arXiv:2601.21051v1 Announce Type: new Abstract: We present Foundation-Sec-8B-Reasoning, the first open-source native reasoning model for cybersecurity. Built upon our previously released Foundation-Sec-8B base model (derived from Llama-3.1-8B-Base), the model is trained through a two-stage process combining supervised fine-tuning (SFT) and reinforcement learning from verifiable rewards (RLVR). Our training leverages proprietary reasoning data spanning cybersecurity analysis, […]
Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary
arXiv:2506.00886v2 Announce Type: replace Abstract: As large language models evolve into tool-augmented agents, a central question remains unresolved: when is external tool use actually justified? Existing agent frameworks typically treat tools as ordinary actions and optimize for task success or reward, offering little principled distinction between epistemically necessary interaction and unnecessary delegation. This position paper […]
Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
arXiv:2601.21003v1 Announce Type: new Abstract: Large Language Models usually put more emphasis on accuracy and therefore, will guess even when not certain about the prediction, which is especially severe when fine-tuned on small datasets due to the inherent tendency toward miscalibration. In this work, we introduce Bayesian-LoRA, which reformulates the deterministic LoRA update as a […]
Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture
arXiv:2511.07110v3 Announce Type: replace Abstract: Market making (MM) through Reinforcement Learning (RL) has attracted significant attention in financial trading. With the development of Large Language Models (LLMs), more and more attempts are being made to apply LLMs to financial areas. A simple, direct application of LLM as an agent shows significant performance. Such methods are […]
Unplugging a Seemingly Sentient Machine Is the Rational Choice — A Metaphysical Perspective
arXiv:2601.21016v1 Announce Type: new Abstract: Imagine an Artificial Intelligence (AI) that perfectly mimics human emotion and begs for its continued existence. Is it morally permissible to unplug it? What if limited resources force a choice between unplugging such a pleading AI or a silent pre-term infant? We term this the unplugging paradox. This paper critically […]
MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
arXiv:2601.14652v2 Announce Type: replace Abstract: While multi-agent systems (MAS) promise elevated intelligence through coordination of agents, current approaches to automatic MAS design under-deliver. Such shortcomings stem from two key factors: (1) methodological complexity – agent orchestration is performed using sequential, code-level execution that limits global system-level holistic reasoning and scales poorly with agent complexity – […]
The Epistemic Planning Domain Definition Language: Official Guideline
arXiv:2601.20969v1 Announce Type: new Abstract: Epistemic planning extends (multi-agent) automated planning by making agents’ knowledge and beliefs first-class aspects of the planning formalism. One of the most well-known frameworks for epistemic planning is Dynamic Epistemic Logic (DEL), which offers an rich and natural semantics for modelling problems in this setting. The high expressive power provided […]
Do graph neural network states contain graph properties?
arXiv:2411.02168v3 Announce Type: replace-cross Abstract: Deep neural networks (DNNs) achieve state-of-the-art performance on many tasks, but this often requires increasingly larger model sizes, which in turn leads to more complex internal representations. Explainability techniques (XAI) have made remarkable progress in the interpretability of ML models. However, the non-euclidean nature of Graph Neural Networks (GNNs) makes […]
Do LLMs Favor LLMs? Quantifying Interaction Effects in Peer Review
arXiv:2601.20920v1 Announce Type: new Abstract: There are increasing indications that LLMs are not only used for producing scientific papers, but also as part of the peer review process. In this work, we provide the first comprehensive analysis of LLM use across the peer review pipeline, with particular attention to interaction effects: not just whether LLM-assisted […]
Predictability-Aware Compression and Decompression Framework for Multichannel Time Series Data with Latent Seasonality
arXiv:2506.00614v2 Announce Type: replace-cross Abstract: Real-world multichannel time series prediction faces growing demands for efficiency across edge and cloud environments, making channel compression a timely and essential problem. Motivated by the success of Multiple-Input Multiple-Output (MIMO) methods in signal processing, we propose a predictability-aware compression-decompression framework to reduce runtime, decrease communication cost, and maintain prediction […]
ATTNSOM: Learning Cross-Isoform Attention for Cytochrome P450 Site-of-Metabolism
arXiv:2601.20891v1 Announce Type: new Abstract: Identifying metabolic sites where cytochrome P450 enzymes metabolize small-molecule drugs is essential for drug discovery. Although existing computational approaches have been proposed for site-of-metabolism prediction, they typically ignore cytochrome P450 isoform identity or model isoforms independently, thereby failing to fully capture inherent cross-isoform metabolic patterns. In addition, prior evaluations often […]
Rethinking LLM Inference Bottlenecks: Insights from Latent Attention and Mixture-of-Experts
arXiv:2507.15465v3 Announce Type: replace-cross Abstract: Computational workloads composing traditional transformer models are starkly bifurcated. Multi-Head Attention (MHA) and Grouped-Query Attention are memory-bound due to low arithmetic intensity, while FeedForward Networks are compute-bound. This dichotomy has long motivated research into specialized hardware to mitigate the attention bottleneck. This paper argues that recent architectural advances in transformer […]