diff --git a/SESSION-HANDOFF.md b/SESSION-HANDOFF.md index adf5ce5ee..8637ab57a 100644 --- a/SESSION-HANDOFF.md +++ b/SESSION-HANDOFF.md @@ -2,10 +2,34 @@ > 状态:当前接班入口。旧的批量生产 session 快照已失效,不得用于恢复自动循环;持续运行使用只读 supervisor + 有界 writer epoch。 -## 2026-07-15 继续推进 4 篇 web / app / tool-use 环境论文 +## 2026-07-15 总结不足后推进 4 篇通用助手 / 浏览器 / 移动端论文 - status:`local-ready`(已完成本地内容、receipt、atlas 和核心审计;远端 PR / merge / Pages deploy 仍以实时外部状态为准)。 +- 起始 ref:`38a0f7a8f31acca8ad728189d4e8530a72cba60c`(PR #35 merge 后的 `origin/main`)。 +- 本轮不足总结:上一轮 web / app / tool-use 环境卡完成了环境层补齐,但仍偏单类环境组件;缺少通用助手综合任务、真实耗时 open-web 任务、统一浏览器评测生态、移动 GUI 动态环境四条主线;所有新卡仍是 `STATIC_ANALYSIS` / `UNVERIFIED`,没有真实 benchmark 运行证据。 +- objective:新增 4 篇 `study-v2` paper note,补强 general assistant / browser ecosystem / mobile GUI agent 评测:`GAIA`、`AssistantBench`、`BrowserGym`、`AndroidWorld`。 +- scope:允许新增 `src/content/docs/papers/*.md`、`data/review-receipts/papers/*.json`,刷新 `data/note-index.json`、papers atlas 派生页和公开计数文案;不修改候选队列、policy/threshold、既有论文正文语义。 +- activated_by:`explicit-user-request-2026-07-15-summarize-gaps-and-advance-one-more-round` +- review_after:`2026-07-15` +- acceptance_checks: + - `lr search arxiv` + arXiv API 元数据核验 4/4; + - `node scripts/quality-gate.mjs` 逐篇通过,行数分别为 136 / 136 / 143 / 140,无 advisory; + - `npm run audit:content-contract`:0 blocking,64 v2; + - `npm run atlas`:2036 notes,69 chunks; + - `npm run audit:counts`:projects=961、papers=1075、total=2036; + - `npm run audit:links` / `npm run audit:wikilinks`:无 blocking。 +- budget:1 个内容小批次、4 篇新增 paper、1 个可写切片、1 个本地 writer。 +- external_outcome:当前为本地 review-ready change set;PR、merge 和 Pages deploy 需要以单独外部动作完成并复核。 +- stop_conditions:规范工具链不可用;arXiv 来源不可核验;content contract / redline / strict build / verify:ci 失败且无法在 scope 内修复;需要改 policy/threshold、候选队列或敏感内容;用户停止。 +- superseded_by:`none` + +## 2026-07-15 继续推进 4 篇 web / app / tool-use 环境论文全流程完成记录 + +- status:`complete` - 起始 ref:`aac96ba8b574509edf089c20732a17b19e98b487`(PR #34 merge 后的 `origin/main`)。 +- 完成 ref:`38a0f7a8f31acca8ad728189d4e8530a72cba60c`(PR #35 merge commit)。 +- external delta:PR #35 `Add four web and tool-use agent papers` 已合并;GitHub Pages workflow `29382534990` 已成功完成,公开站点为 `https://estelledc.github.io/study/`。 +- 内容 delta:新增 4 篇 `study-v2` paper note(`webarena`、`mind2web`、`appworld`、`toolsandbox`)、4 份 `study-review-receipt-v1`,并刷新 atlas / note-index / 公开规模文案;当前公开计数为 projects=961、papers=1071、total=2032。 - objective:在用户明确要求“继续推进”下,新增 4 篇 `study-v2` paper note,补强 web / app / tool-use agent 环境评测主线:`WebArena`、`Mind2Web`、`AppWorld`、`ToolSandbox`。 - scope:允许新增 `src/content/docs/papers/*.md`、`data/review-receipts/papers/*.json`,刷新 `data/note-index.json`、papers atlas 派生页和公开计数文案;不修改候选队列、policy/threshold、既有论文正文语义。 - activated_by:`explicit-user-request-2026-07-15-continue-study-round` @@ -16,10 +40,15 @@ - `npm run audit:content-contract`:0 blocking,60 v2; - `npm run atlas`:2032 notes,69 chunks; - `npm run audit:counts`:projects=961、papers=1071、total=2032; - - `npm run audit:links` / `npm run audit:wikilinks`:无 blocking。 + - `npm run audit:links` / `npm run audit:wikilinks`:无 blocking; + - `git ls-files -co --exclude-standard -z | node scripts/audit-public-redlines.mjs --stdin0`:0 blocking; + - `npm run build:strict -- --log /tmp/study-20260715-web-tool-round-build-clean.log`:通过;首次失败由 stale `.astro` cache 触发 duplicate-id warning,删除 ignored cache 后恢复; + - `STUDY_CHANGED_FROM=origin/main npm run verify:ci`:本地通过;PR #35 远端 CI `29382391831` 通过; + - 线上冒烟:主页和 `webarena`、`mind2web`、`appworld`、`toolsandbox` 均返回 200。 - budget:1 个内容小批次、4 篇新增 paper、1 个可写切片、1 个本地 writer。 -- external_outcome:当前为本地 review-ready change set;PR、merge 和 Pages deploy 需要以单独外部动作完成并复核。 +- external_outcome:4 篇新增论文笔记进入公开 study 站点;验证状态保持 `UNVERIFIED`。 - stop_conditions:规范工具链不可用;arXiv 来源不可核验;content contract / redline / strict build / verify:ci 失败且无法在 scope 内修复;需要改 policy/threshold、候选队列或敏感内容;用户停止。 +- 最终状态:`main...origin/main` 对齐;下一次写入只能由新的显式 backlog、外部状态变化或用户重新授权触发。 - superseded_by:`none` ## 2026-07-14 总结不足后再推进 4 篇补强论文全流程完成记录 diff --git a/data/note-index.json b/data/note-index.json index cdb3e7694..0d7b022dc 100644 --- a/data/note-index.json +++ b/data/note-index.json @@ -3,16 +3,16 @@ "taxonomy_version": "taxonomy-v1", "stats": { "summary": { - "total": 2032, - "classified": 1985, + "total": 2036, + "classified": 1989, "unclassified": 47, "unknown_difficulty": 1975, "empty_description": 1970 }, "by_area": { "papers": { - "total": 1071, - "classified": 1052, + "total": 1075, + "classified": 1056, "unclassified": 19, "unknown_difficulty": 1014, "empty_description": 1013 @@ -1044,6 +1044,38 @@ "chunk_route": "/study/atlas/papers/topic-papers-compilers-and-programming-language-theory-01/" } }, + { + "id": "papers::androidworld", + "area": "papers", + "slug": "androidworld", + "title": "AndroidWorld — 动态 Android 环境里的移动端 agent 评测", + "description": "用 AndroidWorld 理解移动 GUI agent 为什么需要真实 App、动态任务、初始化和成功检查,而不只是截图问答。", + "difficulty": "intermediate", + "canonical_topics": [ + "papers-agents-and-llm-systems" + ], + "classification": { + "state": "classified", + "source": "frontmatter-category", + "topic_id": "papers-agents-and-llm-systems", + "matched_category": "agent", + "raw_category": "AI Agent / Mobile GUI Benchmark" + }, + "trust": { + "contract_state": "v2", + "verification_status": "UNVERIFIED" + }, + "freshness": { + "state": "NOT_EVALUATED", + "reviewed_at": "2026-07-15", + "review_after": null + }, + "route": "/study/papers/androidworld/", + "atlas": { + "chunk_id": "topic-papers-agents-and-llm-systems-01", + "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-01/" + } + }, { "id": "papers::andromeda-2018", "area": "papers", @@ -1427,6 +1459,38 @@ "chunk_route": "/study/atlas/papers/topic-papers-databases-01/" } }, + { + "id": "papers::assistantbench", + "area": "papers", + "slug": "assistantbench", + "title": "AssistantBench — 真实耗时 Web 任务里的助手评测", + "description": "用 AssistantBench 理解为什么 web agent 不能只测短路径点击,还要测耗时、开放、可自动验收的现实任务。", + "difficulty": "intermediate", + "canonical_topics": [ + "papers-agents-and-llm-systems" + ], + "classification": { + "state": "classified", + "source": "frontmatter-category", + "topic_id": "papers-agents-and-llm-systems", + "matched_category": "agent", + "raw_category": "AI Agent / Assistant Benchmark" + }, + "trust": { + "contract_state": "v2", + "verification_status": "UNVERIFIED" + }, + "freshness": { + "state": "NOT_EVALUATED", + "reviewed_at": "2026-07-15", + "review_after": null + }, + "route": "/study/papers/assistantbench/", + "atlas": { + "chunk_id": "topic-papers-agents-and-llm-systems-01", + "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-01/" + } + }, { "id": "papers::asterisk", "area": "papers", @@ -3712,6 +3776,38 @@ "chunk_route": "/study/atlas/papers/topic-papers-hci-and-software-engineering-research-01/" } }, + { + "id": "papers::browsergym", + "area": "papers", + "slug": "browsergym", + "title": "BrowserGym — Web Agent 研究的统一浏览器环境", + "description": "用 BrowserGym 理解为什么 web agent 需要统一 observation / action / evaluation 接口,而不是每个 benchmark 各跑一套。", + "difficulty": "intermediate", + "canonical_topics": [ + "papers-agents-and-llm-systems" + ], + "classification": { + "state": "classified", + "source": "frontmatter-category", + "topic_id": "papers-agents-and-llm-systems", + "matched_category": "agent", + "raw_category": "AI Agent / Browser Environment" + }, + "trust": { + "contract_state": "v2", + "verification_status": "UNVERIFIED" + }, + "freshness": { + "state": "NOT_EVALUATED", + "reviewed_at": "2026-07-15", + "review_after": null + }, + "route": "/study/papers/browsergym/", + "atlas": { + "chunk_id": "topic-papers-agents-and-llm-systems-01", + "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-01/" + } + }, { "id": "papers::btrfs-2013", "area": "papers", @@ -12119,6 +12215,38 @@ "chunk_route": "/study/atlas/papers/topic-papers-compilers-and-programming-language-theory-01/" } }, + { + "id": "papers::gaia", + "area": "papers", + "slug": "gaia", + "title": "GAIA — 通用 AI 助手的现实任务基准", + "description": "用 GAIA 理解为什么真正的助手能力不等于专业考试高分,而是能组合推理、多模态、浏览和工具。", + "difficulty": "intermediate", + "canonical_topics": [ + "papers-agents-and-llm-systems" + ], + "classification": { + "state": "classified", + "source": "frontmatter-category", + "topic_id": "papers-agents-and-llm-systems", + "matched_category": "agent", + "raw_category": "AI Agent / General Assistant Benchmark" + }, + "trust": { + "contract_state": "v2", + "verification_status": "UNVERIFIED" + }, + "freshness": { + "state": "NOT_EVALUATED", + "reviewed_at": "2026-07-15", + "review_after": null + }, + "route": "/study/papers/gaia/", + "atlas": { + "chunk_id": "topic-papers-agents-and-llm-systems-01", + "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-01/" + } + }, { "id": "papers::game-semantics-pcf", "area": "papers", @@ -31392,8 +31520,8 @@ }, "route": "/study/papers/toolsandbox/", "atlas": { - "chunk_id": "topic-papers-agents-and-llm-systems-01", - "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-01/" + "chunk_id": "topic-papers-agents-and-llm-systems-02", + "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-02/" } }, { @@ -31456,8 +31584,8 @@ }, "route": "/study/papers/toxigen-2022/", "atlas": { - "chunk_id": "topic-papers-agents-and-llm-systems-01", - "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-01/" + "chunk_id": "topic-papers-agents-and-llm-systems-02", + "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-02/" } }, { @@ -31711,8 +31839,8 @@ }, "route": "/study/papers/tree-of-thoughts-2023/", "atlas": { - "chunk_id": "topic-papers-agents-and-llm-systems-01", - "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-01/" + "chunk_id": "topic-papers-agents-and-llm-systems-02", + "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-02/" } }, { @@ -31902,8 +32030,8 @@ }, "route": "/study/papers/truthfulqa-2021/", "atlas": { - "chunk_id": "topic-papers-agents-and-llm-systems-01", - "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-01/" + "chunk_id": "topic-papers-agents-and-llm-systems-02", + "chunk_route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-02/" } }, { @@ -64587,7 +64715,7 @@ "page": 2, "pages": 2, "route": "/study/atlas/papers/topic-papers-agents-and-llm-systems-02/", - "entries": 9 + "entries": 13 }, { "id": "topic-papers-ai-safety-and-interpretability-01", diff --git a/data/review-receipts/papers/androidworld.json b/data/review-receipts/papers/androidworld.json new file mode 100644 index 000000000..b2b2784d5 --- /dev/null +++ b/data/review-receipts/papers/androidworld.json @@ -0,0 +1,55 @@ +{ + "schema_version": "study-review-receipt-v1", + "generation": 1, + "predecessor_digest_sha256": null, + "note": { + "area": "papers", + "slug": "androidworld", + "digest_sha256": "02841f4e4a5f95d6b4da863075f7f698c1a491a1e877bc3db871098b122f219e" + }, + "source_revision": "arXiv:2405.14573v5", + "research_input_sha256": "1e77cd892ba8898f8f2630c6cbc0e322318c18ab6007717e74609e9647b9ff73", + "reviewers": [ + { + "role": "ZERO_BASE", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 87, + "warnings": [ + "Explains AndroidWorld with a toy mobile GUI task; Android emulator and benchmark tasks were not executed." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "MANUAL_SIMULATION" + } + }, + { + "role": "ENGINEER", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 85, + "warnings": [ + "Engineering interpretation is static; no AndroidWorld task initialization, success check, or teardown was run." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "NOT_APPLICABLE" + } + }, + { + "role": "ACADEMIC", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 84, + "warnings": [ + "Citation identity was checked through arXiv metadata; reported benchmark results are not independently reproduced." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "NOT_APPLICABLE" + } + } + ], + "waivers": [], + "created_at": "2026-07-15T03:20:00.000Z" +} diff --git a/data/review-receipts/papers/assistantbench.json b/data/review-receipts/papers/assistantbench.json new file mode 100644 index 000000000..4d7d61bcf --- /dev/null +++ b/data/review-receipts/papers/assistantbench.json @@ -0,0 +1,55 @@ +{ + "schema_version": "study-review-receipt-v1", + "generation": 1, + "predecessor_digest_sha256": null, + "note": { + "area": "papers", + "slug": "assistantbench", + "digest_sha256": "a5fcd23b75333a50c26fb62c10c10b63ee23d2744af90f08a68c05c85df3d53c" + }, + "source_revision": "arXiv:2407.15711v2", + "research_input_sha256": "784f08016d90cb342475f9a7d95c16d430bf9318b45d2c18211bf7c177f64cd6", + "reviewers": [ + { + "role": "ZERO_BASE", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 86, + "warnings": [ + "Explains AssistantBench with a toy time-consuming web task; benchmark tasks were not executed." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "MANUAL_SIMULATION" + } + }, + { + "role": "ENGINEER", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 84, + "warnings": [ + "Engineering interpretation is static; SeePlanAct and web task execution were not run." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "NOT_APPLICABLE" + } + }, + { + "role": "ACADEMIC", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 84, + "warnings": [ + "Citation identity was checked through arXiv metadata; benchmark scores are not independently reproduced." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "NOT_APPLICABLE" + } + } + ], + "waivers": [], + "created_at": "2026-07-15T03:20:00.000Z" +} diff --git a/data/review-receipts/papers/browsergym.json b/data/review-receipts/papers/browsergym.json new file mode 100644 index 000000000..779362796 --- /dev/null +++ b/data/review-receipts/papers/browsergym.json @@ -0,0 +1,55 @@ +{ + "schema_version": "study-review-receipt-v1", + "generation": 1, + "predecessor_digest_sha256": null, + "note": { + "area": "papers", + "slug": "browsergym", + "digest_sha256": "4e7491fe5be6e76e75e13d902ddaeb81730325fea26150b8522ed74251d816a3" + }, + "source_revision": "arXiv:2412.05467v4", + "research_input_sha256": "b322ad18703ca31d2e47036365d016ec4f7369e8aee247c75fbc2136051a6578", + "reviewers": [ + { + "role": "ZERO_BASE", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 86, + "warnings": [ + "Explains BrowserGym through a toy gym-like browser interface; BrowserGym was not installed or run." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "MANUAL_SIMULATION" + } + }, + { + "role": "ENGINEER", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 85, + "warnings": [ + "Engineering claims are limited to static paper reading; no AgentLab or benchmark adapter was executed." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "NOT_APPLICABLE" + } + }, + { + "role": "ACADEMIC", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 84, + "warnings": [ + "Citation identity was checked through arXiv metadata; ecosystem claims are not independently reproduced." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "NOT_APPLICABLE" + } + } + ], + "waivers": [], + "created_at": "2026-07-15T03:20:00.000Z" +} diff --git a/data/review-receipts/papers/gaia.json b/data/review-receipts/papers/gaia.json new file mode 100644 index 000000000..c62758d5d --- /dev/null +++ b/data/review-receipts/papers/gaia.json @@ -0,0 +1,55 @@ +{ + "schema_version": "study-review-receipt-v1", + "generation": 1, + "predecessor_digest_sha256": null, + "note": { + "area": "papers", + "slug": "gaia", + "digest_sha256": "b5dbc82ffd40f3433719aea40be4f8c8441c2ee8ddbf2c312c04c62f9c0567e2" + }, + "source_revision": "arXiv:2311.12983v1", + "research_input_sha256": "34779f3f0b380c2fc850322226d20a6a33846f83200b18868b66ff6efde3e85f", + "reviewers": [ + { + "role": "ZERO_BASE", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 87, + "warnings": [ + "Explains GAIA through a toy multimodal browsing task; GAIA dataset was not executed." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "MANUAL_SIMULATION" + } + }, + { + "role": "ENGINEER", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 84, + "warnings": [ + "Engineering claims are limited to static paper reading; no assistant agent or plugin stack was run." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "NOT_APPLICABLE" + } + }, + { + "role": "ACADEMIC", + "reviewer_version": "study-static-review-20260715-general-assistant-round", + "decision": "PASS_WITH_NOTES", + "score": 84, + "warnings": [ + "Citation identity was checked through arXiv metadata; reported human/model scores are not independently reproduced." + ], + "execution": { + "review_mode": "STATIC_REVIEW", + "code_mode": "NOT_APPLICABLE" + } + } + ], + "waivers": [], + "created_at": "2026-07-15T03:20:00.000Z" +} diff --git a/src/content/docs/about.md b/src/content/docs/about.md index c66420e08..d0cad9989 100644 --- a/src/content/docs/about.md +++ b/src/content/docs/about.md @@ -14,7 +14,7 @@ sidebar: 写到今天的硬数字: -- **1071 篇论文笔记** + **961 篇项目笔记**,合计 **2000+ 篇** +- **1075 篇论文笔记** + **961 篇项目笔记**,合计 **2000+ 篇** - 横跨 19 个主题:分布式系统 76 / 编程语言 76 / 数据库 47 / 操作系统 46 / 机器学习 44 / 区块链 44 / 后端 API 40 / 基础设施 38 / 网络协议 37 / 图形学 36 / 形式化方法 27 / 通信 27 / 信息检索 25 / Agent 24 / CLI 23 / NLP 11 / 编译器 11 / 等 - 近 30 天集中产出:基础设施(444 commits)、编译器与 PL(72)、自演化 Agent(10+ 新建)、分布式(47)、区块链(44) diff --git a/src/content/docs/atlas/papers/topic-papers-agents-and-llm-systems-01.md b/src/content/docs/atlas/papers/topic-papers-agents-and-llm-systems-01.md index 960b3b0f1..6110d074b 100644 --- a/src/content/docs/atlas/papers/topic-papers-agents-and-llm-systems-01.md +++ b/src/content/docs/atlas/papers/topic-papers-agents-and-llm-systems-01.md @@ -17,14 +17,17 @@ sidebar: | [Agent-R1 — 把 LLM agent 当 RL 环境训练的模块化框架](/study/papers/agent-r1-2511/) | `agent-r1-2511` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [Agentic Context Engineering — 把上下文当成会进化的 playbook](/study/papers/agentic-context-engineering-2025/) | `agentic-context-engineering-2025` | intermediate | UNVERIFIED | ACE 将上下文视为可演化 playbook,用生成、反思和整理缓解 context collapse | | [Agentless — 反 Agent 派的 SWE-bench 解法](/study/papers/agentless/) | `agentless` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | +| [AndroidWorld — 动态 Android 环境里的移动端 agent 评测](/study/papers/androidworld/) | `androidworld` | intermediate | UNVERIFIED | 用 AndroidWorld 理解移动 GUI agent 为什么需要真实 App、动态任务、初始化和成功检查,而不只是截图问答 | | [Anthropic Prompt Caching — 让长 prompt 只算一次,后续只付 10%](/study/papers/anthropic-prompt-caching/) | `anthropic-prompt-caching` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [APEX — 给自进化 agent 配一张"策略图"防止它走老路](/study/papers/apex-policy-exploration/) | `apex-policy-exploration` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [AppWorld — 多 App 世界里的交互式代码 agent](/study/papers/appworld/) | `appworld` | intermediate | UNVERIFIED | 用 AppWorld 理解为什么工具调用 benchmark 需要状态、用户、多个 App 和可执行代码,而不是单轮 API 序列 | +| [AssistantBench — 真实耗时 Web 任务里的助手评测](/study/papers/assistantbench/) | `assistantbench` | intermediate | UNVERIFIED | 用 AssistantBench 理解为什么 web agent 不能只测短路径点击,还要测耗时、开放、可自动验收的现实任务 | | [AutoGen — 多智能体对话框架](/study/papers/autogen/) | `autogen` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [AWQ — 看激活脸色给权重打折](/study/papers/awq/) | `awq` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [AWQ 2023 — 把 70B 大模型权重压到 35GB](/study/papers/awq-2023/) | `awq-2023` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [BIG-Bench Hard — 从大题库里挑出模型最头疼的 23 类题](/study/papers/big-bench-hard-2022/) | `big-bench-hard-2022` | intermediate | UNVERIFIED | 用 BBH 理解为什么 benchmark 需要难题子集和 CoT 对照 | | [BLOOM — 把 176B 多语种模型做成开放科学工程](/study/papers/bloom-2022/) | `bloom-2022` | intermediate | UNVERIFIED | 用 BLOOM 理解大模型也可以用社区协作、数据治理和开放发布来推进 | +| [BrowserGym — Web Agent 研究的统一浏览器环境](/study/papers/browsergym/) | `browsergym` | intermediate | UNVERIFIED | 用 BrowserGym 理解为什么 web agent 需要统一 observation / action / evaluation 接口,而不是每个 benchmark 各跑一套 | | [Chain-of-Thought — 让大模型先写步骤再回答](/study/papers/chain-of-thought/) | `chain-of-thought` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [ClawTrace — 把 agent 每步操作的"成本账"先算清再蒸馏](/study/papers/clawtrace-cost-aware/) | `clawtrace-cost-aware` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [Code as Agent Harness — 把代码当 agent 的"骨架"来重新看 agentic AI](/study/papers/code-as-agent-harness/) | `code-as-agent-harness` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | @@ -34,6 +37,7 @@ sidebar: | [EVE-Agent — 自我训练前先把证据钉在桌上](/study/papers/eve-agent-evidence/) | `eve-agent-evidence` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [Evo-Memory — 给"会自己长记性"的 agent 出一份统一考卷](/study/papers/evo-memory-2511/) | `evo-memory-2511` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [EXG 经验图 — 把 agent 的成败拼成一张可复用的关系图](/study/papers/exg-experience-graphs/) | `exg-experience-graphs` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | +| [GAIA — 通用 AI 助手的现实任务基准](/study/papers/gaia/) | `gaia` | intermediate | UNVERIFIED | 用 GAIA 理解为什么真正的助手能力不等于专业考试高分,而是能组合推理、多模态、浏览和工具 | | [Gorilla — 让 LLM 学会查 API 文档再调用](/study/papers/gorilla-2023/) | `gorilla-2023` | intermediate | UNVERIFIED | 用 Gorilla 理解 API grounding 如何降低工具调用幻觉 | | [GPTQ — 把 175B 大模型压成 4-bit 还几乎不掉点](/study/papers/gptq-2023/) | `gptq-2023` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [GraphRAG — 微软的知识图谱 + RAG](/study/papers/graphrag/) | `graphrag` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | @@ -109,9 +113,5 @@ sidebar: | [ToolBench-X — 工具会坏时,agent 还能不能把事做完](/study/papers/toolbench-x/) | `toolbench-x` | intermediate | UNVERIFIED | 用 ToolBench-X 理解 tool-use benchmark 为什么要模拟规格漂移、调用错误、执行失败和结果冲突 | | [Toolformer — 教 LLM 自主调用 API](/study/papers/toolformer/) | `toolformer` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [ToolLLM — 用 16000+ API 训练模型进入真实工具世界](/study/papers/toolllm-2023/) | `toolllm-2023` | intermediate | UNVERIFIED | 用 ToolLLM 理解大规模 API 数据集、工具检索和工具评测如何支撑 agent | -| [ToolSandbox — 状态化对话工具调用评测](/study/papers/toolsandbox/) | `toolsandbox` | intermediate | UNVERIFIED | 用 ToolSandbox 理解为什么工具调用 agent 需要测状态依赖、信息不足和多轮用户反馈,而不是只测单轮函数参数 | -| [ToxiGen — 用生成模型造隐性仇恨测试集](/study/papers/toxigen-2022/) | `toxigen-2022` | intermediate | UNVERIFIED | 用 ToxiGen 理解安全评测为什么要覆盖隐性、对抗性和群体相关文本 | -| [Tree of Thoughts — 让 LLM 像下棋一样多想几步再答](/study/papers/tree-of-thoughts-2023/) | `tree-of-thoughts-2023` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | -| [TruthfulQA — 专门问模型容易学人类谬误的问题](/study/papers/truthfulqa-2021/) | `truthfulqa-2021` | intermediate | UNVERIFIED | 用 TruthfulQA 理解语言模型为什么会模仿常见假话而不是坚持事实 | [下一组](/study/atlas/papers/topic-papers-agents-and-llm-systems-02/) diff --git a/src/content/docs/atlas/papers/topic-papers-agents-and-llm-systems-02.md b/src/content/docs/atlas/papers/topic-papers-agents-and-llm-systems-02.md index c74b4afcd..d1e92c78a 100644 --- a/src/content/docs/atlas/papers/topic-papers-agents-and-llm-systems-02.md +++ b/src/content/docs/atlas/papers/topic-papers-agents-and-llm-systems-02.md @@ -1,6 +1,6 @@ --- title: "智能体与 LLM 系统 · 论文 · 第 2 组" -description: "9 条 智能体与 LLM 系统 Atlas 分块" +description: "13 条 智能体与 LLM 系统 Atlas 分块" sidebar: hidden: true --- @@ -9,10 +9,14 @@ sidebar: [返回论文全景索引](/study/papers-atlas/) -本分块共 9 条,稳定上限为 100 条。 +本分块共 13 条,稳定上限为 100 条。 | 论文 | Slug | 难度 | 可信状态 | 简介 | |---|---|---|---|---| +| [ToolSandbox — 状态化对话工具调用评测](/study/papers/toolsandbox/) | `toolsandbox` | intermediate | UNVERIFIED | 用 ToolSandbox 理解为什么工具调用 agent 需要测状态依赖、信息不足和多轮用户反馈,而不是只测单轮函数参数 | +| [ToxiGen — 用生成模型造隐性仇恨测试集](/study/papers/toxigen-2022/) | `toxigen-2022` | intermediate | UNVERIFIED | 用 ToxiGen 理解安全评测为什么要覆盖隐性、对抗性和群体相关文本 | +| [Tree of Thoughts — 让 LLM 像下棋一样多想几步再答](/study/papers/tree-of-thoughts-2023/) | `tree-of-thoughts-2023` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | +| [TruthfulQA — 专门问模型容易学人类谬误的问题](/study/papers/truthfulqa-2021/) | `truthfulqa-2021` | intermediate | UNVERIFIED | 用 TruthfulQA 理解语言模型为什么会模仿常见假话而不是坚持事实 | | [UL2 — 一个模型同时练完补空、续写和长文本](/study/papers/ul2-2022/) | `ul2-2022` | advanced | UNVERIFIED | 用 UL2 理解 mixture-of-denoisers 如何统一不同语言模型训练范式 | | [VeriCache: Turning Lossy KV Cache into Lossless LLM Inference — 有损压缩草稿,无损输出验收](/study/papers/vericache/) | `vericache` | unknown | UNVERIFIED | 暂无独立描述;可先从标题与正文定位开始。 | | [VisualWebArena — 让网页 agent 真正看见界面](/study/papers/visualwebarena/) | `visualwebarena` | intermediate | UNVERIFIED | 用 VisualWebArena 理解多模态 web agent 为什么不能只读 DOM 文本,还要处理视觉线索 | diff --git a/src/content/docs/career-plan.md b/src/content/docs/career-plan.md index 9588b08c8..8fd2709fa 100644 --- a/src/content/docs/career-plan.md +++ b/src/content/docs/career-plan.md @@ -5,7 +5,7 @@ sidebar: order: 1 --- -> 本页是路径说明。具体笔记见左侧分组;当前规模 2000+ 篇(论文 1071 + 项目 961)。 +> 本页是路径说明。具体笔记见左侧分组;当前规模 2000+ 篇(论文 1075 + 项目 961)。 ## 1. 路径模型的演化 diff --git a/src/content/docs/index.md b/src/content/docs/index.md index 17607ae18..9afb62e80 100644 --- a/src/content/docs/index.md +++ b/src/content/docs/index.md @@ -144,7 +144,7 @@ head: -
当前规模:1071 篇论文 + 961 个项目 = 2032 篇笔记,按 19 个主题组织。数量已移出首屏,只作为覆盖面证据。
+当前规模:1075 篇论文 + 961 个项目 = 2036 篇笔记,按 19 个主题组织。数量已移出首屏,只作为覆盖面证据。