Study group · Map
A map
of papers.
The library and the radar as one network. Papers that treat similar topics, by shared tags and by the words of their abstracts, sit close together and are joined by a line. Drag to pan, scroll or pinch to zoom, click a paper to open it.
All papers on the map, by cluster
agent · benchmark · research
- ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents ↗
- MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching ↗
- iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents ↗
- TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents ↗
- From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings ↗
- Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents ↗
- Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling ↗
multi-turn · interaction · doe
- Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling ↗
- EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL ↗
- Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute? ↗
- Axion 1.0: Open Agent Foundation Models, Simplified ↗
- What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? ↗
- TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing ↗
- A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement ↗
policy · reasoning · space
- OneTrans-GSR: A Generative Slate Ranking Paradigm Unifying Reranking and Mix-Ranking with One Autoregressive Transformer ↗
- Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training ↗
- ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning ↗
- Latent Reasoning in Continuous Space for Unified Multimodal Models ↗
- WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search ↗
- Towards Foundation Decision Models: Drex ↗