Key papers

• More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG (2025)
  Shahar Levy et al.
  2.87
• EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines (2026)
  Shuo Zhang et al.
  1.94
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction (2026)
  Zhuofeng Li et al.
  1.94
• Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs (2026)
  Wanli Yang et al.
  1.94
• Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs (2026)
  Fahd Seddik et al.
  1.94
• InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis (2026)
  Oliver Bentham et al.
  1.83
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration (2026)
  Bowei He et al.
  1.72
• ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026)
  Zheng Liu et al.
  1.67
• Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction (2025)
  Rui Qian et al.
  1.28
• Search-o1: Agentic Search-Enhanced Large Reasoning Models (2025)
  Xiaoxi Li et al.
  1.28
• START: Self-taught Reasoner with Tools (2025)
  Chengpeng Li et al.
  1.28
• VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering (2025)
  Yanling Wang et al.
  1.28
• PlainQAFact: Automatic Factuality Evaluation Metric for Biomedical Plain Language Summaries Generation (2025)
  Zhiwen You et al.
  1.28
• Typed-RAG: Type-aware Multi-Aspect Decomposition for Non-Factoid Question Answering (2025)
  DongGeon Lee et al.
  1.28
• MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models (2025)
  Wulin Xie et al.
  1.28
• ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models (2025)
  Liyan Tang et al.
  1.28
• s3: You Don't Need That Much Data to Train a Search Agent via RL (2025)
  Pengcheng Jiang et al.
  1.28
• Visual Agentic Reinforcement Fine-Tuning (2025)
  Ziyu Liu et al.
  1.28
• FREESON: Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS (2025)
  Chaeeun Kim et al.
  1.28
• FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow (2025)
  Haoyu Sun et al.
  1.28
• MIRIAD: Augmenting LLMs with millions of medical query-response pairs (2025)
  Qinyue Zheng et al.
  1.28
• Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering (2025)
  Bolei He et al.
  1.28
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use (2025)
  Dongfu Jiang et al.
  1.28
• BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions (2025)
  Zhengbo Zhang et al.
  1.28
• Explore to Evolve: Scaling Evolved Aggregation Logic via Proactive Online Exploration for Deep Research Agents (2025)
  Rui Wang et al.
  1.28
• Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation (2025)
  Su Ho Han et al.
  1.28
• ScreenAI: A Vision-Language Model for UI and Infographics Understanding (2024)
  Gilles Baechler et al.
  —
• CRAG -- Comprehensive RAG Benchmark (2024)
  Xiao Yang et al.
  —
• Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation (2024)
  Jirui Qi et al.
  —
• video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models (2024)
  Guangzhi Sun et al.
  —
• SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation (2024)
  Zijun Yao et al.
  —
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases (2024)
  Zhaorun Chen et al.
  —
• Visual Haystacks: Answering Harder Questions About Sets of Images (2024)
  Tsung-Han Wu et al.
  —
• HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models (2024)
  Haoran Que et al.
  —
• MM-Ego: Towards Building Egocentric Multimodal LLMs (2024)
  Hanrong Ye et al.
  —
• HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems (2024)
  Jiejun Tan et al.
  —
• O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson? (2024)
  Zhen Huang et al.
  —
• MapQaTor: A System for Efficient Annotation of Map Query Datasets (2024)
  Mahir Labib Dihan et al.
  —