All notes, newest first
2,343 notes. Notes 651 to 700, page 14 of 47.
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
The paper introduces CoPlan, a new AI system designed to aid in care planning. CoPlan allows various stakeholders like clinicians, patients, and caregivers to collaborate on complex decisions by generating potential…
Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools
Researchers introduce 'canary tools' to diagnose why language models choose wrong tools in specific tasks. The study evaluates eight different models across three capability tiers and finds that susceptibility drops…
EviGraph: Evidence-Guided Autonomous Research Agents
The paper introduces EviGraph, a framework for autonomous research agents that maintains and validates an 'evolving claim-evidence structure' throughout the research process. The goal is to reduce unsupported claims…
From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking
The paper presents an auditable information harness that combines dynamic Poisson-family models and large language models (LLMs) to forecast football scores. The system goes through four iterations, each improving on…
Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent
Researchers present Guideline-as-Oracle (GAO), a method to train an ophthalmic telephone triage agent without relying on expensive expert annotations or confidential clinical conversations. Instead, they use a rule…
Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent
Researchers present Guideline-as-Oracle (GAO), a method for training an ophthalmic telephone triage agent using guidelines from the American Academy of Ophthalmology as the only source of instance-level supervision…
Hardware Design and Security in the Era of Chiplets and LLMs
The semiconductor industry is experiencing a double revolution with the shift towards heterogeneous 2.5D chiplet systems and the integration of Large Language Models (LLMs) into Electronic Design Automation (EDA)…
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
The authors propose HiGram, a hierarchical graph memory framework for long-term reasoning agents. This framework aims to efficiently update memories over time by organizing them into a coarse-to-fine architecture…
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
The authors propose HiGram, an evolving hierarchical graph memory framework that aims to improve the efficiency and effectiveness of long-term reasoning agents by reducing irrelevant information during retrieval and…
InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval
The paper proposes a new method called InsightEmb for learning action-intent embeddings to improve agentic insight retrieval, which helps self-improving agents make better decisions by using insights from prior…
Item Response Theory for AI Safety
The paper proposes using Item Response Theory (IRT) to measure the safety of language models. IRT is a statistical method used to analyze the latent traits of individuals from their performance on specific tasks. The…
Item Response Theory for AI Safety
The paper presents a study using Item Response Theory (IRT) to analyze the safety of language models. The authors find that three factors - refusal strictness, truthfulness, and contextual harm - explain most of the…
Item Response Theory for AI Safety
Researchers used Item Response Theory (IRT), a statistical toolkit, to analyze the safety performance of 192 language models across eight different safety benchmarks. The study found that three key factors - refusal…
MarsCast: Transfer Learning of AI Weather Foundation Models to Planetary Atmospheres
Researchers adapted the GraphCast graph neural network weather forecasting model to Mars, achieving accurate predictions of current conditions with zero-shot training. Fine-tuning improved forecasts by capturing…
MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation
In the paper 'MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation', the authors propose a new approach for training wireless foundation models. Instead of pre-training on channel tensors…
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment
Researchers propose NSF-HRPT, a framework that uses a Neural Semantic Field (NSF) to model scene semantics, trajectory predictions, and probabilistic Time-to-Collision (TTC) distributions from simulation data. During…
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment
The research introduces NSF-HRPT, a framework that uses neural semantic fields and structured reasoning to accurately assess risks in safety-critical scenarios such as autonomous driving. The method learns to model…
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
The research presents a new approach called OctoLong for creating longer contexts for language models. It uses an AST parser, a language server backend, and a package manager to retrieve code references from various…
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
In this research, a new pipeline called OctoLong is introduced to enhance the training of language models (LM) by providing them with long code contexts. This is done through the use of an AST parser, a language server…
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
The paper introduces a new method called On-Policy Self-Distillation with Visual Modality Balance (OPD-V) to improve the visual reasoning of multimodal large language models. The authors argue that previous methods…
ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration
The paper presents ORACLE, a multi-objective reinforcement learning-based framework for optimizing analog circuit design. The framework addresses limitations of existing methods by using vector-valued learning and…
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
The study investigates self-distillation (SD), a method used in reinforcement learning for efficient teaching by a 'teacher' using privileged information about the answer. The research finds that while SD reproduces…
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
The research investigates self-distillation (SD), a method used in reinforcement learning with verifiable rewards, where a teacher conditioned on privileged information supplies supervision to a student. The study…
RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
The text discusses a new benchmark called RepoProbe for evaluating the ability of Large Language Models (LLMs) to understand repository-scale code. The benchmark uses open-ended questions from GitHub Discussions and…
Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems
The paper proposes using representation theorems in decision theory to evaluate and regulate Large Language Models (LLMs) and other AI systems. The 'if and only if' structure allows for axiom compliance checks from the…
Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems
The paper suggests using representation theorems in decision theory to evaluate and regularize Large Language Models (LLMs) and other AI systems. This approach checks if the model's behavior complies with certain…
Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
Researchers present a new method for recognizing incidents in classrooms using computer vision while maintaining privacy and computational efficiency. The method uses motion reasoning based on human actions…
Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First
The researchers introduce SuperScout, a cost-effective solution for routing language models to resolve software issues in repositories. SuperScout first explores the repository and produces a structured handoff, which…
Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First
Scrouting is a new system that aims to solve software issues more efficiently by first exploring a repository and then routing the issue to the appropriate model for resolution. This approach, presented in the paper…
Short-term load forecasting under EU-AI Act Requirements in Safety-Critical Environments: Results from a 41-day live challenge on the aggregated German transmission-grid load
A 41-day live challenge was conducted to evaluate a short-term load forecasting (STLF) pipeline for the aggregated German transmission grid. The pipeline uses the open-source Python library spotforecast2-safe, which…
The Effect of Perceived Race and Gender on Police Language Use: Experimental Evidence from VR Simulations
Researchers studied how police officers speak to virtual characters depicted as Black adult males in VR simulations. The study found that most officers speak less deferentially to Black male characters, except for…
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
The study investigates how effective relaying key-value caches between multi-agent language models is, particularly when the receiver does not need the sender's private information. The research shows that when the…
When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs
The research examines the claim that multi-agent language models (LLMs) transmit 'latent thoughts' through relayed key-value caches instead of text, and finds significant evidence for this claim when the receiver needs…
When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
The study identifies a risk in NAVSIM v2.2 original scene single-stage scoring where reference-conditioned forgiveness can propagate shared reference failures into compliance credit, potentially leading to incorrect…
When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
The paper discusses a flaw in the NAVSIM v2.2 defensive driving evaluation system where shared rollouts can lead to misleading compliance credit. This issue is demonstrated through a series of experiments and is…
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
The researchers present a study to make knowledge distillation training efficient for small language models deployed under tight constraints. They propose two methods: offline knowledge distillation (caching teacher's…
Implementing Causal Perception: Competing SCMs and Situated Fairness
The paper presents the first implementation of a causal perception framework for multi-agent systems. This framework helps agents reason about a system and perceive its fairness when they have different interpretations…
The Transformer Revolution, Part 1: Dynamic Processing through Output- Weight Interconnections
The paper proposes a new interpretation of Transformers during inference, suggesting they construct prompt-dependent transformations whose parameters are generated during inference. This form of computation is named…
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
The authors propose a framework called TurnSight for Tool-Integrated Reasoning (TIR). This framework aims to improve fine-grained credit assignment in long-horizon TIR scenarios by addressing the limitations of…
VIBE: A VAD-Informed Benchmark for Entity-Centered Affective Profiling of Large Language Model Outputs
The text introduces VIBE, a new benchmark for analyzing the emotional tone of language models' outputs. The benchmark measures valence (positive or negative), arousal (exciting or calm), and dominance (powerful or…
When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding
Researchers propose EcoFrame, a framework for adaptively scheduling visual evidence selection in long videos for efficient video understanding by vision-language models (VLMs). The method uses the VLM's inference…
DarwinX: Evolving Agent Harnesses Through Natural Selection
The paper proposes improving AI agents not by changing the underlying model weights, but by evolving the surrounding "harness" (prompts, tools, workflow scaffolding) through a selection process across a population of…
A foundation model of numerical intelligence with cross-disciplinary generalization
The paper introduces UNified In-Context Operator Networks (UNICON), a model that demonstrates numerical intelligence across various disciplines. It is capable of inferring predictive relations from graph-based examples…
A foundation model of numerical intelligence with cross-disciplinary generalization
Researchers introduce UNified In-Context Operator Networks (UNICON), a new AI model that can understand and solve numerical problems across various scientific and social systems. The model uses graph-based examples to…
A foundation model of numerical intelligence with cross-disciplinary generalization
Researchers introduce UNICON, a foundation model that exhibits numerical intelligence across various disciplines. This model can infer relationships from graph-based examples within a system and apply them to queries…
Agentic Metaverse Services: A New As-a-Service Paradigm
The paper discusses a new concept called Agentic Metaverse Services (AMServ), which combines advanced Generative Artificial Intelligence (GenAI) with the metaverse to create a virtual ecosystem for various aspects of…
Agentic Metaverse Services: A New As-a-Service Paradigm
The paper discusses Agentic Metaverse Services (AMServ), a new paradigm of agentic services and service computing, that combines Generative Artificial Intelligence (GenAI) with the metaverse to provide customized agent…
Agentic Method for Deterministic Validation of Legacy Code Migration
The paper proposes a new method called 'Locksmith Loop' to simplify the testing process when migrating COBOL programs to Java. The method uses mocks, iterative agentic loops, and parity-preserving mutations to ensure…
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…
Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation
Researchers introduce a new method called budget-constrained confidence-scheduled restricted responses (CS-RNR) for safe opponent exploitation in two-player zero-sum imperfect-information games. The method allows an…
Page 14 of 47
