Zhongzhu (Charlie) Zhou
Home
Research
Publication
Experience
Recent News
Blog
CV
↗
Tag
#
LLM Agent
93 posts tagged with this label. Back to
all tags
or the
main feed
.
2026
11-15
EN
CAAS | Scheduling LLM agent batches across inference and tools
11-15
中
CAAS 阅读笔记|怎样让 LLM 智能体的一整批任务更早完成?
11-09
EN
Silent Instrument Errors | What an agent leaderboard actually measures
11-09
中
Silent Instrument Errors 阅读笔记|智能体榜单的测量误差
11-05
EN
Polar: Training Native Agent Harnesses Through the Model Boundary
11-05
中
Polar 阅读笔记:在原生 Agent Harness 中训练,先把轨迹说清楚
11-05
中
Mac mini + ChatGPT 可以冒名顶替我
11-03
EN
HarnessBandit: Which Agent Interface Should Receive the Next RL Update?
11-03
中
HarnessBandit:下一步强化学习,该让哪个智能体接口来训练?
11-02
EN
InfraDev: When Passing the Tests Does Not Complete the Task
11-02
中
InfraDev:测试通过了,任务真的完成了吗?
10-27
EN
Self-HPO: When the Harness and the Policy Learn Together
10-27
中
Self-HPO:让模型和运行框架一起进化,收益来自哪里?
10-26
EN
RRSI: When Should a Self-Evolving Agent Keep Its Changes?
10-26
中
RRSI:Agent 改进自己之后,哪些修改值得留下?
10-25
EN
VERSE: What Makes a Self-Evolving Harness Optimizer Worth Trusting?
10-25
中
VERSE:让优化器改进自己,怎样才不只是越改越自信?
10-24
EN
Harness²: Can an agent improve its workflow without a correctness oracle?
10-24
中
Harness²:没有标准答案,agent 怎样改进自己的工作方式?
10-18
EN
STOP: When the Code Improver Becomes Its Own Optimization Target
10-18
中
STOP:让代码改进器改写自己,怎样判断它真的变好了?
10-17
EN
ADAS: What Changes When Agents Design Other Agents?
10-17
中
ADAS:让智能体设计智能体,究竟改变了什么?
10-12
EN
AFlow: Searching for Better Agent Workflows, and Measuring What Improves
10-12
中
AFlow 阅读笔记:让模型搜索工作流,也把改进的代价算清楚
10-11
EN
AutoHarness: Learning the Rules Around an LLM Agent
10-11
中
AutoHarness:让智能体写出自己的规则护栏
10-08
EN
Pie: Who Should Control the LLM Generation Loop?
10-08
中
Pie 阅读笔记:谁来控制大模型的生成循环
10-05
EN
SICA: When a Coding Agent Becomes Its Own Next Engineer
10-05
中
SICA 阅读笔记:让代码 Agent 成为自己的下一位工程师
10-04
EN
Darwin Gödel Machine: How a Coding Agent Learns to Improve Its Own Harness
10-04
中
Darwin Gödel Machine 阅读笔记:让智能体改进自己的 Harness
10-01
EN
FlashInfer-Bench: Closing the Loop Between Kernel Generation and LLM Serving
10-01
中
FlashInfer-Bench 阅读笔记:从生成 GPU 算子到接入真实推理系统
09-28
EN
ACE: How Agents Accumulate Useful Context Without Rewriting It Away
09-28
中
ACE 阅读笔记:让智能体积累经验,也别把旧经验改没了
09-21
EN
GEPA: Learning Better Agent Instructions from Execution Feedback
09-21
中
GEPA 阅读笔记:把 Agent 的失败轨迹变成更好的提示词
09-03
EN
HIERA: Teaching LLM Agents Where to Optimize, Not Just How — Workload-Aware Planning Across GPU Implementation Spaces
09-03
中
HIERA 阅读笔记:让 LLM Agent 先学会「在哪一层优化」,再谈「怎么优化」——GPU 算子实现空间的分层规划
08-31
EN
ContextPilot: Teaching LLM Agents to Manage Their Own Context with Fine-Grained RL
08-31
中
ContextPilot 阅读笔记:让 Agent 用细粒度强化学习学会自己管理上下文
08-17
EN
AgentRewind: Giving Long-Horizon LLM Agents an Undo Button That Actually Undoes Things
08-17
中
AgentRewind 阅读笔记:给长程 LLM Agent 装一个真正能撤销的悔棋键
08-10
EN
GRAFT: Global Optimization and Inference-Time Region Grafting for Agentic Workflows
08-10
中
阅读笔记:GRAFT——给智能体工作流做「全局定骨架、局部动手术」的推理时嫁接
07-28
EN
Branching Policy Optimization: Turning Sandbox Snapshots Into a Variance-Reduction Primitive
07-28
中
Branching Policy Optimization:把沙盒快照变成一个方差削减原语
07-27
EN
The Regression Tax: Why Adding Skills to an LLM Agent Also Breaks Tasks It Used to Solve
07-27
中
Regression Tax(回归税):给 LLM Agent 加 Skill 为什么既能帮忙又能拆台
07-25
EN
When Does Adding More Agents Actually Help? An Information-Bottleneck Answer
07-25
中
多智能体到底什么时候才有用?一个信息瓶颈视角的答案
07-20
EN
SEED: When Hindsight Becomes a Training Signal, Not Just a Better Prompt
07-20
中
SEED 阅读笔记:当「事后诸葛亮」变成训练信号,而不只是更好的提示词
07-13
EN
Long-Horizon-Terminal-Bench: Dense Reward Grading Exposes Agent Long-Horizon Execution Limits
07-13
中
Long-Horizon-Terminal-Bench 阅读笔记:密集奖励评估揭露 Agent 长程执行瓶颈
07-07
EN
RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents
07-07
中
RSPO:多轮LLM智能体的奖励交换策略优化
06-22
EN
MRAgent: Why Memory Should Be Reconstructed, Not Retrieved
06-22
中
MRAgent:记忆应该被重建,而不是被检索
06-15
EN
Parallel-Synthesis: Direct KV-Cache Synthesis for Parallel Branches in LLM-Agent Workflows
06-15
中
Parallel-Synthesis:让 LLM 综合智能体直接消费并行分支的 KV 缓存
06-08
EN
ExpWeaver: How LLM Agents Learn from Past Experience in Latent Space
06-08
中
ExpWeaver:LLM 智能体如何在隐空间中从经验中学习
06-01
EN
AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle
06-01
中
AutoSci:以记忆为中心的全科研生命周期自主智能体系统
05-25
EN
CodeAct: Executable Code Actions Elicit Better LLM Agents
05-25
中
CodeAct:用可执行代码驱动更强的 LLM Agent
05-18
EN
Why Single-Agent LLMs Beat Multi-Agent Systems on Multi-Hop Reasoning — A Budget-Controlled Story
05-18
中
思考预算锁死之后,单 Agent 为什么打过多 Agent —— 阅读笔记
05-11
EN
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
05-11
中
MASPO:面向 LLM 多智能体系统的联合提示词优化
05-01
EN
Low-Rank Optimization Trajectories for LLM RLVR Acceleration: A Technical Review of NExt
04-27
EN
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond — Technical Review
04-22
EN
SAGE: Training-Free Semantic Evidence Composition for Edge-Cloud Inference Under Hard Uplink Budgets
04-13
EN
Toolformer: Language Models Can Teach Themselves to Use Tools — Deep Technical Review
04-13
中
Toolformer:让语言模型自己学会“什么时候调用工具”——深度阅读笔记
04-12
EN
Voyager: An Open-Ended Embodied Agent with Large Language Models — Deep Technical Review
04-12
中
Voyager:一个能在 Minecraft 中持续成长的 LLM 具身智能体 —— 深度阅读笔记
04-11
EN
Language Agent Tree Search (LATS): Unifying Reasoning, Acting, and Planning in Language Models — Deep Technical Review
04-11
中
LATS(Language Agent Tree Search):把推理、行动、规划统一到同一个语言模型代理框架里 — 深度阅读笔记
03-30
EN
Chain-of-Thought Prompting Elicits Reasoning in LLMs — In-Depth Technical Review
03-23
EN
MiRA: A Subgoal-driven Framework for Improving Long-Horizon LLM Agents — Technical Review
03-16
EN
MetaGPT: When LLM Agents Form a Software Company — Multi-Agent Collaboration Done Right
03-09
EN
AutoGen: Microsoft's Framework for Building Multi-Agent Conversations That Actually Work
03-09
EN
Generative Agents: 25 AI Characters Living in a Simulated Town — Believable Human Behavior from LLMs
03-06
EN
SWE-agent: Turning LLMs Into Autonomous Software Engineers That Fix Real GitHub Issues
02-23
EN
Self-Refine: Teaching LLMs to Critique and Improve Their Own Output — No Extra Training Needed
02-20
EN
Reflexion: LLM Agents That Learn from Failure Through Verbal Self-Reflection
02-18
EN
GLM-5 Technical Review: From Vibe Coding to Agentic Engineering
02-16
EN
Tree of Thoughts: Deliberate Problem Solving with Large Language Models — Technical Review
02-09
EN
ReAct Technical Review: From Reasoning Ability to Executable Reasoning