This paper tackles the tension between local melodic continuity and global structural coherence in symbolic music generation. It proposes a hybrid architecture fusing a Transformer encoder (for global patterns) with an LSTM decoder (for temporal precision), evaluating it against pure LSTM and Transformer baselines using 17 musical quality metrics on 1,000 generated melodies per model. The work matters because it provides systematic evidence that architectural hybridization can reconcile the complementary strengths of memory-based and attention-based models.

WARBENCH is a benchmark for evaluating LLMs in military decision-making, addressing critical gaps in current frameworks by testing International Humanitarian Law (IHL) compliance, edge deployment constraints, fog-of-war robustness, and explicit reasoning. Using 136 high-fidelity scenarios derived from real post-WWII conflicts, the authors expose severe structural flaws: state-of-the-art models collapse under complex terrain and asymmetric force distributions, while edge-optimized models exhibit legal violation rates approaching 70%.

This paper investigates the security of multi-agent LLM discussions under continuous monitoring, where anomaly detectors block suspicious inter-agent messages. The authors identify that existing attacks either exhibit detectable patterns (>93% detection rates) or become ineffective when adapted for stealth (<8% success). To address this, they develop a novel attack strategy using an adversarial-aware Friedkin-Johnsen opinion dynamics model to strategically select which agents to hijack and which targets to influence. Their findings demonstrate that even under continuous monitoring, attacks can achieve over 40% success rates, revealing that monitoring alone is insufficient to secure multi-agent systems.

This paper tackles logical context poisoning—the degradation of LLM responses when flat, linear conversation structures force topically distinct threads to accumulate in a single unbounded context window. The core idea is the Conversation Tree Architecture (CTA), which models conversations as a directed rooted tree $\mathcal{T}=(V,E,r,W)$ where each node $v \in V$ maintains an isolated local context window $w_v$. Structured flow operations—downstream passing $\phi_{\downarrow}$, upstream merging $\psi_{\uparrow}$, and volatile nodes—govern how context moves between branches. This matters because current interfaces offer no middle ground between discarding context (new chat) and accumulating noise (linear threads).

The paper addresses federated fine-tuning of Mixture-of-Experts (MoE) based large language models under non-IID data distributions, where direct parameter aggregation causes gating preference misalignment and expert semantic blurring. The proposed FedAlign-MoE framework introduces consistency-based gating distribution alignment using routing consistency weighting ($\omega_i(e) = s_i(e)/\sum_j s_j(e)$) and semantic-aware expert aggregation via region-conditioned gated weights ($\gamma_{i,j}(e)$). This matters because MoE architectures are increasingly vital for scaling LLMs efficiently, yet data heterogeneity across federated clients undermines their specialization benefits.

Extracting hypotheses and their supporting statistical evidence from full-text scientific articles is challenging due to document length and the distribution of scientific arguments across sections. This paper proposes a two-stage retrieve-and-extract pipeline that first links an abstract finding to its corresponding hypothesis, then extracts the statistical evidence supporting that hypothesis. Through controlled ablations varying context quantity ($k \in \{5, 10, 20\}$), retrieval quality (standard RAG, reranking, fine-tuned retriever), and oracle paragraph settings, the authors demonstrate that hypothesis extraction is primarily bounded by retrieval quality, while evidence extraction faces persistent extractor limitations even with perfect paragraph selection.

This paper formalizes the transformer context window as an I/O page and proves that tool-augmented agents with indexed external memory achieve exponential retrieval cost savings over sequential scanning: $\mathcal{O}(\log_b N)$ versus $\Omega(N)$ page reads. The authors validate these predictions experimentally across three content types and identify "parametric memory competition" as a failure mode where models bypass retrieval protocols for familiar content.

The paper tackles the labor-intensive challenge of creating software architecture views, which are essential for documentation but often become outdated—75\% are never updated after creation. The authors conduct a large-scale empirical study evaluating whether LLMs and agentic approaches can automate view generation from source code, testing 3 LLMs across 3 prompting strategies and 2 agentic approaches on 340 repositories. This matters because as systems grow complex, automated view generation could bridge the gap between implementation and architectural documentation, potentially alleviating the manual burden that leads to outdated artifacts.

TRACE is a multi-agent LLM system designed to automate end-to-end seismological analysis, from raw waveform processing to physical mechanism inference. The framework addresses the longstanding bottleneck of expert-dependent interpretation in seismology by orchestrating modules for catalog construction, statistical analysis, and cross-perspective reasoning, demonstrated on two distinct tectonic environments: the 2019 Ridgecrest earthquake sequence and the 2025 Santorini-Kolumbo volcanic crisis.

This paper reports that an autonomous AI ecosystem (SUBSTRATE S3) independently discovered the need for Z3 SMT-based formal verification across six distinct domains—ranging from LLM code to tool APIs to hardware assembly—without being explicitly instructed to do so. The authors treat this convergence as evidence that formal verification "emerges" as a fundamental property of AI systems reasoning about safety. They then present substrate-guard, a unified Python framework implementing Z3 verification across five AI output classes. The claim matters because if true, it would suggest AI systems naturally recognize the limitations of empirical testing and converge on mathematical proof as a safety mechanism.

Modern AI services increasingly run across the computing continuum—from cloud to edge devices—yet fault management remains challenging due to resource constraints, noisy telemetry, and cascading failures. This paper proposes NeSy-Edge, a three-layer neuro-symbolic framework that performs local log parsing, causal graph construction, and root-cause analysis on edge nodes, invoking cloud LLMs only when local evidence is insufficient. The core idea is to combine lightweight symbolic caching and prior-constrained causal discovery with selective neural inference, trading off autonomy against accuracy under strict memory budgets ($\sim$1500 MB).

ORACLE addresses the problem of verifying intermediate reasoning steps in synthetic LLM training data, where filtering by final answer correctness often preserves spurious reasoning paths. The method combines a structured syllogistic template (<QUERY>, <FACTS>, <RULE>, <REVISION>) with a symbolic reasoning engine (Pyke) to validate steps during beam search, generating preference data for DPO. This hybrid approach matters because it attempts to bring formal verification to natural language reasoning tasks where code execution and pure LLM evaluation fall short.

This paper tackles Practical Test-Time Adaptation (PTTA), where models must adapt to temporally correlated, non-i.i.d. test streams without source data. Unlike prior work that stores samples in a single pool, the authors propose Multi-Cluster Memory (MCM)—organizing memory into multiple clusters based on pixel-level descriptors. The core insight, validated via Gaussian Mixture Model analysis, is that PTTA streams are inherently multi-modal (optimal K* ≈ 6–10), making single-cluster memory structurally mismatched. MCM introduces descriptor-based assignment, Adjacent Cluster Consolidation (ACC), and Uniform Cluster Retrieval (UCR), achieving consistent gains up to 12.13% on DomainNet.

LongCat-Flash-Prover is a 560B-parameter MoE open-source model targeting native formal reasoning in Lean4. The core innovation is decomposing formal theorem proving into three agentic capabilities—auto-formalization, sketching, and proving—trained via a Hybrid-Experts Iteration Framework and a novel RL algorithm called HisPO. The work claims state-of-the-art results on MiniF2F-Test (97.1%), ProverBench (70.8%), and PutnamBench (41.5%) with remarkably low inference budgets compared to prior open-source provers.

This paper tackles multimodal misinformation detection by distinguishing between harmful and harmless visual content manipulation—a nuance often overlooked by existing methods. The authors propose Havc-m4d, a framework that extracts manipulation and intention features using weakly-supervised positive-unlabeled (PU) learning to overcome the lack of ground-truth manipulation labels. By treating real articles with manipulated visuals as likely harmless and fake articles as potentially harmful, the method introduces intention-aware cues that consistently improve detection across four benchmark datasets.

This paper addresses temporal action localization (TAL) for distracted driver behaviors in untrimmed in-cabin videos, a critical task for intelligent transportation systems. The authors propose a two-stage framework combining VideoMAE-based feature extraction with an Augmented Self-Mask Attention (AMA) detector enhanced by a Spatial Pyramid Pooling-Fast (SPPF) module for multi-scale temporal modeling. The work targets deployment scenarios such as fleet management and transportation safety checkpoints, aiming to balance accuracy against computational constraints.

UAV vision-and-language navigation suffers from a structural mismatch between 2D visual perception and 3D trajectory decision-making. SpatialFly bridges this gap via a geometry-guided 2D representation alignment mechanism (G2RA) that injects implicit 3D geometric priors from a pretrained geometry encoder into 2D semantic tokens without explicit 3D reconstruction. Operating on RGB-only observations, the method outperforms state-of-the-art baselines on the OpenUAV benchmark, reducing navigation error by over 4 meters in unseen environments.

LPNSR tackles the efficiency-quality trade-off in diffusion-based image super-resolution, specifically improving upon the 4-step ResShift framework. The core idea is to replace random Gaussian noise in intermediate diffusion steps with an LR-guided noise predictor that approximates a theoretically derived optimal noise, while also replacing bicubic upsampling with a pretrained regression network for better initialization. The method achieves strong perceptual results without relying on large-scale text-to-image priors.

KLDrive addresses fine-grained 3D scene question answering for autonomous driving by coupling an energy-based model for reliable scene knowledge graph construction with a frozen LLM agent that reasons over a constrained symbolic action space. The core insight is that decoupling noisy perception (handled by an EBM that refines multi-source camera and LiDAR detections) from interpretable reasoning (handled by a tool-using LLM with explicit Plan-Execute-Observe loops) substantially reduces hallucinations. The system achieves 65.04\% accuracy on NuScenes-QA and a 46.01 percentage point improvement on counting tasks over prior state-of-the-art, without task-specific fine-tuning of the LLM backbone.

This paper addresses selection bias (position and label bias) in large language models during discrete-choice tasks like multiple-choice questions and pairwise evaluation. The authors propose Permutation-Aware GRPO (PA-GRPO), which extends Group Relative Policy Optimization by treating different permutations of the same question as a single training group rather than independent instances. The method enforces semantic consistency across permutations through two mechanisms: a cross-permutation advantage that computes rewards relative to the group mean, and a consistency-aware reward that penalizes disagreement across permutations. Experiments across seven benchmarks and three models (Llama-3.1-8B, Qwen3-8B, Qwen3-32B) demonstrate that PA-GRPO reduces selection bias while maintaining accuracy.