Xkev/Llama-3.1-8B-Instruct-multihop-BES

Llama-3.1-8B-Instruct — Multi-Hop BES

Paper Link: https://arxiv.org/abs/2605.28814

Multi-hop retrieval-augmented QA agent fine-tuned from `meta-llama/Llama-3.1-8B-Instruct` with Bidirectional Evolutionary Search (BES) on the 3–4-hop subset of MuSiQue.

For the 3B variant see `Xkev/Llama-3.2-3B-Instruct-multihop-BES`.

Training

• —Base model: meta-llama/Llama-3.1-8B-Instruct
• —Dataset: 3–4-hop subset of MuSiQue (~5.5k examples)
• —Retrieval: E5 + FAISS over wiki-18

Intended use

Research on multi-hop reasoning and post-training. Not intended for general dialog or production.

License

Llama 3.1 Community License for fine-tuning artifacts. Base model meta-llama/Llama-3.1-8B-Instruct is governed by Meta's Llama 3.1 License, which still applies to derived weights.