Skip to content
← Daily Digest

Tool Use

function calling、API 呼叫最佳化、工具選擇、工具組合

Paper Timeline (5)

2026-06-06
Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline Must Read

8 種主流 agent 記憶系統放在 5 種不同場景跑,發現大多數只在自己設計的場景表現好、換個場景就崩;讓 agent 自己透過 tool call 管自己的記憶(AutoMEM)反而是最泛化的方法。

arxiv: 2606.04315
2026-06-17
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents Must Read

小模型面對 250 個工具的 MCP 目錄幾乎癱瘓(執行成功率 3%),Evoflux 用推論時的演化搜尋反覆修復失敗的工具 graph,把成功率拉到 17–24%——不需要 fine-tuning。

arxiv: 2606.12674
2026-06-28
APPO: Agentic Procedural Policy Optimization Skim

訓練 Agent 的強化學習通常在「工具呼叫點」才分配功勞,APPO 把這精細到「每個 token 的真實影響力」,在 13 個 benchmark 上比強基線提升近 4 分,且不增加工具呼叫次數。

arxiv: 2606.12384
2026-07-18
AgentCheck: A Reproduce–Intervene–Mitigate Workbench for LLM Agents over MCP Must Read

一個開源工作台:讓你把 MCP 工具的故障重現在可控環境,測你的修復是否真的有用,再確認沒有其他東西壞掉。

arxiv: 2607.11098
2026-08-01
ORCA-bench: How Ready Are Language Model Agents for Oncall? Must Read

用真實 SRE on-call 場景測試 LLM Agent 的故障根因分析(RCA)能力:1,079 個任務、真實 telemetry 介面、SRE 人工審核答案——最強模型答對率僅 40%,拿掉源碼存取後每個指標都掉。

arxiv: 2607.28545

Related Digests (6)

AI Agent GitHub Digest — 2026-08-21

Cursor open-sources its official plugin marketplace cursor/plugins, standardizing the ecosystem with plugin.json + skills + MCP definitions (+470 stars in one day); apache/maka enters the Apache incubator with an append-only event log recording every tool call and permission decision for auditable local-first agent workbenches; magnitudedev/magnitude auto-detects hardware, downloads, and runs models locally out of the box for offline agents; vercel/eve puts agent capabilities into convention directories like tools/, skills/, and schedules/ — the filesystem is the interface. On the framework side, pydantic-ai ships a v2.32.1 patch.

AI Agent Arxiv Digest — 2026-08-07

ToolLIFT lifts tool trajectories to function-level workflow graphs and consistently beats SOTA on three OOD benchmarks; SkillTV-Bench uses 681 cases to show skill-aware judge skills boost agent evaluation accuracy by 14.8pp; TRIO-20's prespecified equivalence study finds zero unauthorized calls from GPT-5.6 across 840 trajectories, but higher reasoning effort increases rule-probing rate by 14.3pp

AI Agent Arxiv Digest — 2026-07-31

Three papers today converge on one core question: **are AI Agents production-ready?** The answer is unanimously — far from it. HANDBOOK.md reveals that even the strongest frontier models achieve only **36.2%** SOP compliance when dropped into a simulated enterprise; a LangGraph paper delivers three actionable stateful workflow recipes plus a decision guide on when *not* to use LangGraph; and MM-ToolSandBox is the first benchmark to quantify how hard visually-grounded tool calling really is — the best of 12 models still falls below 50% success. Three dimensions — compliance evaluation, framework design, visual tool use — together map out exactly how far Agents are from real-world deployment.

AI Agent Arxiv Digest — 2026-07-23

Today's common theme: **the way we evaluate agents is itself broken**. The first paper audits major tool-calling benchmarks and finds nearly 20% of scores are wrong; the second uses replay analysis to show which benchmarks can be stopped early for reliable conclusions (SWE-bench is the exception); the third introduces the first multimodal web agent benchmark that jointly evaluates task completion and guide generation — screenshot input, dual-objective scoring, and even the strongest models complete less than 40%. Read all three for a complete picture of the crisis in agent evaluation and where to go from here.

AI Agent Arxiv Digest — 2026-07-18

Three papers tackle production-grade agent reliability from different angles: MemCon models memory operations as an RL problem so agents learn when to store, retrieve, and forget — up to +15.2 points on 6 benchmarks; AgentCheck turns MCP servers into a debugging surface for reproducing tool faults and verifying fixes, filling a long-standing gap in the MCP ecosystem; AgentAbstain uses 263 paired tasks to show that even the strongest frontier models score below 60% on 'should-not-act' scenarios, and abstention ability barely correlates with task-solving ability — swapping in a stronger model won't fix this.

AI Agent Arxiv Digest — 2026-06-10

Three papers today converge on one theme — moving agents from experiments to reliable production: a multi-agent troubleshooting architecture deployed at hyperscale cloud with 90%+ autonomous resolution; a memory mechanism that lets agents learn from past tool-call successes and failures without retraining; and the first systematic comparison of six AI-assisted development process frameworks across six dimensions.