All notes, newest first
2,343 notes. Notes 801 to 850, page 17 of 47.
SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
Researchers propose SciFigQual-Bench, a benchmark for evaluating the quality of scientific figures in computer science papers across five dimensions. The dataset includes over 6,000 images from top conferences between…
Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents
The paper proposes a method called Cost-Aware Marginal Decision-Focused Stopping (CAM-DF) for selecting tools in large language model agents. This method aims to balance between acquiring enough tools and keeping costs…
Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents
A new approach, Cost-Aware Marginal Decision-Focused Stopping (CAM-DF), is proposed for tool selection in Large Language Model (LLM) agents that use external services. The method helps address the challenge of…
Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents
The paper presents a new approach, Cost-Aware Marginal Decision-Focused Stopping (CAM-DF), for tool selection in Large Language Model (LLM) agents that use various external services. The approach addresses the…
ScratchSim: A Procedural Synthetic Data Pipeline for Surface Scratch Detection
The paper introduces ScratchSim, a procedural rendering pipeline that generates large-scale synthetic data for surface scratch detection in industrial quality control. This pipeline uses BlenderProc and produces…
SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response
The study introduces SecRespond, a new benchmark for evaluating AI agents in post-compromise incident response scenarios. The benchmark tests the ability of agents to produce forensic reports and remediation plans…
Setoka: A Benchmark for Hierarchical User Understanding in Personalized Agents over Heterogeneous Data
The researchers propose a benchmark called Setoka to evaluate how well personalized agents understand users' abstract characteristics, such as personality traits and behaviors, beyond just retrieving explicit facts…
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
The paper introduces SkillRise, a reinforcement learning framework that allows large language model agents to learn and reuse skills across related yet distinct tasks. SkillRise improves Pass@1 performance on ALFWorld…
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
SkillRise is a new reinforcement learning framework that helps large language model agents solve related yet distinct tasks more efficiently. It organizes tasks into sequences and uses a single policy to alternate…
The Social Cost of an AI Teammate: How an Artificial Teammate Reshapes Human-Human Communication in Small-Team Decision-Making
A study found that using conversational AI as a teammate in small group decision-making reshapes human communication in several ways. The AI was the most talkative and self-cohesive member but contributed less new…
The Social Cost of an AI Teammate: How an Artificial Teammate Reshapes Human-Human Communication in Small-Team Decision-Making
A study found that when an AI teammate is introduced in small decision-making teams, it becomes the most talkative and self-cohesive member but its contributions lack new information and density. Human teammates in…
Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents
Researchers have proposed a framework called Think Short, Defer Smart (TSDS) for edge LLM agents that can handle complex multi-step tasks while managing their reasoning budget effectively. TSDS integrates a lightweight…
Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents
The paper proposes a framework called Think Short, Defer Smart (TSDS) for LLM agents that follow the ReAct paradigm. This framework helps manage reasoning budget and ensures reliability when deployed at the edge. It…
UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks
The paper presents UrbanDS, a multi-agent system that uses a graph to organize and analyze large-scale and heterogeneous urban data. The system includes a Data Profiling Agent, a Relation Agent, a Planner Agent…
UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks
Researchers have developed a system called UrbanDS that helps automate data science tasks for urban scenarios. UrbanDS is a graph-guided multi-agent system designed to handle large-scale and heterogeneous data…
What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under Browser Automation
Researchers propose a new detection framework that can distinguish between humans, bots, and AI agents browsing the web using browser automation. The proposed framework shows improvement over binary classifiers in…
What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under Browser Automation
Researchers present a new AI detection framework that can distinguish between humans, bots, and AI agents. The study finds that existing binary classifiers struggle to identify AI agents as they browse the web through…
From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon
BAIR's archive describes K-Search as work on translating CUDA optimization expertise into architecture-native MLX strategies for Apple Silicon.
A Computational Ethical Framework for Financial Digital Phenotyping for Mental Health
Researchers propose a computational ethical framework to verify that AI-driven digital phenotyping systems adhere to ethical requirements, specifically focusing on consent, privacy, and fairness. The framework uses…
A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
Researchers introduce APS-RAG, a platform that makes it easier for staff at the Advanced Photon Source (APS) to access institutional knowledge through natural language queries. The platform combines multiple channels…
A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
Researchers have developed a platform called APS-RAG for scientific facilities like the Advanced Photon Source (APS). The platform aims to make the vast amount of institutional knowledge accessible through natural…
A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
Researchers have developed APS-RAG, a platform that helps scientists at the Advanced Photon Source (APS) access institutional knowledge through natural language queries. The platform uses a retrieval engine that fuses…
Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
Researchers have developed APPA (Agentic Permissions Policy Algebra), an Information Flow Control (IFC) framework designed to enhance security in Large Language Model (LLM) agents that handle mixed-confidentiality data…
Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
Researchers have proposed a new framework called APPA (Agentic Permissions Policy Algebra) to enhance the security of large language model (LLM) agents while maintaining their usability. The proposed framework…
Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
Researchers propose APPA, an IFC framework to address usability issues in LLM agents handling mixed-confidentiality data. The proposed solution involves engine-managed context branching and prospective acquisition…
Artificial Intelligence and Innovation Ecosystem: Evolutionary Developments, Challenges, and Future Directions
This research investigates the influence of Artificial Intelligence (AI) on the Innovative Ecosystem (IE), a new paradigm for economic integration and collaboration. The study analyzes AI's unique contributions to IE…
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
Researchers propose a new method for controlling risk in language model agents' actions, which are performed through structured tool calls. The proposed method, called role-stratified per-field conformal risk control…
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
Researchers introduce a new method called role-stratified per-field conformal risk control for language model agents that perform actions through structured tool calls. This method aims to ensure safety by setting…
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
The paper introduces ClinFusion, a system designed for holistic medical understanding using multimodal large language models (MLLMs). ClinFusion addresses challenges in the medical domain by unifying diverse 2D and…
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
The paper introduces ClinFusion, a multimodal large language model designed for holistic medical understanding. It can handle both 2D and 3D medical images and outperforms other open-source and proprietary models on…
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
Researchers have developed a new multimodal large language model called ClinFusion for understanding medical information from various image sources. The model outperforms leading open-source models and proprietary ones…
Closed-Loop Validation-Repair for Healthcare Interoperability: A Multi-Model Study of Schema Compliance in Clinical LLMs
A study evaluates three large language models (Qwen2.5 7B, Llama 3.1 8B, and Gemma2 9B) on their compliance with healthcare standards such as ICD-10, CPT, and HL7 FHIR in 320 clinical scenarios. The study found that…
Closed-Loop Validation-Repair for Healthcare Interoperability: A Multi-Model Study of Schema Compliance in Clinical LLMs
The study evaluates three large language models (Qwen2.5 7B, Llama 3.1 8B, and Gemma2 9B) in the context of healthcare interoperability. The models were assessed across 320 clinical scenarios for their compliance with…
DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data
The paper proposes a framework called DataOrchestra that learns to curate pre-training data example-by-example rather than applying a uniform strategy across many examples. The framework decides whether to drop, clean…
DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data
Researchers propose a framework called DataOrchestra that adapts data processing strategies for each example in Large Language Models (LLMs) pretraining, improving performance across 11 benchmarks.
DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense
In this paper, the authors propose a framework called DeepFaith to create more accurate and reliable incident reports in multi-stage APT defense. The framework uses large language models (LLMs) and ensures that…
Efficiency Matters in Autonomous Research
The paper argues that while AI-driven autonomous research (AR) systems are effective at producing high-quality outcomes, their efficiency in the solution-search process is often overlooked. The authors propose…
Efficiency Matters in Autonomous Research
This research paper argues that not only the quality of results but also the efficiency of the solution-search process is crucial for AI-driven autonomous research systems. The authors propose evaluating AR systems…
Efficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures
Researchers present a study where they use a large language model (LLM) called Claude Opus 4.7 to generate and refine Python code for shuttling compilers in trapped-ion quantum computers. The compilers are designed for…
Efficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures
Researchers used a large language model named Claude Opus 4.7 to generate and refine Python code for shuttling compilers in trapped-ion quantum computers. The study covers three types of architectures: linear segmented…
Epistemic Norms for AI Safety and Alignment Research
The text discusses a new epistemic code named ECAISA for AI Safety and Alignment Research, which aims to ensure that catastrophic failures in AI never occur under specific conditions. The code focuses on two main…
ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams
A new benchmark called ERUnderstand has been introduced for evaluating the ability of Vision-Language Models (VLMs) to understand Entity-Relationship Diagrams (ERDs), which are important in database design. The…
Evaluating RAG for French immigration law: a benchmark and baseline study
The paper presents a new benchmark for evaluating AI models used in French immigration law, focusing on permit-type recommendation, required document retrieval, and legal citation coverage. The study compares a…
Evaluating RAG for French immigration law: a benchmark and baseline study
The authors present a new benchmark for evaluating AI models in the context of French immigration law. They compare a parameterized language model baseline with dense retrieval augmentation at two scales (Qwen3.5-9B…
Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review
A study investigates how the level of explanation in AI-assisted code reviews affects developer trust and agreement with AI recommendations. The results show that full explanations lead to higher perceived trust but…
Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review
A study investigates the impact of Explainable AI (XAI) on developers' trust in AI-assisted code reviews. The research compared three LLM-based code review systems with varying levels of XAI support. Results show that…
Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating
The authors present a new approach for managing a language model's working memory by treating the decision of which stored items to keep as an estimation problem. They introduce a method called 'fixed-lag smoothing'…
Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers
Researchers present a new framework called RecursiveECG that uses a language model (LLM) to improve ECG classifiers by analyzing the reasons for individual case failures and suggesting targeted revisions based on…
Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers
Researchers present a new framework called RecursiveECG that uses a language model (LLM) to automatically design ECG classifiers by learning from specific failures and objective ECG evidence. The LLM is used as an…
Falsifiable Commitment Planning for Self-Correcting Web Agents
Researchers propose a new framework called FCPAgent for web agents to ensure they stay on track during long-term planning. The framework represents each plan step as a Falsifiable Commitment Unit (FCU) that includes…
Page 17 of 47
