Awesome Artificial Intelligence

Key papers

• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning (2025)
  DeepSeek-AI et al.
  21.94
• Arcee's Mergekit: A Toolkit For Merging Large Language Models (2024)
  Charles Goddard, Shamane Siriwardhana, Malikeh Ehghaghi, et al.
  18.99
• Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL (2025)
  Weizhen Li et al.
  18.23
• SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning (2025)
  Zhongwei Wan et al.
  16.17
• OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data (2026)
  Jiwen Liu et al.
  14.82
• Toward Generalist Autonomous Research via Hypothesis-Tree Refinement (2026)
  Jiajie Jin et al.
  14.49
• Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution (2026)
  Liliana Hotsko et al.
  12.93
• FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention (2026)
  Yan Wang et al.
  12.92
• SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks (2026)
  Hongcheng Gao et al.
  12.37
• HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers (2026)
  Guozhen Zhang et al.
  12.25
• Rethinking RAG in Long Videos: What to Retrieve and How to Use It? (2026)
  Yuho Lee et al.
  11.90
• MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents (2025)
  Kunlun Zhu et al.
  11.84
• EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents (2026)
  Weixian Xu et al.
  11.34
• Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World (2026)
  Yusong Lin et al.
  10.88
• DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off (2026)
  Xiaofan Li et al.
  10.80
• MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery (2026)
  Shangheng Du et al.
  10.72
• From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills (2026)
  Zisu Huang et al.
  10.54
• SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills (2026)
  Yingtie Lei et al.
  10.29
• One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA (2026)
  Zhi Zheng et al.
  10.21
• QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents (2026)
  Ye Yuan et al.
  10.15
• Doremi: Grounding Language Model By Detecting And Recovering From Plan-execution Misalignment (2023)
  Yanjiang Guo, Yen-Jen Wang, Lihan Zha, et al.
  9.92
• Unsupervised Skill Discovery for Agentic Data Analysis (2026)
  Zhisong Qiu et al.
  9.90
• HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs (2026)
  Yansong Ning et al.
  9.84
• When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents (2026)
  Dongsheng Zhu et al.
  9.73
• MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining (2025)
  LLM-Core Xiaomi: Bingquan Xia et al.
  9.66
• Adaptive-solver Framework For Dynamic Strategy Selection In Large Language Model Reasoning (2023)
  Jianpeng Zhou, Wanjun Zhong, Yanlin Wang, et al.
  9.50
• ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions (2026)
  Chuanyang Jin et al.
  9.41
• ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism (2025)
  Jia Liu et al.
  8.67
• Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training (2026)
  Yuanda Xu et al.
  8.60
• Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders (2026)
  Yi Jing et al.
  8.60
• Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring (2026)
  Seongheon Park et al.
  8.51
• TuRTLe: A Unified Evaluation of LLMs for RTL Generation (2025)
  Dario Garcia-Gasulla et al.
  8.39
• Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification (2025)
  Xu Xu et al.
  8.37
• Language-conditioned Imitation Learning With Base Skill Priors Under Unstructured Data (2023)
  Hongkuan Zhou, Zhenshan Bing, Xiangtong Yao, et al.
  8.35
• Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior (2026)
  Rafal Kocielnik et al.
  8.24
• OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework (2024)
  Jian Hu et al.
  7.89
• Towards Autonomous Mechanistic Reasoning in Virtual Cells (2026)
  Yunhui Jang et al.
  7.58
• optimize_anything: A Universal API for Optimizing any Text Parameter (2026)
  Lakshya A Agrawal et al.
  7.30
• HiPlan: Hierarchical Planning for LLM-Based Agents with Adaptive Global-Local Guidance (2025)
  Ziyue Li et al.
  7.17
• PATS: Process-Level Adaptive Thinking Mode Switching (2025)
  Yi Wang et al.
  7.13
• Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs (2025)
  Jaemin Kim et al.
  7.11
• MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control (2026)
  Yuchi Wang et al.
  7.04
• PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning (2025)
  Wenfeng Feng et al.
  6.97
• Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing (2025)
  Jinwei Hu et al.
  6.91
• ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning (2025)
  Hanyang Chen et al.
  6.67
• Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization (2026)
  Jiarui Yao et al.
  6.67
• Multi-Agent Causal Discovery Using Large Language Models (2024)
  Hao Duong Le et al.
  6.56
• ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces (2026)
  Jinu Lee et al.
  6.50
• Multi-Turn Code Generation Through Single-Step Rewards (2025)
  Arnav Kumar Jain and Gonzalo Gonzalez-Pumariega and Wayne Chen and Alexander M Rush and Wenting Zhao and Sanjiban Choudhury
  6.43
• REALM-Bench: A Benchmark for Evaluating Multi-Agent Systems on Real-world, Dynamic Planning and Scheduling Tasks (2025)
  Longling Geng and Edward Y. Chang
  6.41
• AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms (2025)
  Zhenxing Xu et al.
  6.29
• Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets (2025)
  Adam Younsi et al.
  6.28
• Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems (2024)
  Shengming Zhao et al.
  6.19
• Rewarding The Scientific Process: Process-level Reward Modeling For Agentic Data Analysis (2026)
  Zhisong Qiu, Shuofei Qiao, Kewei Xu, et al.
  5.90
• LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI (2026)
  Lalit Yadav et al.
  5.88
• ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis (2026)
  Guohong Liu et al.
  5.82
• Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning (2025)
  Xin Qiu et al.
  5.71
• Graph of States: Solving Abductive Tasks with Large Language Models (2026)
  Yu Luo et al.
  5.69
• Koshur Diacritizer: A Byte-Level Sequence-to-Sequence Model for Kashmiri Diacritic Restoration (2026)
  Haq Nawaz Malik et al.
  5.49
• Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Humans (2024)
  Yu Lei et al.
  5.40