data. However, data heterogeneity across clients leads to client drift, which degrades the overall generalization performance of the model. This effect...
Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation
arXiv:2602.22215v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate potential in the field of scientific idea generation. However, the generated results often lack controllable academic context and traceable inspiration pathways. To bridge this gap, this paper proposes a scientific...
FIRE: A Comprehensive Benchmark for Financial Intelligence and Reasoning Evaluation
arXiv:2602.22273v1 Announce Type: new Abstract: We introduce FIRE, a comprehensive benchmark designed to evaluate both the theoretical financial knowledge of LLMs and their ability to handle practical business scenarios. For theoretical assessment, we curate a diverse set of examination questions...
Vibe Researching as Wolf Coming: Can AI Agents with Skills Replace or Augment Social Scientists?
arXiv:2602.22401v1 Announce Type: new Abstract: AI agents -- systems that execute multi-step reasoning workflows with persistent state, tool access, and specialist skills -- represent a qualitative shift from prior automation technologies in social science. Unlike chatbots that respond to isolated...
Towards Autonomous Memory Agents
arXiv:2602.22406v1 Announce Type: new Abstract: Recent memory agents improve LLMs by extracting experiences and conversation history into an external storage. This enables low-overhead context assembly and online memory update without expensive LLM training. However, existing solutions remain passive and reactive;...
Exploring Human Behavior During Abstract Rule Inference and Problem Solving with the Cognitive Abstraction and Reasoning Corpus
arXiv:2602.22408v1 Announce Type: new Abstract: Humans exhibit remarkable flexibility in abstract reasoning, and can rapidly learn and apply rules from sparse examples. To investigate the cognitive strategies underlying this ability, we introduce the Cognitive Abstraction and Reasoning Corpus (CogARC), a...
Epistemic Filtering and Collective Hallucination: A Jury Theorem for Confidence-Calibrated Agents
arXiv:2602.22413v1 Announce Type: new Abstract: We investigate the collective accuracy of heterogeneous agents who learn to estimate their own reliability over time and selectively abstain from voting. While classical epistemic voting results, such as the \textit{Condorcet Jury Theorem} (CJT), assume...
How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
arXiv:2602.22441v1 Announce Type: new Abstract: Latent reasoning has been recently proposed as a reasoning paradigm and performs multi-step reasoning through generating steps in the latent space instead of the textual space. This paradigm enables reasoning beyond discrete language tokens by...
CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines
arXiv:2602.22452v1 Announce Type: new Abstract: A reliable action feasibility scorer is a critical bottleneck in embodied agent pipelines: before any planning or reasoning occurs, the agent must identify which candidate actions are physically executable in the current state. Existing approaches...
ConstraintBench: Benchmarking LLM Constraint Reasoning on Direct Optimization
arXiv:2602.22465v1 Announce Type: new Abstract: Large language models are increasingly applied to operational decision-making where the underlying structure is constrained optimization. Existing benchmarks evaluate whether LLMs can formulate optimization problems as solver code, but leave open a complementary question. Can...
VeRO: An Evaluation Harness for Agents to Optimize Agents
arXiv:2602.22480v1 Announce Type: new Abstract: An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles. Despite its relevance, the community lacks a systematic understanding of coding agent performance on this...
Mapping the Landscape of Artificial Intelligence in Life Cycle Assessment Using Large Language Models
arXiv:2602.22500v1 Announce Type: new Abstract: Integration of artificial intelligence (AI) into life cycle assessment (LCA) has accelerated in recent years, with numerous studies successfully adapting machine learning algorithms to support various stages of LCA. Despite this rapid development, comprehensive and...
A Mathematical Theory of Agency and Intelligence
arXiv:2602.22519v1 Announce Type: new Abstract: To operate reliably under changing conditions, complex systems require feedback on how effectively they use resources, not just whether objectives are met. Current AI systems process vast information to produce sophisticated predictions, yet predictions can...
Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents
arXiv:2602.22523v1 Announce Type: new Abstract: While contemporary large language models (LLMs) are increasingly capable in isolation, there are still many difficult problems that lie beyond the abilities of a single LLM. For such tasks, there is still uncertainty about how...
Agentic AI for Intent-driven Optimization in Cell-free O-RAN
arXiv:2602.22539v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) is emerging as a key enabler for autonomous radio access networks (RANs), where multiple large language model (LLM)-based agents reason and collaborate to achieve operator-defined intents. The open RAN (O-RAN) architecture...
Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention
arXiv:2602.22546v1 Announce Type: new Abstract: Large Language Model (LLM) based agents excel at general reasoning but often fail in specialized domains where success hinges on long-tail knowledge absent from their training data. While human experts can provide this missing knowledge,...
Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance
arXiv:2602.22583v1 Announce Type: new Abstract: Example-based guidance is widely used to improve mathematical reasoning at inference time, yet its effectiveness is highly unstable across problems and models-even when the guidance is correct and problem-relevant. We show that this instability arises...
SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning
arXiv:2602.22603v1 Announce Type: new Abstract: Long-running agentic tasks, such as deep research, require multi-hop reasoning over information distributed across multiple webpages and documents. In such tasks, the LLM context is dominated by tokens from external retrieval, causing memory usage to...
AHBid: An Adaptable Hierarchical Bidding Framework for Cross-Channel Advertising
arXiv:2602.22650v1 Announce Type: new Abstract: In online advertising, the inherent complexity and dynamic nature of advertising environments necessitate the use of auto-bidding services to assist advertisers in bid optimization. This complexity is further compounded in multi-channel scenarios, where effective allocation...
Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions
arXiv:2602.22680v1 Announce Type: new Abstract: Large language models have enabled agents that reason, plan, and interact with tools and environments to accomplish complex tasks. As these agents operate over extended interaction horizons, their effectiveness increasingly depends on adapting behavior to...
Knob: A Physics-Inspired Gating Interface for Interpretable and Controllable Neural Dynamics
arXiv:2602.22702v1 Announce Type: new Abstract: Existing neural network calibration methods often treat calibration as a static, post-hoc optimization task. However, this neglects the dynamic and temporal nature of real-world inference. Moreover, existing methods do not provide an intuitive interface enabling...
RLHFless: Serverless Computing for Efficient RLHF
arXiv:2602.22718v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) has been widely applied to Large Language Model (LLM) post-training to align model outputs with human preferences. Recent models, such as DeepSeek-R1, have also shown RLHF's potential to improve...
Generative Data Transformation: From Mixed to Unified Data
arXiv:2602.22743v1 Announce Type: new Abstract: Recommendation model performance is intrinsically tied to the quality, volume, and relevance of their training data. To address common challenges like data sparsity and cold start, recent researchs have leveraged data from multiple auxiliary domains...
Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning
arXiv:2602.22751v1 Announce Type: new Abstract: Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks. In practice, these models are predominantly trained via Reinforcement Learning with Verifiable Rewards (RLVR), yet most existing outcome-only RLVR pipelines...
Decomposing Physician Disagreement in HealthBench
arXiv:2602.22758v1 Announce Type: new Abstract: We decompose physician disagreement in the HealthBench medical AI evaluation dataset to understand where variance resides and what observable features can explain it. Rubric identity accounts for 15.8% of met/not-met label variance but only 3.6-6.9%...