Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.06261 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908874740596736 |
|---|---|
| author | Zhou, Zhanke Cao, Chentao Feng, Xiao Li, Xuan Li, Zongze Lu, Xiangyu Yao, Jiangchao Huang, Weikai Cheng, Tian Zhang, Jianghangfan Jiang, Tangyu Xu, Linrui Zheng, Yiming Miranda, Brando Liu, Tongliang Koyejo, Sanmi Sugiyama, Masashi Han, Bo |
| author_facet | Zhou, Zhanke Cao, Chentao Feng, Xiao Li, Xuan Li, Zongze Lu, Xiangyu Yao, Jiangchao Huang, Weikai Cheng, Tian Zhang, Jianghangfan Jiang, Tangyu Xu, Linrui Zheng, Yiming Miranda, Brando Liu, Tongliang Koyejo, Sanmi Sugiyama, Masashi Han, Bo |
| contents | We present AlphaApollo, an agentic reasoning system that targets two bottlenecks in foundation-model reasoning: (1) limited reasoning capacity for complex, long-horizon problem solving and (2) unreliable test-time evolution without trustworthy verification. AlphaApollo orchestrates models and tools via three components: (i) multi-turn agentic reasoning, which formalizes model-environment interaction with structured tool calls and responses; (ii) multi-turn agentic learning, which applies turn-level reinforcement learning to optimize tool-use reasoning while decoupling actions from tool responses for stable training; and (iii) multi-round agentic evolution, which refines solutions through a propose-judge-update loop with tool-assisted verifications and long-horizon memory. Across seven math reasoning benchmarks and multiple model scales, AlphaApollo improves performance through reliable tool use (> 85% tool-call success), substantial gains from multi-turn RL (Avg@32: Qwen2.5-1.5B-Instruct 1.07% -> 9.64%, Qwen2.5-7B-Instruct 8.77% -> 20.35%), and improvements from evolution (e.g., Qwen2.5-3B-Instruct 5.27% -> 7.70%, Qwen2.5-14B-Instruct 16.53% -> 21.08%). This project is still ongoing. We welcome feedback from the community and will frequently update the source code and technical report. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06261 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AlphaApollo: A System for Deep Agentic Reasoning Zhou, Zhanke Cao, Chentao Feng, Xiao Li, Xuan Li, Zongze Lu, Xiangyu Yao, Jiangchao Huang, Weikai Cheng, Tian Zhang, Jianghangfan Jiang, Tangyu Xu, Linrui Zheng, Yiming Miranda, Brando Liu, Tongliang Koyejo, Sanmi Sugiyama, Masashi Han, Bo Artificial Intelligence Computation and Language Machine Learning We present AlphaApollo, an agentic reasoning system that targets two bottlenecks in foundation-model reasoning: (1) limited reasoning capacity for complex, long-horizon problem solving and (2) unreliable test-time evolution without trustworthy verification. AlphaApollo orchestrates models and tools via three components: (i) multi-turn agentic reasoning, which formalizes model-environment interaction with structured tool calls and responses; (ii) multi-turn agentic learning, which applies turn-level reinforcement learning to optimize tool-use reasoning while decoupling actions from tool responses for stable training; and (iii) multi-round agentic evolution, which refines solutions through a propose-judge-update loop with tool-assisted verifications and long-horizon memory. Across seven math reasoning benchmarks and multiple model scales, AlphaApollo improves performance through reliable tool use (> 85% tool-call success), substantial gains from multi-turn RL (Avg@32: Qwen2.5-1.5B-Instruct 1.07% -> 9.64%, Qwen2.5-7B-Instruct 8.77% -> 20.35%), and improvements from evolution (e.g., Qwen2.5-3B-Instruct 5.27% -> 7.70%, Qwen2.5-14B-Instruct 16.53% -> 21.08%). This project is still ongoing. We welcome feedback from the community and will frequently update the source code and technical report. |
| title | AlphaApollo: A System for Deep Agentic Reasoning |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2510.06261 |