On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective

Computer Science > Artificial Intelligence [Submitted on 8 May 2026] On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective Yuhao Li, Shengchao Liu Debates about large language model post-training often treat supervised fine-tuning (SFT) as imitation and reinforcement learning (RL) as discovery. But this distinction is too coarse. What matters is whether a training procedure increases the probability of behaviors the pretrained model could already produce, or whether it changes what the model can practically reach. We argue that post-training research should distinguish between capability elicitation and capability creation. We make this distinction operational by introducing the notion of accessible support: the set of behaviors that a model can practically produce under finite budgets. Post-training that reweights behaviors within this support is capability elicitation; whereas changing the support itself corresponds to capability creation. We develop this argument through a free-energy view of post-training. SFT and RL can both be seen as reweighting a pretrained reference distribution, only with different external signals. Demonstration signals define low-energy behavior for SFT, and reward signals define low-energy behavior for RL. When the update remains close to the base model, the main effect is local reweighting, not capability creation. Within this framework, the central question is no longer whether post-training is framed as SFT or RL, but whether it reweights behaviors already within reach, or instead expands the model's reachable behavioral space through search, interaction, tool use, or the incorporation of new information. Subjects: Artificial Intelligence (cs.AI); Statistical Mechanics (cond-mat.stat-mech); Machine Learning (cs.LG) Cite as: arXiv:2605.08368 [cs.AI]   (or arXiv:2605.08368v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.08368 Focus to learn more Submission history From: Yuhao Li [view email] [v1] Fri, 8 May 2026 18:23:25 UTC (55 KB) Access Paper: view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cond-mat cond-mat.stat-mech cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)