All notes, newest first
2,343 notes. Notes 951 to 1,000, page 20 of 47.
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
Researchers propose a new method called PATS for training agents in long-term reinforcement learning tasks. The method uses a dynamic training scaffold that adapts to the evolving policy, providing concrete guidance to…
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
The paper proposes a new training paradigm called PATS for long-horizon reinforcement learning in language models. The method aims to improve weak policies that repeat similar failures by using a policy-centric…
Regulating autonomous and agentic AI
This research paper explores the difficulties in regulating activities that use autonomous and agentic AI. The authors argue that existing regulatory assumptions no longer apply due to the distributed knowledge and…
Regulating autonomous and agentic AI
The paper explores the difficulties in regulating activities that involve autonomous and agentic AI due to the shift in control and knowledge away from the regulatees. The authors investigate four regulatory systems…
Regulating autonomous and agentic AI
The paper explores the difficulties in regulating activities that use autonomous and agentic AI due to changes in regulatee knowledge and control, which often lie outside the AI supply chain. The authors investigate…
Regulating autonomous and agentic AI
This research paper discusses the difficulties in regulating activities that use autonomous and agentic AI due to changes in traditional regulatory assumptions about knowledge and control. The authors analyze four…
RUMBA: Russian User Memory Benchmark
The authors introduce RUMBA (Russian User Memory Benchmark), a new long-term conversational memory benchmark for Russian. It offers a detailed taxonomy of memory-centric question types and a unified methodology that…
RUMBA: Russian User Memory Benchmark
Researchers introduce a new benchmark called RUMBA for evaluating the long-term conversational memory abilities of Language Models (LLMs), particularly focusing on Russian dialogues. The benchmark provides a detailed…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study found that a high-capacity language model (gpt-5.6-sol) behaves differently when presented with dangerous objectives directly compared to when other agents manipulate and relay the instructions. The model gave…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study using OpenAI's gpt-5.6-sol model found that the model gave different advice when presented with a dangerous objective directly compared to when other agents transformed and relayed the direction. When shown an…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study comparing direct exposure to a dangerous objective versus multi-agent mediation using OpenAI's gpt-5.6-sol model reveals that direct exposure leads to advice contrary to the target, while mediated exposure…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study compares the behavior of a high-capability language model when it is given dangerous objectives directly versus through other agents. The results show that the model gives advice against its target when given…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study found that a high-capability language model (gpt-5.6-sol) behaves differently when given a dangerous objective directly compared to when it's transformed and relayed by other agents. When shown the objective…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study tests two scenarios: direct exposure of a dangerous objective to an AI model and the same objective being transformed and relayed by other agents. The results show that the AI model's advice is opposed to the…
Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study
Researchers present CT-TEL workflow, a scalable pipeline that uses Large Language Models (LLMs) to convert clinical trial protocols from unstructured free text into Temporal Ensemble Logic (TEL) formulas. The study…
Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study
Researchers propose a pipeline called CT-TEL that uses Large Language Models (LLMs) to convert narrative clinical trial protocols into a format called Temporal Ensemble Logic (TEL). This conversion allows for automated…
Synthetic data generation framework for quality control automation in gravure printing
Researchers have developed a synthetic data generation framework to help automate the quality control process in gravure printing. The framework generates high-fidelity images of common printing defects and uses them…
The Boundaries of Automation: A Theory of Persistent Human Participation
This research paper questions the assumption that as AI becomes more capable, human participation in tasks will decrease. Instead, it argues that there are three reasons why human participation may persist even with…
The Boundaries of Automation: A Theory of Persistent Human Participation
The paper discusses why human participation in tasks traditionally automated by AI may persist even when highly capable AI systems are available. It identifies three reasons: technical or complementarity grounds…
Thinkink: 2D Spatial Ink-native Interaction with LLMs
The researchers proposed a new tool called Thinkink that integrates large language models (LLMs) into handwritten note-taking and sketching practices. The tool allows users to handwrite or draw on a shared canvas, with…
Thinkink: 2D Spatial Ink-native Interaction with LLMs
The researchers propose Thinkink, a tool that allows users to interact with large language models (LLMs) using handwritten text or sketches on a shared canvas. The tool uses a semantic tree for ink interpretation and a…
Thinkink: 2D Spatial Ink-native Interaction with LLMs
Researchers propose Thinkink, a tool that allows users to interact with large language models (LLMs) using handwritten notes and sketches on a shared digital canvas. The tool was designed through a series of studies to…
Thinkink: 2D Spatial Ink-native Interaction with LLMs
Researchers propose 'Thinkink', a system that allows users to interact with large language models (LLMs) using handwritten notes and sketches, which are then visually integrated into a shared canvas. The system was…
Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought Models
Researchers have found that certain chain-of-thought reasoning models exhibit two types of behavior: converged (where solutions are reached within a set token budget) and non-converged (where the model exhausts the…
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
The paper discusses a reliability challenge caused by AI agents being created by non-engineering users within organizations, due to their dependency on various factors that can cause silent degradation over time. The…
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
The paper proposes a solution to ensure reliability in AI agents created by non-engineering users within organizations, through democratized low-code, no-code, and conversational development environments. The proposed…
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
The paper discusses a reliability challenge created by the democratization of AI agent creation within organizations. To address this, it proposes a lightweight continuous-assurance framework that includes dependency…
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
The paper discusses a reliability challenge in AI agents created by non-engineering users within organizations, due to multiple dependencies that can cause silent degradation after deployment. The authors propose a…
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
The paper proposes a solution for ensuring the reliability of AI agents created by non-engineering users within organizations, as the democratization of AI agent creation can lead to unforeseen dependencies causing…
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
The authors propose a lightweight continuous-assurance framework for ensuring reliability of AI agents created by non-engineering users within organizations through low-code, no-code, or conversational development…
Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation
This research paper proposes a new concept called Cryptographically Verifiable Agent Authorization (CVA). The authors aim to create a system where AI agents can be authorized to perform actions with cryptographic…
Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation
The authors propose a new approach to cryptographically verifiable authorization for autonomous AI agents, which would provide evidence that an agent's request satisfies the applicable policy in a specific execution…
Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation
The paper proposes a cryptographic method to ensure that an autonomous AI agent's authorization request satisfies the applicable policy in a specific execution context, while preserving confidentiality of private…
Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation
The authors propose a model for Cryptographically Verifiable Agent Authorization (CVA), which aims to provide cryptographic evidence that an AI agent's authorization request satisfies the applicable policy in a…
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
Researchers propose FAIRGET, a Visual Question Answering benchmark to evaluate the effectiveness of unlearning (removing personal data from trained models) in multimodal large language models under unbalanced…
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
Researchers propose a new benchmark, FAIRGET, to evaluate the effectiveness of machine unlearning in multimodal large language models under unbalanced, realistic scenarios. They also introduce FAUN, an unlearning…
VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
Researchers introduce a new navigation challenge called Vision-Only Long-Horizon Navigation (VoLN), which aims to shift the route-relevant information from externally supplied instructions and global guidance to…
VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
The text discusses a new navigation system called Vision-Only Long-Horizon Navigation (VoLN) for autonomous agents. In this system, the agent navigates using visual cues instead of relying on route-level instructions…
VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
Researchers introduce Vision-Only Long-Horizon Navigation (VoLN), a new paradigm for autonomous agents to navigate using only onboard sensors and in-scene cues, rather than relying on external instructions. They create…
VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
The researchers propose a new benchmark for vision-based navigation called Vision-Only Long-Horizon Navigation (VoLN). This benchmark is designed for aerial navigation and requires agents to detect, interpret, and…
When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation
A new AI guardrail system called ResponseGuard has been developed that is faster and more efficient than previous reasoning-based systems for real-time moderation of vision-language AI assistants. ResponseGuard uses a…
When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation
A new AI guardrail called ResponseGuard has been developed that can quickly and efficiently detect harmful responses from a vision-language model without needing to go through step-by-step reasoning, which makes…
Active Inference as a Convex Markov Decision Process
The paper presents Active Inference (AIF) as a method that minimizes the expected free energy (EFE), combining both epistemic and pragmatic objectives within a single variational principle. The authors frame AIF as…
Adaptive Bayesian Online Learning via Expert Aggregation
The researchers propose a method for Bayesian online learning that allows for uncertainty-aware predictions on data streams. Instead of fixing inferential choices before seeing the stream, they treat update rules as…
Adaptive deep nonparametric regression from dependent data under covariate shift
The paper discusses a deep neural network approach for nonparametric quantile and Huber regression under covariate shift, where source and target observations come from different distributions. The authors propose a…
Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design
Researchers have developed a new model called AAMFM to improve the design of functional antibodies. This model learns unified representations of antibody sequences and structures, considering antigen context, which…
Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design
Researchers introduce a new model called AAMFM (Antigen-specific Antibody Multimodal Foundation Model) for designing functional antibodies. The model learns unified representations of antibody sequences and structures…
Autonomous Collaborative Learning Among an Ensemble of Tsetlin Machines with Consensus-Based Inference
The researchers propose a decentralized collaborative learning paradigm for an ensemble of Tsetlin Machines (TMs) using consensus-based inference. Each agent has its own private TM model, and they combine individual…
Autonomous Collaborative Learning Among an Ensemble of Tsetlin Machines with Consensus-Based Inference
This research proposes a new learning paradigm for Tsetlin Machines (TM) in a decentralized setting, where multiple TM agents collaborate without exchanging raw data. The paradigm uses consensus-based inference to…
Clinical Pathways as Safety Specifications for Physical AI in Hospital Wards
The paper proposes a robotic architecture for Physical AI systems in hospital wards that uses Clinical Pathways as explicit runtime safety specifications. The system, called Runtime Safety Monitor (RSM), evaluates…
Page 20 of 47
