Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Open-source Agentic models specialized on Long-horizon tasks.
agents-a1-team-shanghai-ai-lab
•
•
1 min read
From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator
Graph-search-based end-to-end MLE task solver.
xiaohua-wang
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
System review of reward hacking.
xiaohua-wang
Intern-S1-Pro: Scientific multimodal foundation model at trillion scale
Intern-S1-Pro: one-trillion-parameter scientific multimodal foundation model.
intern-s1-team-shanghai-ai-lab
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery.
internagent-team-shanghai-ai-lab
LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding
A Multi-Agent System emulates LSTM’s hierarchical information flow and gated memory mechanisms for long-context understanding.
yichen-jiang
FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow
A multi-agent system built upon the dynamic structured knowledge flow.
yusong-hu
Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction
A framework that allows users to dynamically regulate memory reliance.
muzhao-tian
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence
A unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities.
scievalkit-team-shanghai-ai-lab
AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
Graph-search-based end-to-end MLE task solver.
shangheng-du