computer science
50 notes, newest first.
Inducing Task Models from Computer-Use Traces
Researchers present Task Model Induction (TMI), a method that extracts structured task models from naturalistic computer-use traces. These traces are screenshots and mouse or keyboard actions recorded during work. TMI…
Inducing Task Models from Computer-Use Traces
Researchers present a new method called Task Model Induction (TMI) to extract detailed and structured task models from computer use traces, such as screenshots and mouse or keyboard actions. These task models can help…
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
The paper presents MaliciousSkillBench, a comprehensive benchmark for detecting malicious Agent Skills in large language models (LLMs). The benchmark consolidates various sources of malicious artifacts and reduces them…
Repo0: Design-Driven Zero-to-All Code Generation
The paper introduces Repo0, a framework for zero-to-all code generation that maintains an explicit architectural state using a Dual-Directed Acyclic Graph (Dual-DAG). It iteratively evolves component boundaries guided…
DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation
In this paper, the authors introduce DreamFly, a new framework for aerial vision-language navigation that addresses the challenges of limited historical context, short planning horizons, and unreliable implicit…
VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
The paper introduces VICBench, a multi-language benchmark for code vulnerability detection. It was created by human experts and an agentic workflow, featuring 100 verified vulnerabilities across 88 projects in Python…
A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem
The paper discusses a solution to a governance crisis caused by the rapid adoption of Model Context Protocol (MCP) for connecting LLM agents with enterprise tools. The solution is a centralized MCP gateway that…
ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation
The paper introduces ChemWorld, a programmable chemical environment that allows researchers to create executable worlds with reusable components. This environment separates the experimental contract available to an…
Conversational Orchestration for Organic 6G
The authors propose a lightweight, decentralized conversational orchestration framework using Large Language Model (LLM)-driven domain agents for the future network of networks, Organic 6G. The aim is to provide…
Defining Decentralization: An Ontological Perspective
This research paper addresses the lack of a universal definition for decentralization in computer science and its related fields like security, AI, cloud infrastructure, IoT, etc. The authors propose a graph-based…
Defining Decentralization: An Ontological Perspective
The authors address the lack of a universally accepted definition of decentralization in computer science, particularly in emerging fields like decentralized AI and machine learning. They propose a graph-based ontology…
MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration
A new method called MicroEvo is proposed for efficient exploration of microarchitecture design spaces. This approach utilizes a combination of large language models (LLMs) and Monte Carlo Tree Search (MCTS) to optimize…
Agentic Method for Deterministic Validation of Legacy Code Migration
The paper proposes a new method called 'Locksmith Loop' for testing the migration of COBOL programs to Java. This method is designed to improve coverage beyond input-search plateaus, reaching near complete coverage in…
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
Researchers have introduced a new framework for ontology matching called AgentMap. This framework can simultaneously discover both equivalent and subsuming mappings in ontologies, which existing systems cannot do. The…
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
MemSecBench is a new benchmark for testing the lifecycle security of agent memory systems. The benchmark contains 310 cases drawn from various contexts, and it follows a controlled protocol to test the persistence…
SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
Researchers have created SciFigQual-Bench, a new benchmark for evaluating the quality of scientific figures in computer science papers. The benchmark assesses five dimensions: clarity, layout, caption fit, context…
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
Researchers propose a new framework called Agent-Guided Concept Discovery to improve the clinical adoption of deep learning models for surgical margin assessment using Rapid Evaporative Ionization Mass Spectrometry…
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
Researchers propose a new method called Agent-Guided Concept Discovery to help deep learning models assess surgical margins more effectively, particularly in noisy and unlabeled data acquired during surgery. The…
From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurrent Stateful Rust APIs
The paper proposes a methodology using Petri nets to generate tests for concurrent stateful Rust APIs, aiming to address issues with large language models (LLMs) in generating executable tests that may violate API…
From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurrent Stateful Rust APIs
The authors present a methodology using Petri nets to generate tests for concurrent stateful Rust APIs, aiming to bridge the gap between formal scenario design and low-cost test concretization.
From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurrent Stateful Rust APIs
The paper presents a methodology using Petri nets for test generation in concurrent stateful Rust APIs, aiming to bridge the gap between formal scenario design and low-cost test concretization. It allows large language…
PIER: Physics-Informed Environmental Retrieval for Time-Series Modeling
The researchers propose Physics-Informed Environmental Retrieval (PIER), a model-agnostic framework to improve the accuracy of environmental system modeling. The framework is designed to address challenges in limited…
SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs
Researchers present SelectInfer, a neuron-level optimization framework for Large Language Models (LLMs) that can run efficiently on resource-constrained edge devices. It reduces memory footprint and computation by…
In-Place Tokenizer Expansion for Pre-trained LLMs
Researchers have developed an in-place method called Tokenizer Expansion to upgrade a pre-trained model's tokenizer when language priorities shift, focusing on improving efficiency for users of languages added later…
LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research
The paper introduces LQCDMaster, a tool that helps convert natural language Lattice Quantum Chromodynamics (LQCD) research tasks into executable PyQUDA computing workflows. It combines agentic planning…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers have introduced a new benchmark called MM-IssueLoc for evaluating the effectiveness of systems in repository-level issue localization that also includes visual evidence such as screenshots, error dialogs…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers have introduced a new benchmark called MM-IssueLoc for evaluating the effectiveness of multimodal repository-level issue localization, which includes visual evidence such as screenshots, error dialogs, and…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers introduce MM-IssueLoc, a benchmark and evaluation protocol designed specifically for repository-level issue localization with visual evidence. The dataset includes 652 issue-PR instances across multiple…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
The paper introduces MM-IssueLoc, a benchmark and evaluation protocol for repository-level issue localization that includes visual evidence. The benchmark has 652 issue-PR instances across 23 languages with annotations…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
The paper introduces MM-IssueLoc, a new benchmark and evaluation protocol for repository-level issue localization with visual evidence. The benchmark contains over 650 issue-PR instances across multiple languages…
CAVA: Canonical Action Verification and Attestation for Runtime Governance of Agentic AI Systems
The paper introduces Canonical Action Verification and Attestation (CAVA), a system designed to convert diverse agent activities into standardized action objects, addressing the challenge of governing heterogeneous AI…
Social Simulations: from Agent-Based Modeling to Digital Twins
The text discusses the evolution of social simulation from traditional agent-based modeling to more advanced AI-enhanced simulations and Social Digital Twins, focusing on their methodological foundations, applications…
Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing
The text discusses a new research area called Agentic Service-Oriented Computing (ASOC), which focuses on engineering agents as services, managing their complex distributed workflows, and ensuring their reliability for…
FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation
The paper presents FormalAnalyticGeo, a framework for generating multimodal analytic geometry problems using neural-symbolic based methods. The framework leverages a formal intermediate representation called CDL to…
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
The paper presents ProjAgent, a system for generating code at the repository level that uses 'procedural similarity' as a new signal in the retrieval process. This system decomposes the target function into…
SLORR: Simple and Efficient In-Training Low-Rank Regularization
The paper introduces SLORR, a simple and efficient low-rank regularization method for compressing neural networks during training. It addresses the limitations of existing methods by being stateless…
SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling
The paper proposes SMetric, a new scheduling method for Large Language Models (LLMs) in serving agents. The method aims to balance the session-centric workload of agents and increase Key-Value (KV$) reuse by…
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
This research study introduces a new metric, called 'correctness agreement', to evaluate the impact of post-training quantization on large language models. The authors show that even when task performance seems…
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
The paper introduces a new benchmark, DramaSR-532K, for speaker recognition in long-form TV dramas. They also propose a new approach called DramaSR-LRM which uses a large reasoning model (LRM) to aggregate contextual…
TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution
The paper introduces TestEvo-Bench, a new benchmark for testing software that evolves with its code. This benchmark is designed to evaluate how well a test automation agent understands the impact of a code change on…
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
Researchers propose a new framework, SPG-Layout, to generate physically plausible indoor scenes in complex non-Manhattan environments. The framework uses statistical priors of object distributions and a hierarchical…
Measuring the Gap Between Human and LLM Research Ideas
The authors explore the gap between ideas generated by Large Language Models (LLMs) and those of human researchers in the field of computer science. They develop an evaluation framework based on high-quality human…
An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping
A new AI framework developed at Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory aims to automate the analysis of large plant imaging datasets generated by automated stations. The framework…
In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
The paper proposes a new method called In-Context Model Predictive Generation (ICMPG) for generating human motions based on textual descriptions in digital applications. The method combines language model planning with…
AI-Assisted Computational Reproducibility on the FABRIC Testbed
This paper discusses how the FABRIC testbed, along with an AI coding assistant named LoomAI, can help simplify reproducing published experiments across various domains. The authors present three case studies and…
GUI agent: Guided Exploration of User-Sensitive Screens
This research presents a new agent called Guided Exploration of User-Sensitive Screens (GUI agent) designed to automate tasks within an open Graphical User Interface (GUI) environment. The GUI agent is intended to…
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
The authors propose a safety mechanism for AI agents called the Unfireable Safety Kernel, which is designed to prevent AI systems from making unauthorized changes within their own runtime. The kernel is implemented in…
Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation
Researchers propose a framework for training Computer-Use Agents (CUAs) using reinforcement learning and autonomous vision-language evaluation. This method provides a scalable supervision signal, improving success…
When CQs Go Wrong: Challenges in CQ Verification with OE-Assist
This research paper discusses the challenges faced during Competency Questions (CQ) verification, a crucial step in ensuring that an ontology accurately represents its intended purpose. The authors found that CQs can…
Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse
Researchers propose a new method called Kamera for efficient use of KV cache by multimodal agents during reasoning iterations. The method avoids the need to re-encode from scratch and reduces the need for multiple…
