Blog
告别冗长 PDF，一文读懂最新顶会与核心期刊的创新价值。
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
Bundibugyo virus glycoprotein seroreactivity following recombinant vesicular stomatitis virus–Zaire Ebola virus glycoprotein vaccination in outbreak-affected populations of the Democratic Republic of the Congo: a longitudinal cohort study
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
World in World: Explore the World with World Models
Breaking the Token Ceiling: Distilling Smaller, Stronger Byte Models
An Enterprise Language Model for Agentic Tool Use
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up
Mo' Models, Mo' Problems: How to best select model pools when designing Multi-Agent Systems
Common method biases in behavioral research: A critical review of the literature and recommended remedies.
Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery Tencent Zhuque Lab
The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It
Self Improvement via Fast Tree-search
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI
Sparse Reward Subsystem in Large Language Models
Reinforcement Learning for Real-Time Vision-Language-Action Policies
FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA
KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU