日次実行レポート 2026-06-25
生成: 2026-06-25T06:00:01 ・ エンジン: llm:gemma-4-26b
自動倉庫におけるマルチエージェント計画・タスク形成最適化
候補 42 / 新規 19 / 追加 0 / スキップ 19
スキップ
- SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety (関連キーワードが弱い)
- CodeAlchemy: Synthetic Code Rewriting at Scale (関連キーワードが弱い)
- PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting (関連キーワードが弱い)
- BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine (関連キーワードが弱い)
- Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings (関連キーワードが弱い)
- Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States (関連キーワードが弱い)
- Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue (関連キーワードが弱い)
- The Right Inference Strategy Is All You Need: Nearly Training-Free Domain-Wise Inference for EgoCross Challenge (関連キーワードが弱い)
- Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation (関連キーワードが弱い)
- MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks (関連キーワードが弱い)
- AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment (関連キーワードが弱い)
- BiAxisAudit: A Novel Framework to Evaluate LLM Bias Across Prompt Sensitivity and Response-Layer Divergence (関連キーワードが弱い)
- IntentGrasp: A Comprehensive Benchmark for Intent Understanding (関連キーワードが弱い)
- VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation (関連キーワードが弱い)
- Toward a Unified Framework for Collaborative Design of Human-AI Interaction (関連キーワードが弱い)
- Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer (関連キーワードが弱い)
- No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs (関連キーワードが弱い)
- Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation (関連キーワードが弱い)
- All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding (関連キーワードが弱い)
文書構造解析に基づく検索・質問応答・RAG
候補 153 / 新規 139 / 追加 2 / スキップ 1
追加
- 新着論文 / 採択先 未取得 / 読む価値 4 / 関連度 5 / 被引用 0: Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity
- 補充候補 / 採択先 未取得 / 読む価値 4 / 関連度 5 / 被引用 0: ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphs
スキップ
- SPR-RAG: Semantic Parsing Retriever-Enhanced Question Answering for Power Policy (本文未取得(アブストラクトのみ))