WTF GENIUS PAPERS Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 339 items • Updated about 15 hours ago • 77
EnvHarness: Awakening Static Worlds for Agent Learning Paper • 2608.19880 • Published 18 days ago • 274
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development Paper • 2608.13417 • Published 25 days ago • 58
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling Paper • 2608.02602 • Published Aug 3 • 82
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement Paper • 2607.23802 • Published Jul 26 • 106
CAST: Game Solvers as Turn-Level Teachers for LLM Agents Paper • 2607.25308 • Published Jul 28 • 42
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization Paper • 2607.25659 • Published Jul 28 • 84
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps Paper • 2605.16928 • Published May 16 • 100
A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning Paper • 2510.15444 • Published Oct 17, 2025 • 151
ChinaTravel: A Real-World Benchmark for Language Agents in Chinese Travel Planning Paper • 2412.13682 • Published Dec 18, 2024 • 7
Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models Paper • 2502.04404 • Published Feb 6, 2025 • 25
STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution Paper • 2501.02976 • Published Jan 6, 2025 • 56