feat: publish long-horizon agent chapter

2026-07-29 06:54:31 +08:00
parent 6c8c0fb90f
commit 25982cbbb4
25 changed files with 5122 additions and 39 deletions
@@ -2144,6 +2144,278 @@ export const papers: Paper[] = [
    spotlight: "Kimi",
    verified: true,
  },
+  {
+    year: 2018,
+    title: "TextWorld: A Learning Environment for Text-based Games",
+    url: "https://arxiv.org/abs/1806.11532",
+    topics: ["Agent"],
+    contribution: "用可程序生成的文字世界、状态与动作接口，为语言 Agent 建立可控交互环境。",
+    verified: true,
+  },
+  {
+    year: 2019,
+    title: "Jericho: A Learning Environment for Interactive Fiction Games",
+    url: "https://arxiv.org/abs/1909.05398",
+    topics: ["Agent"],
+    contribution: "把真实交互式小说标准化为含世界状态与语言动作的强化学习环境。",
+    verified: true,
+  },
+  {
+    year: 2020,
+    title: "ALFWorld: Aligning Text and Embodied Environments for Interactive Learning",
+    url: "https://arxiv.org/abs/2010.03768",
+    topics: ["Agent"],
+    contribution: "对齐抽象文本环境与具身家务环境，让文字策略能迁移到更真实的交互世界。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "ScienceWorld: Is your Agent Smarter than a 5th Grader?",
+    url: "https://arxiv.org/abs/2203.07540",
+    topics: ["Agent", "评测"],
+    contribution: "用需要多步实验和科学知识的文本环境评估语言 Agent 的交互推理。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents",
+    url: "https://arxiv.org/abs/2207.01206",
+    topics: ["Agent", "评测"],
+    contribution: "以 1.18M 商品、12K 指令和可计算 reward 构造大规模网页购物环境。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "Do As I Can, Not As I Say: Grounding Language in Robotic Affordances",
+    url: "https://arxiv.org/abs/2204.01691",
+    topics: ["Agent"],
+    contribution: "SayCan 将 LLM 给出的任务相关性与技能 value/affordance 相乘，过滤语言合理但世界中不可行的动作。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning",
+    url: "https://arxiv.org/abs/2205.00445",
+    topics: ["Agent"],
+    contribution: "让 LLM 作为路由器组合计算器、知识库与离散推理模块，建立模块化工具系统主线。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "PAL: Program-aided Language Models",
+    url: "https://arxiv.org/abs/2211.10435",
+    topics: ["推理", "Agent"],
+    contribution: "让语言模型生成程序作为中间表示，再由解释器承担精确执行。",
+    verified: true,
+  },
+  {
+    year: 2022,
+    title: "Code as Policies: Language Model Programs for Embodied Control",
+    url: "https://arxiv.org/abs/2209.07753",
+    topics: ["Agent"],
+    contribution: "用可组合代码表达机器人策略，把自然语言任务映射到可执行控制程序。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Generative Agents: Interactive Simulacra of Human Behavior",
+    url: "https://arxiv.org/abs/2304.03442",
+    topics: ["Agent"],
+    contribution: "用记忆流、反思与计划驱动长期社会行为，建立 Agent 记忆系统的经典结构。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models",
+    url: "https://arxiv.org/abs/2305.18323",
+    topics: ["Agent", "推理"],
+    contribution: "先由 Planner 写含变量依赖的计划，再由 Worker 执行工具，减少重复 observation 与模型调用。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs",
+    url: "https://arxiv.org/abs/2307.16789",
+    topics: ["Agent", "数据"],
+    contribution: "从 16,464 个真实 REST APIs 合成指令与调用路径，并训练检索增强的 ToolLLaMA。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face",
+    url: "https://arxiv.org/abs/2303.17580",
+    topics: ["Agent", "多模态"],
+    contribution: "以语言模型为控制器，规划并调度模型工具库完成跨模态任务。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "CAMEL: Communicative Agents for Mind Exploration of Large Scale Language Model Society",
+    url: "https://arxiv.org/abs/2303.17760",
+    topics: ["Agent"],
+    contribution: "用 inception prompting 与角色扮演协议研究多 Agent 自主通信和任务协作。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework",
+    url: "https://arxiv.org/abs/2308.00352",
+    topics: ["Agent"],
+    contribution: "把软件工程 SOP、角色和中间文档写入多 Agent 协作流程。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation",
+    url: "https://arxiv.org/abs/2308.08155",
+    topics: ["Agent"],
+    contribution: "用可对话 Agent 抽象组合模型、工具、人类与多种交互拓扑。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models",
+    url: "https://arxiv.org/abs/2310.04406",
+    topics: ["Agent", "推理"],
+    contribution: "LATS 用树搜索、环境反馈和 value judgment 统一 reasoning、acting 与 planning。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "MemGPT: Towards LLMs as Operating Systems",
+    url: "https://arxiv.org/abs/2310.08560",
+    topics: ["Agent", "长上下文"],
+    contribution: "用 main、recall 与 archival memory 分层管理有效上下文，类比操作系统虚拟内存。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "Mind2Web: Towards a Generalist Agent for the Web",
+    url: "https://arxiv.org/abs/2306.06070",
+    topics: ["Agent", "评测"],
+    contribution: "以真实网站轨迹研究 element selection、action prediction 与跨任务/站点/领域泛化。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "WebArena: A Realistic Web Environment for Building Autonomous Agents",
+    url: "https://arxiv.org/abs/2307.13854",
+    topics: ["Agent", "评测"],
+    contribution: "提供可自托管、功能完整的多站点环境，并以数据库和页面状态检查任务结果。",
+    verified: true,
+  },
+  {
+    year: 2023,
+    title: "GAIA: A Benchmark for General AI Assistants",
+    url: "https://arxiv.org/abs/2311.12983",
+    topics: ["Agent", "评测"],
+    contribution: "用 466 个真实助手问题联合考察推理、检索、工具与多步执行。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "VisualWebArena: Evaluating Multimodal Agents on Realistic Visually Grounded Web Tasks",
+    url: "https://arxiv.org/abs/2401.13649",
+    topics: ["Agent", "多模态", "评测"],
+    contribution: "把视觉 grounding、图片与布局信息加入可执行的真实网页任务。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents",
+    url: "https://arxiv.org/abs/2406.13352",
+    topics: ["Agent", "评测"],
+    contribution: "以 97 个任务和 629 个安全测试，在动态工具环境中同时测 utility 与间接提示注入。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Agentless: Demystifying LLM-based Software Engineering Agents",
+    url: "https://arxiv.org/abs/2407.01489",
+    topics: ["Agent", "评测"],
+    contribution: "以定位、修复、验证三阶段简化流程，证明复杂自治 harness 并非默认更优。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities",
+    url: "https://arxiv.org/abs/2408.04682",
+    topics: ["Agent", "评测"],
+    contribution: "引入隐式状态依赖、on-policy 用户模拟、milestone、minefield 与动态轨迹评测。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Agent Security Bench: Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents",
+    url: "https://arxiv.org/abs/2410.02644",
+    topics: ["Agent", "评测"],
+    contribution: "跨 system/user prompt、工具与记忆形式化 Agent 攻击面，并联合评估效用与安全。",
+    verified: true,
+  },
+  {
+    year: 2024,
+    title: "Training Software Engineering Agents and Verifiers with SWE-Gym",
+    url: "https://arxiv.org/abs/2412.21139",
+    topics: ["Agent", "后训练", "评测"],
+    contribution: "构建 2,438 个可执行 Python 软件任务，用于训练软件 Agent 与 verifier。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "The Berkeley Function Calling Leaderboard: From Tool Use to Agentic Evaluation of Large Language Models",
+    url: "https://proceedings.mlr.press/v267/patil25a.html",
+    topics: ["Agent", "评测"],
+    contribution: "以 AST 与执行检查覆盖串行、并行、abstention 和多轮 function calling。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "τ²-bench: Evaluating Conversational Agents in a Dual-Control Environment",
+    url: "https://arxiv.org/abs/2506.07982",
+    topics: ["Agent", "评测"],
+    contribution: "用 Dec-POMDP 建模 Agent 与用户双方都能调用工具、共同改变环境的双控制任务。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning",
+    url: "https://arxiv.org/abs/2504.20073",
+    topics: ["Agent", "后训练", "推理"],
+    contribution: "提出 StarPO，并用 Echo Trap 揭示多轮 Agent RL 的 reward cliff、梯度 spike 与 collapse。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "Agent Lightning: Train ANY AI Agents with Reinforcement Learning",
+    url: "https://arxiv.org/abs/2508.03680",
+    topics: ["Agent", "后训练", "训练系统"],
+    contribution: "以统一 transition 接口、分层 credit assignment 和训练—Agent 解耦连接任意运行时与 RL。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning",
+    url: "https://arxiv.org/abs/2508.03501",
+    topics: ["Agent", "后训练", "长上下文", "训练系统"],
+    contribution: "在 131K context 的可执行 SWE 环境中研究终局测试奖励、长轨迹与多轮 RL。",
+    verified: true,
+  },
+  {
+    year: 2025,
+    title: "MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use",
+    url: "https://arxiv.org/abs/2509.24002",
+    topics: ["Agent", "评测"],
+    contribution: "在真实 MCP 工具协议与服务器生态中压力测试选择、组合和长程执行。",
+    verified: true,
+  },
+  {
+    year: 2026,
+    title: "AgentENV",
+    url: "https://github.com/kvcache-ai/AgentENV",
+    topics: ["Agent", "训练系统"],
+    contribution: "面向 Agentic AI 的 Firecracker microVM 环境，支持 pause、resume、fork、snapshot 与高密度运行。",
+    verified: true,
+  },
  {
    year: 2020,
    title: "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale",
@@ -2270,7 +2542,7 @@ export const papers: Paper[] = [
    year: 2026,
    title: "DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence",
    url: "https://arxiv.org/abs/2606.19348",
-    topics: ["基础", "长上下文", "MoE", "数据", "训练系统", "推理"],
+    topics: ["基础", "长上下文", "MoE", "数据", "训练系统", "推理", "Agent"],
    contribution: "32/33T 长文与 agentic 数据、CSA/HCA、mHC、Muon 和 1M 上下文双模型。",
    spotlight: "DeepSeek",
    verified: true,