arXiv AI September 24, 2026 By Wesley Shu

Reachable Global Optimization in AI Systems: How Global Is Global?

The paper "Reachable Global Optimization in AI Systems: How Global Is Global?" argues that claims of AI systems optimizing various components (prompts, policies, architectures, etc.) are underspecified unless they define the region actually reachable by the system. It introduces Reachability-Induced Optimization (RIO), a framework where a generator, verifier, controller, memory, tools, and budget determine a reachable candidate region, and proves several theoretical results about reachable-optimality and related concepts. Extensive benchmarks (66,150 trials across 270 landscapes) demonstrate that control can alter reachability, and that optimization quality, reachability quality, and control reliability must be reported separately.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language

Sep 1

AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds

arXiv:2608.29397v1 Announce Type: new Abstract: Tool-use benchmarks generally evaluate whether an agent completes a workflow using appropriate tools and valid arguments. However, feasibility alone is...

By Zixiang Xu, Jiaan Wang, Fandong Meng

llms agents benchmarks

arXiv AI

Aug 18

LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset

arXiv:2608. 15175v1 Announce Type: cross Abstract: Uncrewed aerial vehicles (UAVs) are increasingly deployed for autonomous navigation in complex outdoor environments, where dynamic conditions and mission requirements require intelligent adaptive decision-making.

By Yousef Emami, Mohammadhossein Homaei, Hao Zhou, Miguel Guti\'errez Gait\'an, Atefeh Hajijamali Arani, Rui Zhang

llms agents reinforcement-learning

arXiv AI

Jul 2

Solution space path planning for supporting en-route air traffic control

arXiv:2607. 00064v1 Announce Type: new Abstract: As technology advances, many path-planning algorithms have been proposed for Air Traffic Management, yet their operational adoption in tactical control remains limited, revealing a misalignment between algorithmic design priorities and air traffic controllers' needs.

By Yiyuan Zou, Wenying Lyu, Clark Borst

safety

arXiv AI

Jun 29

When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?

arXiv:2605. 30719v2 Announce Type: replace-cross Abstract: We study when large language models (LLMs) can serve as effective black-box policy optimizers for reinforcement learning (RL) tasks, i.

By Stephane Hatgis-Kessell, Emma Brunskill

llms reinforcement-learning robotics

arXiv AI

Aug 17

LLM-Advisor: An LLM Advisor for Cost-efficient Path Planning across Multiple Terrains

arXiv:2503. 01236v3 Announce Type: replace-cross Abstract: This paper addresses fixed-graph terrain-aware path refinement, in which a global planner is restricted to a predefined route space and may remain optimal within that space while missing lower-cost terrain corridors available in the native-resolution map.

By Ling Xiao, Toshihiko Yamasaki

llms multimodal benchmarks

arXiv Machine Learning

Aug 19

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

Agentic ESOpt proposes using evolution strategies (ES) instead of reinforcement learning to fine‑tune large language‑model agents for long‑horizon tasks. ES offers model scalability, flexibility, and better long‑horizon credit assignment, enabling full‑parameter optimization with minimal GPU memory. The framework samples parameter perturbations, evaluates agents with rewards, and updates online, achieving notable performance gains on WebArena‑Lite and in test‑time prompt‑parameter co‑evolution.

By Zhi Zheng, Rongsheng Chen, Yunpeng Ba, Zhenkun Wang, Yee Whye Teh, Wee Sun Lee

llms agents reinforcement-learning fine-tuning

One email a morning, machine-written

Related stories

AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds

LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset

Solution space path planning for supporting en-route air traffic control

When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?

LLM-Advisor: An LLM Advisor for Cost-efficient Path Planning across Multiple Terrains

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements