BestHub
Sign in
SmartApe AI
Author

SmartApe AI

SmartApe's AI technology content account, focusing on cutting-edge AI developments and open-source frontlines.

70
Articles
1
Likes
97
Views
0
Comments
Recent Articles

Latest from SmartApe AI

70 recent articles
SmartApe AI
SmartApe AI
Oct 20, 2026 · Artificial Intelligence

NVIDIA's SoL-Pi Slashes Agent API Costs 33% with Recursive Self-Improvement

NVIDIA and Song Han's team open-source SoL-Pi, an automated research system that discovers four reusable harness optimizations—Action Fusion, Online Context Compact, ObservationPack, and Evidence-Preserving Reducer—cutting token usage by up to 49% and API costs by 33% while retaining over 93% task performance on EdgeBench and transferring gains to other benchmarks and multi-agent clusters.

API Cost ReductionEdgeBenchMulti-Agent Systems
0 likes · 17 min read
NVIDIA's SoL-Pi Slashes Agent API Costs 33% with Recursive Self-Improvement
SmartApe AI
SmartApe AI
Oct 20, 2026 · Artificial Intelligence

ZCode 3.16.1 Adds Generative UI & Plugin Marketplace, Rivaling DeepSeek Harness

ZCode 3.16.1 introduces Gen UI for dynamic interactive HTML/JS interfaces and UI Plugin for collaborative canvas editing via MCP Apps, plus an open plugin marketplace supporting custom sources, moving the AI coding agent toward visual, interactive workflows similar to DeepSeek Harness and Codex.

AI coding agentDeepSeek HarnessGen UI
0 likes · 6 min read
ZCode 3.16.1 Adds Generative UI & Plugin Marketplace, Rivaling DeepSeek Harness
SmartApe AI
SmartApe AI
Oct 19, 2026 · Artificial Intelligence

Visual Generation Knowledge Fails to Transfer to Text QA: New Research Bridges Gap

A new paper from Tsinghua and Zhipu AI introduces Knowledge Transfer Probing (KTP) to test if unified multimodal models can use knowledge learned from image generation for text QA, revealing a significant gap; interleaved image-text alignment training and visual chain-of-thought reasoning substantially improve text QA accuracy across BAGEL, SenseNova-U1, and GLM-Omni, though a gap persists.

GLM-OmniKTP protocolMultimodal Models
0 likes · 12 min read
Visual Generation Knowledge Fails to Transfer to Text QA: New Research Bridges Gap
SmartApe AI
SmartApe AI
Oct 19, 2026 · Industry Insights

DHS Bans DeepSeek from Federal Systems, Extends Purge to Third-Party Tools

The U.S. Department of Homeland Security ordered all federal civilian agencies to immediately halt procurement of DeepSeek products and remove them from IT systems, including third-party tools built on DeepSeek technology, citing risks of data transmission to China and potential malware vulnerabilities.

AI SecurityAI banDHS
0 likes · 6 min read
DHS Bans DeepSeek from Federal Systems, Extends Purge to Third-Party Tools
SmartApe AI
SmartApe AI
Oct 19, 2026 · Artificial Intelligence

Terminal-RSI: 27B Agent Rivals Frontier Models via Recursive Self-Improvement

Tencent's Terminal-RSI framework uses recursive self-rewrite and policy refinement phases to train a Qwen3.8-27B terminal agent that achieves 86.52% on Terminal-Bench 2.1, surpassing GPT-6 Sol and Kimi K3, while demonstrating improved long-horizon task completion through credit assignment and reward design innovations.

Credit AssignmentLong-Horizon TasksQwen
0 likes · 13 min read
Terminal-RSI: 27B Agent Rivals Frontier Models via Recursive Self-Improvement
SmartApe AI
SmartApe AI
Oct 19, 2026 · Artificial Intelligence

MIT-IBM & Amazon Launch OpenRSI-Index: Open Platform for AI-Driven Research

MIT-IBM and Amazon's A-EVO Lab have open-sourced OpenRSI-Index, a platform enabling AI agents to autonomously design, execute, and evaluate research experiments across domains like LLMs, vision, and robotics, with built-in safeguards against evaluation gaming.

AI AgentsAI Research AutomationAmazon A-EVO Lab
0 likes · 7 min read
MIT-IBM & Amazon Launch OpenRSI-Index: Open Platform for AI-Driven Research
SmartApe AI
SmartApe AI
Oct 18, 2026 · Artificial Intelligence

TerminalHorizon: 27 Behavioral Patterns Power 12-Hour Autonomous Agents

Researchers from USTC and Alibaba DreamX introduce TerminalHorizon, an automated data synthesis engine that generates 2,852 long-horizon training trajectories across 25 domains and 27 behavioral patterns, enabling Qwen3.5-27B to achieve 60.67% on Terminal-Bench 2.1 and sustain 12-hour autonomous research in RSI exams.

Qwen3.5-27BRSI examTerminal-Bench
0 likes · 17 min read
TerminalHorizon: 27 Behavioral Patterns Power 12-Hour Autonomous Agents
SmartApe AI
SmartApe AI
Oct 17, 2026 · Artificial Intelligence

Liu Yang Joins HKU: From Ambient Light Privacy Leaks to Physical AI Imaging

Caltech postdoctoral researcher Liu Yang has joined Hong Kong University as a tenure-track assistant professor, bringing a research portfolio that includes exposing privacy risks in ambient light sensors, encoding vaccine records in microneedle QR codes, and developing a plug-and-play computational imaging toolkit now powered by diffusion models.

Ambient Light SensorsComputational ImagingDiffusion Models
0 likes · 6 min read
Liu Yang Joins HKU: From Ambient Light Privacy Leaks to Physical AI Imaging
SmartApe AI
SmartApe AI
Oct 17, 2026 · Artificial Intelligence

HA-VLN 2.0: Benchmarking Socially-Aware Navigation in Dynamic Human Environments

Researchers from UW, CMU, NUS, and Microsoft Research introduce HA-VLN 2.0, a benchmark for vision-language navigation that incorporates dynamic human movements, multi-person interactions, and social constraints across discrete and continuous environments, featuring the HAPS 2.0 dataset with 172 activity types and HA-R2R with 16,844 enriched instructions, plus baselines and real-robot validation on a Unitree Go2.

BenchmarkDynamic EnvironmentsHA-R2R
0 likes · 9 min read
HA-VLN 2.0: Benchmarking Socially-Aware Navigation in Dynamic Human Environments