Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914215075250176 |
|---|---|
| author | Zhang, Zhan |
| author_facet | Zhang, Zhan |
| contents | Finding rare but useful solutions in very large candidate spaces is a recurring practical challenge across language generation, planning, and reinforcement learning. We present a practical framework, \emph{Inverted Causality Focusing Algorithm} (ICFA), that treats search as a target-conditioned reweighting process. ICFA reuses an available proposal sampler and a task-specific similarity function to form a focused sampling distribution, while adaptively controlling focusing strength to avoid degeneracy. We provide a clear recipe, a stability diagnostic based on effective sample size, a compact theoretical sketch explaining when ICFA can reduce sample needs, and two reproducible experiments: constrained language generation and sparse-reward navigation. We further show how structured prompts instantiate an approximate, language-level form of ICFA and describe a hybrid architecture combining prompted inference with algorithmic reweighting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_19717 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference Zhang, Zhan Machine Learning Artificial Intelligence Finding rare but useful solutions in very large candidate spaces is a recurring practical challenge across language generation, planning, and reinforcement learning. We present a practical framework, \emph{Inverted Causality Focusing Algorithm} (ICFA), that treats search as a target-conditioned reweighting process. ICFA reuses an available proposal sampler and a task-specific similarity function to form a focused sampling distribution, while adaptively controlling focusing strength to avoid degeneracy. We provide a clear recipe, a stability diagnostic based on effective sample size, a compact theoretical sketch explaining when ICFA can reduce sample needs, and two reproducible experiments: constrained language generation and sparse-reward navigation. We further show how structured prompts instantiate an approximate, language-level form of ICFA and describe a hybrid architecture combining prompted inference with algorithmic reweighting. |
| title | Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2512.19717 |