Papers

• OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment (2026)
  Ming Zhang et al.
  6.91
• Skill-Contracted Agents for Evidence-Aware Materials Literature Analysis (2026)
  Bixuan Li et al.
  5.01
• REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning (2026)
  Zhensheng Jin et al.
  5.01
• LegalCiteTrust: Benchmarking Citation Trustworthiness in Chinese Long-Form Legal Research Reports (2026)
  Yunhan Li et al.
  5.01
• QuantiBias: Benchmarking Quantization-Induced Bias in LLMs (2026)
  Emilio Ferrara
  5.01
• Error Certificates for KV-Cache Eviction via Randomized Design (2026)
  Peng Xie
  4.39
• When Should LLMs Search? Counterfactual Supervision for Search Routing (2026)
  Minho Kim
  3.51
• QUBO-Optimized Evidence Selection for Retrieval-Augmented Question Answering with Unconventional Solvers (2026)
  Rahul Singh et al.
  3.51
• On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage (2026)
  Vinay Kumar Chaganti
  2.00
• ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes (2026)
  Qihao Zhao et al.
  2.00
• Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models (2026)
  Ruchit Rawal et al.
  2.00
• Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts (2026)
  Chen Yang et al.
  1.72
• Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling (2025)
  Hao Mark Chen et al.
  1.22