Full Traces Lift Multi-Agent Attribution Accuracy 76%

Featured

• Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond score 7
  入选 HF Daily Papers; HF 热度: 2 upvotes (+1); 有代码实现; 关键词(1): agentic

Also Worth Noting

• STEM: Structure-Tracing Evidence Mining for Knowledge Graphs-Driven Retrieval-Augmented Generation score 4
  关键词(2): retrieval-augmented, reasoning; 顶会接收: ACL
• Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization score 4
  关键词(1): deployment; 顶会接收: CVPR
• Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding score 4
  关键词(2): lightweight, open-source; 顶会接收: ACL
• Selective Contrastive Learning For Gloss Free Sign Language Translation score 4
  关键词(2): pretraining, vision-language; 顶会接收: ACL
• AgentSearchBench: A Benchmark for AI Agent Search in the Wild score 4
  入选 HF Daily Papers; 关键词(1): lightweight
• RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment score 4
  关键词(2): deployment, serving; 顶会接收: ACL
• Learning Evidence Highlighting for Frozen LLMs score 4
  入选 HF Daily Papers; 关键词(2): lightweight, reasoning
• Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems score 4
  关键词(1): reasoning; 顶会接收: ACL
• Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models score 3
  顶会接收: ACL
• UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions score 3
  顶会接收: ACL
• CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems score 3
  顶会接收: ACL
• Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization score 3
  顶会接收: ACL