Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.21169 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911405597261824 |
|---|---|
| author | Materzok, Tobias |
| author_facet | Materzok, Tobias |
| contents | We introduce Output-Space Search (OS-Search), which turns LLM generation into endpoint search. An outer loop selects a target z* in a frozen encoder-defined 3D output space Z, and a retrieval-grounded policy trained with sequence-level RL generates outputs whose coordinates land near z* under standard autoregressive decoding. This enables parallel sweeps and black-box optimization in Z without path-dependent token/program search. On stories, sweeping Z (text) yields 3.1x higher LLM-scored diversity than prompt-chaining. On code, Bayesian optimization over Z (code) improves an objective withheld from the controller under matched inference budgets while preserving validity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21169 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space Materzok, Tobias Computation and Language Artificial Intelligence We introduce Output-Space Search (OS-Search), which turns LLM generation into endpoint search. An outer loop selects a target z* in a frozen encoder-defined 3D output space Z, and a retrieval-grounded policy trained with sequence-level RL generates outputs whose coordinates land near z* under standard autoregressive decoding. This enables parallel sweeps and black-box optimization in Z without path-dependent token/program search. On stories, sweeping Z (text) yields 3.1x higher LLM-scored diversity than prompt-chaining. On code, Bayesian optimization over Z (code) improves an objective withheld from the controller under matched inference budgets while preserving validity. |
| title | Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.21169 |