ircot
Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23
- 285
- Jsonnet
- Apache-2.0
- 2 y ago
Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23
[ICCV 2025] A Benchmark for Multi-Step Reasoning in Long Narrative Videos
[ACL 2023] Learning Multi-step Reasoning by Solving Arithmetic Tasks. https://arxiv.org/abs/2306.01707
TreeThinkerAgent is a lightweight orchestration layer that turns any LLM into an autonomous multi-step reasoning agent. It supports multi-step planning, tool execution, and final synthesis while exposing the entire reasoning process as a tree you can explore.
The course teaches how to fine-tune LLMs using Group Relative Policy Optimization (GRPO)—a reinforcement learning method that improves model reasoning with minimal data. Learn RFT concepts, reward design, LLM-as-a-judge evaluation, and deploy jobs on the Predibase platform.