Self-Improving Language Models with Bidirectional Evolutionary Search
Search has been proposed as an effective method for self-improving language models and agentic systems, both for post-training sample generation and for inference. However, widely used methods such as best-of-N sampling and tree search face two fundamental limitations: they are guided by sparse verification signals, and they construct candidates primarily through autoregressive expansion, restricting exploration to regions with substantial model probability mass. To address these, we propose Bidirectional Evolutionary Search (BES), a search framework that couples forward candidate evolution with backward goal decomposition. In the forward search, BES augments standard expansion with evolu...
| Authors | Guowei Xu, Zhenting Qi, Huangyuan Su et al. |
|---|---|
| Primary category | cs.CL |
| Published | 27 May 2026 |
| Last updated at source | 13 October 2026 |
Connected in the knowledge graph
- Xkev/gemma-3-1b-it-kkModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.