Reachable Global Optimization in AI Systems: How Global Is Global?
On the map: LLM reasoning → Reasoning for agents, planning and code
Abstract (arXiv)
AI systems increasingly claim to optimize prompts, policies, architectures, plans, tool-use trajectories, reasoning traces, and test-time computation. This paper argues that such claims are underspecified unless they state the region actually reachable by the system that performed the optimization. We introduce Reachability-Induced Optimization (RIO), a model in which a generator, verifier, controller, memory, tools, and budget induce a reachable candidate region. The returned solution is therefore a best visited point, an approximate reachable optimum, or an exact global optimum only when additional certificates relate the reachable region to the full formal space. We prove reachable-optimality, false-globality, gap- decomposition, certificate, escape, pruning, and control-value results. The full benchmark record contains 66,150 executed trials over six known-optimum landscape families, seven control policies, 270 landscapes, and 35 runs per landscape-method. The online appendix includes raw trial records, aggregate tables, figures, benchmark code, validation scripts, and checksums. The results show that control can restrict, expand, or misdirect reachability, and that optimization quality, reachability quality, and control reliability must be reported separately.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 3 of its 25 references that are in the map. First posted on arXiv 20 Aug 2026.
Builds on
3 of 25 references.
References · 3
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2021Evaluating Large Language Models Trained on Codecited by 8,320
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Predictive but Not Plannable: RC-aux for Latent World Models
- 2026Analysis of Optimality of Large Language Models on Planning Problems
- 2026verdi: retrieval is not transfer for continual world model optimization
- 2026Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization
- 2024Query-Efficient Planning with Language Models
- 2024On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability
- 2026PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
- 2025Local-Global Learning of Interpretable Control Policies: The Interface between MPC and Reinforcement Learning