arXiv:2605.04939v1 Announce Type: cross Abstract: A cooperative robot swarm is a collective of computationally-limited robots that share a common goal. Each robot can only interact with a small subset of its peers, without knowing how this affects the collective utility. Recent advances in distributed multi-agent reinforcement learning have demonstrated that it is possible for robots […]
Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors
arXiv:2512.06393v5 Announce Type: replace Abstract: Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests — redundant vs. essential rule deletion, contradictory-rule injection, logic-preserving rewrites, and multi-law stacking — and use it to expose Logic Inertia: […]
When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems
arXiv:2605.02463v2 Announce Type: replace-cross Abstract: Multi-agent LLM systems are increasingly used to solve complex tasks through decomposition, debate, specialization, and ensemble reasoning. However, these systems are usually evaluated in terms of robustness: whether performance is preserved under perturbation. This paper studies a different question: whether semantic stress exposes structured variation that could support future antifragile […]
Geometry over Density: Few-Shot Cross-Domain OOD Detection
arXiv:2605.03410v2 Announce Type: replace Abstract: Out-of-distribution (OOD) detection identifies test samples that fall outside a model’s training distribution, a capability critical for safe deployment in high-stakes applications. Standard OOD detectors are trained on a specific in-distribution (ID) dataset and detect deviations from that single domain. In contrast, we study few-shot cross-domain OOD detection: given a […]
When Does Gene Regulatory Network Inference Break? A Controlled Diagnostic Study of Causal and Correlational Methods on Single-Cell Data
arXiv:2605.04930v1 Announce Type: cross Abstract: Despite theoretical advantages, causal methods for Gene Regulatory Network (GRN) inference from single-cell RNA-seq data consistently fail to match or outperform correlation-based baselines in many realistic benchmarks, a persistent puzzle which casts doubt on the value of causality for this task. We argue that existing benchmarks are insufficiently controlled to […]
On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training
arXiv:2601.07389v2 Announce Type: replace-cross Abstract: Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimizes the cross-entropy loss between model outputs and expert responses, while RL maximizes reward signals derived from human preferences or rule-based verifiers. Modern reasoning models have widely adopted the […]
RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy
arXiv:2605.02003v2 Announce Type: replace-cross Abstract: Machine Learning (ML) has transformed many scientific fields, yet key applications still lack standardized benchmarks. Raman spectroscopy, a widely used technique for non-invasive molecular analysis, is one such field where progress is limited by fragmented datasets, inconsistent evaluation, and models that fail to capture the structure of spectral data. We […]
SegMix:Shuffle-based Feedback Learning for Semantic Segmentation of Pathology Images
arXiv:2604.15777v2 Announce Type: replace-cross Abstract: Segmentation is a critical task in computational pathology, as it identifies areas affected by disease or abnormal growth and is essential for diagnosis and treatment. However, acquiring high-quality pixel-level supervised segmentation data requires significant workload demands from experienced pathologists, limiting the application of deep learning. To overcome this challenge, relaxing […]
Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
arXiv:2605.04922v1 Announce Type: cross Abstract: LLM-empowered multi-agent systems offer new potential to accelerate scientific discovery by generating novel research ideas. However, existing methods typically coordinate agents through temporary texts, such as drafts or chat logs; it is difficult to pinpoint the weaknesses in the generated ideas and how the agents refine them. To this end, […]
Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking
arXiv:2605.04971v1 Announce Type: cross Abstract: Weight matrices in deep networks exhibit geometric continuity — principal singular vectors of adjacent layers point in similar directions. While this property has been widely observed, its origin remains unexplained. Through experiments on toy MLPs and small transformers, we identify two mechanisms: residual connections create cross-layer gradient coherence that aligns […]
Building informative materials datasets beyond targeted objectives
arXiv:2605.05104v1 Announce Type: cross Abstract: Materials science data collection can be expensive, making the reuse and long-term utility of datasets critical important for future discovery campaigns. In practice, researchers prioritize a subset of properties due to research interests. However, ignoring a subset of outcomes in data collection campaigns potentially generate datasets poorly suited for future […]
Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs
arXiv:2605.04903v1 Announce Type: cross Abstract: Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch — computationally expensive and yielding verbose code. We propose Delta-Code Generation, where fine-tuned LLMs generate compact unified diffs (deltas) to refine baseline architectures rather than synthesizing entire models. Our pipeline […]