EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning Paper • 2609.35290 • Published 22 days ago
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers Paper • 2609.01343 • Published Sep 1 • 92
Agents in the Large: Perception-Centered Architecture for Persistent Agents Paper • 2608.30478 • Published Aug 31 • 13
SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information Paper • 2608.10692 • Published Aug 11 • 14
Harness^2: Recursive Agent Harnessing for an Open World Paper • 2610.14224 • Published 11 days ago • 111
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds Paper • 2609.30199 • Published 26 days ago • 31
PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models Paper • 2605.20873 • Published May 20 • 43
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published May 28 • 145
LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening Paper • 2605.19597 • Published May 19 • 20