arXiv:2609.23293v1 Announce Type: new Abstract: In the A* search algorithm, the tie-breaking strategies for nodes with the same $f$-value determines which…
Tag: AI
Tutoring Large Language Models to be Domain-adaptive, Precise and Safe
arXiv:2609.23071v1 Announce Type: new Abstract: This thesis proposes a framework for “responsible intelligence” to address AI’s critical challenges in…
Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
arXiv:2609.23038v1 Announce Type: new Abstract: Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical…
FireWorldBench: Benchmarking Complex Physical World Intelligence through Coupled-Field Fire Dynamics
arXiv:2609.23064v1 Announce Type: new Abstract: Understanding the physical world requires more than object recognition, scene description, and short-term…
LazyAgent: Demand-Driven Materialization and Physical Optimization of Agentic Programs
arXiv:2609.23058v1 Announce Type: new Abstract: Current agent runtimes that plan before acting generally execute a step once it becomes ready. We present…
Nokia Open-Sources AnyJev: A Training-Free Layer That Turns Any Open LLM Into a Calibrated Decision Model
Nokia’s applied research team has open-sourced AnyJev, a Python library that turns an open LLM into a decision model. It needs no training. It targets a…
Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees
arXiv:2609.23043v1 Announce Type: new Abstract: Large Language Models (LLMs) enable open-ended dialogue in interactive games, but their non-deterministic…
A Compact Stance-Indexed Anterior-Posterior COP Representation for Parkinson’s Disease Classification from Plantar VGRF
arXiv:2609.22956v1 Announce Type: new Abstract: Parkinson’s disease alters gait and bilateral coordination, but machine-learning performance also depends…
AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows
arXiv:2609.22951v1 Announce Type: new Abstract: Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their…
PINNForge: Execution-Grounded Evolutionary Design of Physics-Informed Neural Networks for PDE Solving via Large Language Models
arXiv:2609.23023v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) require coordinated choices over network representation,…