{"slug": "synthesizing-symbolic-models-of-human-and-machine-reasoning-at-scale", "title": "Synthesizing symbolic models of human and machine reasoning at scale", "summary": "A new arXiv paper (2611.07088v1) introduces Behavior-Conditioned Symbolic Synthesis (BCSS), an automated method for searching interpretable, deterministic symbolic programs that verifiably reproduce observed behavior, and applies it to model both human and machine reasoning across hundreds of challenging problems. Analyzing the synthesized programs, the authors report that people and machines both tend to oversimplify, adopt rules that only partially explain their observations, and misinfer dependencies between problem features, with available resources modulating these shared signatures and reasoning effort predicting how much machines simplify. The authors say the results point to mechanisms reminiscent of satisficing in both people and machines and position BCSS as a general approach for interpreting and comparing rule-based reasoning of humans and black-box AI systems.", "body_md": "arXiv:2611.07088v1 Announce Type: new \nAbstract: Symbolic models offer a powerful account of cognition, but their scope has historically been limited by the need for hand-engineering and computational tractability. We show how advances in artificial intelligence (AI) can scale symbolic modeling and help overcome these engineering limitations. We introduce Behavior-Conditioned Symbolic Synthesis (BCSS)---an approach for automated search of interpretable, deterministic symbolic programs that verifiably reproduce behavior---and apply it to model both human and machine behavior across hundreds of challenging reasoning problems. Analyzing these programs reveals that both people and machines tend to oversimplify, adopt rules that are partial explanations for their observations, and misinfer dependencies between problem features. These shared signatures are modulated by available resources, with reasoning effort predicting the extent to which machines simplify and explain their observations. Together, these results point to underlying mechanisms reminiscent of satisficing in both people and machines, and illustrate how BCSS offers a general approach for interpreting and comparing rule-based reasoning of humans and black-box AI systems.", "url": "https://wpnews.pro/news/synthesizing-symbolic-models-of-human-and-machine-reasoning-at-scale", "canonical_source": "https://arxiv.org/abs/2611.07088", "published_at": "2026-11-06 05:00:00+00:00", "updated_at": "2026-11-06 05:22:53.607927+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "machine-learning", "ai-safety"], "entities": ["Behavior-Conditioned Symbolic Synthesis", "BCSS", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/synthesizing-symbolic-models-of-human-and-machine-reasoning-at-scale", "markdown": "https://wpnews.pro/news/synthesizing-symbolic-models-of-human-and-machine-reasoning-at-scale.md", "text": "https://wpnews.pro/news/synthesizing-symbolic-models-of-human-and-machine-reasoning-at-scale.txt", "jsonld": "https://wpnews.pro/news/synthesizing-symbolic-models-of-human-and-machine-reasoning-at-scale.jsonld"}}