arXiv AI
3d ago
Bounded Agents: Delegation Security for Multi-Agent AI Systems
arXiv:2608. 15888v1 Announce Type: new Abstract: LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
3d ago
Navigation-Informed Embeddings: Dense-Retriever Adaptation from Agent Search Traces
arXiv:2608. 15956v1 Announce Type: new Abstract: Agentic retrieval workflows produce query, retrieval, and stopping traces as a byproduct of answering questions.
arXiv AI
3d ago
Competing at Every Price Point with Agentic Evolution over a Menu of LLMs
arXiv:2608. 16207v1 Announce Type: new Abstract: Consider a firm that surveys its competition for a particular agentic task and seeks to offer superior accuracy at every competitor price point.
arXiv AI
3d ago
BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics
arXiv:2608. 16211v1 Announce Type: new Abstract: Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts.
arXiv AI
3d ago
The Value of a Prompt: An LLM-Relative Kolmogorov-Complexity Approach
arXiv:2608. 16438v1 Announce Type: new Abstract: In a world where valuable artifacts are increasingly created, completed, or processed by LLMs, the central economic question is not only what the LLM can produce, but what \emph{value} remains in the inputs (i.
arXiv AI
3d ago
Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling
arXiv:2608. 16507v1 Announce Type: new Abstract: Due to the limited amount of information, modeling longitudinal rare-disease data can benefit from integrating clinical knowledge.
arXiv AI
3d ago
PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning
arXiv:2608. 16637v1 Announce Type: new Abstract: LLMs remain unreliable for long-horizon planning, often generating logically inconsistent or non-applicable plans.
arXiv AI
3d ago
LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing
arXiv:2608. 16763v1 Announce Type: new Abstract: Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints.
arXiv AI
3d ago
Forward Pass Domain Adaptation (Without Cross-Layer Backpropagation)
arXiv:2608. 14563v1 Announce Type: cross Abstract: Forward-Pass-Only MLP training (FPO) adapts large language models without a backward pass through the model body, achieving 2.
arXiv AI
3d ago
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs
arXiv:2608. 14577v1 Announce Type: cross Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis.
arXiv AI
3d ago
Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures
arXiv:2608. 14586v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure.
arXiv AI
3d ago
AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search
arXiv:2608. 14621v1 Announce Type: cross Abstract: Long-term memory is increasingly central to LLM agents, yet memory design remains a highly coupled architecture problem: what to encode, how to store it, how to retrieve it, and how to manage it can vary substantially across tasks and backbone models.
arXiv AI
3d ago
Characterizing Rhetorical Misalignment in Decision-Making with Language Models
arXiv:2608. 14630v1 Announce Type: cross Abstract: Human decision-making is often shaped by a range of well-documented cognitive biases.
arXiv AI
3d ago
Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms
arXiv:2608. 14653v1 Announce Type: cross Abstract: Prediction uncertainty is a widely adopted metric for quantifying model confidence, with downstream applications spanning model explanation, data selection, and prediction rollback.
arXiv AI
3d ago
Domain Agnostic Text Redaction from Natural Language Rules using Instruction Tuning
arXiv:2608. 14693v1 Announce Type: cross Abstract: With the increasing digitization of personal and corporate communication, the automatic sanitization of textual data has become a crucial component of data privacy and compliance frameworks.
arXiv AI
3d ago
Tail-Aware Top-$k$ On-Policy Distillation
arXiv:2608. 14728v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its next-token distribution with the teacher's along its own trajectories.
arXiv AI
3d ago
PolyComp: A Polycube-based Benchmark for Compositional 3D Spatial Reasoning in Multimodal Models
arXiv:2608. 14741v1 Announce Type: cross Abstract: We introduce PolyComp, a procedurally generated and verified benchmark that stresses visual recognition and compositional spatial reasoning.
arXiv AI
3d ago
Evaluating Agentic Code Repair Capabilities in Distributed Systems
arXiv:2608. 14863v1 Announce Type: cross Abstract: LLM-based coding agents have advanced rapidly on single-process SWE tasks, with frontier models now clustering in the high-70s on SWE-bench Verified.
arXiv AI
3d ago
SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable
arXiv:2608. 14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose internal representations into sparse and more interpretable features.
arXiv AI
3d ago
RamseyGadgets: A Graph Construction Dataset for LLMs
arXiv:2608. 14999v1 Announce Type: cross Abstract: Constructing special graphs is an important task within graph theory and computer science.