arXiv:2510.19950v3 Announce Type: replace-cross Abstract: In financial applications, reinforcement learning (RL) agents are commonly trained on historical data, where their actions do not influence prices. However, during deployment, these agents trade in live markets where their own transactions can shift asset prices, a phenomenon known as market impact. This mismatch between training and deployment environments […]
On the Failure of Latent State Persistence in Large Language Models
arXiv:2505.10571v5 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) excel in reasoning, whether they can sustain persistent latent states remains under-explored. The capacity to maintain and manipulate unexpressed, internal representations-analogous to human working memory-is a cornerstone of complex reasoning. In this paper, we formalize and quantify the “Latent State Persistence” (LSP) gap through three […]
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
arXiv:2505.23277v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) often suffers from long and noisy retrieved contexts. Prior context compression methods rely on predefined importance metrics or supervised compression models, rather than on the model’s own inference-time behavior. We propose Sentinel, a lightweight sentence-level compression framework that treats context compression as an understanding decoding problem. Sentinel […]
Labels or Input? Rethinking Augmentation in Multimodal Hate Detection
arXiv:2508.11808v2 Announce Type: replace-cross Abstract: Online hate remains a significant societal challenge, especially as multimodal content enables subtle, culturally grounded, and implicit forms of harm. Hateful memes embed hostility through text-image interactions and humor, making them difficult for automated systems to interpret. Although recent Vision-Language Models (VLMs) perform well on explicit cases, their deployment is […]
Towards a Physics Foundation Model
arXiv:2509.13805v3 Announce Type: replace-cross Abstract: Foundation models have revolutionized natural language processing through a “train once, deploy anywhere” paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining. Access to a Physics Foundation Model (PFM) would be transformative – democratizing access to high-fidelity simulations, accelerating scientific discovery, and eliminating the need for […]
Sprecher Networks: A Parameter-Efficient Kolmogorov-Arnold Architecture
arXiv:2512.19367v2 Announce Type: replace-cross Abstract: We introduce Sprecher Networks (SNs), a family of trainable architectures derived from David Sprecher’s 1965 constructive form of the Kolmogorov-Arnold representation. Each SN block implements a “sum of shifted univariate functions” using only two shared learnable splines per block, a monotone inner spline $phi$ and a general outer spline $Phi$, […]
Gateways to Tractability for Satisfiability in Pearl’s Causal Hierarchy
arXiv:2511.08091v2 Announce Type: replace Abstract: Pearl’s Causal Hierarchy (PCH) is a central framework for reasoning about probabilistic, interventional, and counterfactual statements, yet the satisfiability problem for PCH formulas is computationally intractable in almost all classical settings. We revisit this challenge through the lens of parameterized complexity and identify the first gateways to tractability. Our results […]
How Good Are LLMs at Processing Tool Outputs?
arXiv:2510.15955v2 Announce Type: replace-cross Abstract: Most realistic task automation problems require large language models (LLMs) to call tools, which often return complex JSON responses. These responses must be further processed to derive the information necessary for task completion. The ability of LLMs to do so is under-studied. In this paper, we study the tool response […]
From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision
arXiv:2408.09650v2 Announce Type: replace-cross Abstract: Low-light image enhancement remains a persistent challenge in computer vision, where state-of-the-art models are often hampered by hardware constraints and computational inefficiency, particularly at high resolutions. While foundational architectures like transformers and diffusion models have advanced the field, their computational complexity limits their deployment on edge devices. We introduce ExpoMamba, […]
One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents
arXiv:2512.20957v5 Announce Type: replace-cross Abstract: Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically treat this as a repository-level retrieval task and rely on multiple auxiliary tools, which often overlook code execution logic and complicate model control. We propose RepoNavigator, an […]
FastInsight: Fast and Insightful Retrieval via Fusion Operators for Graph RAG
arXiv:2601.18579v1 Announce Type: cross Abstract: Existing Graph RAG methods aiming for insightful retrieval on corpus graphs typically rely on time-intensive processes that interleave Large Language Model (LLM) reasoning. To enable time-efficient insightful retrieval, we propose FastInsight. We first introduce a graph retrieval taxonomy that categorizes existing methods into three fundamental operations: vector search, graph search, […]
How Information Evolves: Stability-Driven Assembly and the Emergence of a Natural Genetic Algorithm
arXiv:2601.17061v1 Announce Type: new Abstract: Information can evolve as a physical consequence of non-equilibrium dynamics, even in the absence of genes, replication, or predefined fitness functions. We present Stability-Driven Assembly (SDA), a framework in which stochastic assembly combined with differential persistence biases populations toward longer-lived motifs. Assemblies that persist longer become more frequent and are […]