論文・研究の記事
trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories
arXiv:2609.00038v1 Announce Type: new Abstract: Outcome-only evaluation is the production default for LLM agents: show a judge the request and the final reply and ask whether it was handled well. The metric is structura…
UI-Venus-2 Technical Report
arXiv:2609.00028v1 Announce Type: new Abstract: Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable real-world applicati…
OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets
arXiv:2609.00015v1 Announce Type: new Abstract: AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, controllers, and execution…
EULER: Exploring Underused Links with Evidence-Checked Return for Multi-Agent Mathematical Discovery
arXiv:2609.00032v1 Announce Type: new Abstract: Mathematical communities work with different objects, invariants, and tools, so transferring a problem across them is expensive and often skipped. We present EULER, a mult…
CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language
arXiv:2609.00058v1 Announce Type: new Abstract: Developing high-performance CUDA kernels demands specialized knowledge in algorithm implementation, correctness validation, and hardware-aware parallel optimization, creat…
Discrete-Time MDP Modeling for Multi-Item Capacitated Lot Sizing with Stochastic Demand Timing
arXiv:2609.00004v1 Announce Type: new Abstract: This paper studies a finite-horizon multi-item capacitated lot-sizing problem in which demand quantities are deterministic, while demand-arrival periods are stochastic. Ea…
Long-Horizon State Tracking in LLMs: Executing MD5 through a Deep Sequence of Dependent Tool Calls
arXiv:2609.00012v1 Announce Type: new Abstract: Long-horizon tasks remain uncommon in large language model (LLM) evaluation, and for a reason: when each step depends on the last, per-step accuracy that looks excellent i…
GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments
arXiv:2609.00048v1 Announce Type: new Abstract: GUI world models are increasingly evaluated as one-step next-screen predictors, yet their intended use is often as multi-step environments for GUI agents. This mismatch le…
From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
arXiv:2609.00051v1 Announce Type: new Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the internal mechanisms b…
Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents
arXiv:2609.00065v1 Announce Type: new Abstract: A language-model agent asked to analyse an experiment will usually return working code. Whether the analysis is defensible is a different question. A defensible analysis d…
ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation
arXiv:2609.00057v1 Announce Type: new Abstract: Value signals are aggregated user-level moral representations that capture users' inferred value-related tendencies from their online discourse. User behavior on social me…
Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models
arXiv:2609.00005v1 Announce Type: new Abstract: Financial scams targeting older adults increasingly occur through text and voice channels such as email, SMS, and phone calls, unfolding over multiple conversational turns…
Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment
arXiv:2609.00055v1 Announce Type: new Abstract: Self-supervised respiratory encoders lack semantic grounding in clinical domain needed for zero-shot inference, limiting their utility without task-specific labeled data.…
Medical Causal Hypothesis Verification with Large Language Models
arXiv:2609.00063v1 Announce Type: new Abstract: The growing use of large language models (LLMs) for search and information retrieval underscores the need to evaluate their reliability in high-stakes domains such as heal…
I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models
arXiv:2609.00003v1 Announce Type: new Abstract: Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress in generative machin…
SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diagram QA and Chain-of-Thought Reasoning Traces
arXiv:2609.00018v1 Announce Type: new Abstract: Computer science papers rely heavily on diagrams: architecture drawings, system flowcharts, and pipeline schematics that often carry more information than the text around…
HyperWorld: Hypergraph-Structured State Serialization Improves Learned Textual World Models
arXiv:2609.00002v1 Announce Type: new Abstract: World models enable language-model agents to predict environment dynamics and plan before acting. In text environments, the model must learn symbolic action effects from s…
When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation
arXiv:2609.00071v1 Announce Type: new Abstract: Prediction error is widely used to evaluate nuisance-function estimators in causal inference, but its relationship with causal estimator performance may differ across perf…
Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning
arXiv:2609.00014v1 Announce Type: new Abstract: Persona-driven techniques increasingly adapt large language models (LLMs) to diverse contexts. However, existing methods predominantly rely on rigid, synthetic personas th…
RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving
arXiv:2609.00062v1 Announce Type: new Abstract: Data contamination undermines the reliable evaluation of large language models (LLMs) on mathematical problem solving. While rewriting-based evaluation mitigates memorizat…