Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
Recent LLM-based mathematical reasoning agents have begun to tackle research-level problems and, in several cases, have contributed to the resolution of open problems. However, scaling and orchestrating such agents effectively remains challenging, due to the difficulty of coordinating parallel proof search while keeping intermediate claims organized and reliable. In this paper, we propose Danus, an orchestration system for research-level mathematical reasoning centered on a shared fact graph as a global memory-management mechanism. Danus consists of a main agent that performs planning and coor
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorJihao Liu →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorGuoxiong Gao →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorZeming Sun →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorBin Wu →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorShurui Liu →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorJiedong Jiang →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorHaocheng Ju →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorLeheng Chen →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorRonnie Cheng →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorXiping Zhang →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
- Linked via arxiv authorBin Dong →
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory