AGAR: a reinforcement learning substrate for LLM program evolution

Haoran Li et al.

#arXiv #cs.AI #cs.MA

CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use

Gennadiy Savrasov et al.

#arXiv #cs.AI #cs.LG

📌 GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks

Gabriel Diaz-Ireland et al.

#arXiv #cs.AI

RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents

Mayur Akewar, Ravi Ranjan

#arXiv #cs.AI

Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System

Panagiotis Kasnesis et al.

#arXiv #cs.AI

Sigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering

Kemal Davaslioglu, Sastry Kompella

#arXiv #cs.AI #cs.CR

AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails

Melissa Kazemi Rad et al.

#arXiv #cs.AI

How Could AI Eliminate Humanity? A Failure-Mode Analysis of Civilizational Risk

Miko{\l}aj Sienicki, Krzysztof Sienicki

#arXiv #cs.AI #cs.CY #cs.HC

gassy gassy
more demons think clean out.
#Cs

#Cs gassy

Even more geckos (sold)

#BRart #digitalart #art #furryart #furry #ibispaint #pearlygecko #cs #characterdesign

AI Safety Considerations for Agents With Limited Time to Act

Leo Zeitler, Jack Richings, Victoria Nockles

#arXiv #cs.AI #cs.LG

Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint Programming

\'Angel S\'anchez-Fern\'andez, Javier Pernas-\'Alvarez, Diego Crespo-Pereira

#arXiv #cs.AI #cs.SE

Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents

Obada Kraishan

#arXiv #cs.AI

Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents

Wenjie Liao, Liangjie Zhao, Zehong Cao

#arXiv #cs.AI

System Switch: When Should a Fast Decision Model Stop and Think?

Gian Luca Bailo

#arXiv #cs.AI

Cognitive Schemas, Laws and Tasks

Antal Jakov\'ac, Andr\'as Telcs

#arXiv #cs.AI

Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA

Yufeng Li et al.

#arXiv #cs.AI

The AI Evaluation Ecosystem

Yash Dave et al.

#arXiv #cs.AI #cs.CY

Bookkeeping, Composition, or Unreachable Gold? Reading MemoryAgentBench's Conflict-Resolution Scores Against a Frozen Last-Write Resolver

Egor Pakhomov, Erik Nijkamp

#arXiv #cs.AI #cs.CL