Reading candidates 2026-06-24

[github-actions]

Reading candidates 2026-06-24

These links were collected automatically from curated RSS feeds.
Please review them before adding anything to reading/YYYY/MM.md.

• Window: last 7 days
• Max items: 24
• Max per source: 2

Candidates

1. SHERLOC: Structured Diagnostic Localization for Code Repair Agents

• Link: https://arxiv.org/abs/2606.24820v1
• Source: arXiv cs.CL
• Language: en
• Published: 2026-06-23
• Matched topics: llm, agent, coding-agent, rag, training
• Score: 10
• Draft summary: LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated localization frameworks have emerged, yet are still evaluated as file retrieval rather than actionable diagnosis, producing lo...

2. Are We Ready For An Agent-Native Memory System?

• Link: https://arxiv.org/abs/2606.24775v1
• Source: arXiv cs.CL
• Language: en
• Published: 2026-06-23
• Matched topics: llm, agent, rag, eval
• Score: 10
• Draft summary: Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information storage, retrieval, update, consolidation, and dynamic lifecycle governance throughout agent execution...

3. Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

• Link: https://arxiv.org/abs/2606.24623v1
• Source: arXiv cs.AI
• Language: en
• Published: 2026-06-23
• Matched topics: llm, agent, rag
• Score: 9
• Draft summary: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts. To address this, we propose a multi-agent framework that sanitizes retrieved content through...

4. Scaling Laws for Task-Specific LLM Distillation

• Link: https://arxiv.org/abs/2606.24747v1
• Source: arXiv cs.AI
• Language: en
• Published: 2026-06-23
• Matched topics: llm, infra, training
• Score: 8
• Draft summary: Large Language Models (LLMs) achieve strong performance across a growing range of domains, yet their scale poses deployment challenges in applications where latency and cost constraints are critical. This paper derives empirical scaling laws for domain-specific LLM compression...

5. Porting the Moebius 0.2B image inpainting model to run in the browser with Claude Code

• Link: https://simonwillison.net/2026/Jun/22/porting-moebius/#atom-everything
• Source: Simon Willison
• Language: en
• Published: 2026-06-22
• Matched topics: llm, agent, coding-agent, multimodal
• Score: 8
• Draft summary: This morning on Hacker News I saw Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance , describing a small but effective inpainting model - a model where you can mark regions of an image to remove and the model imagines what should fill the space. T...

6. 破局智能体 “进化难”：阿里云 AgentLoop 深度解析全栈观测与自动化评估体系

• Link: https://my.oschina.net/u/3874284/blog/19708491
• Source: OSChina AI
• Language: zh-CN
• Published: 2026-06-22
• Matched topics: agent, coding-agent, eval
• Score: 8
• Draft summary: 当我们谈 Agent 进化的时候，通常涵盖两类场景。一种是员工办公场景 ，通过 Coding Agent 或通用 Agent 的记忆、协作风格、用户画像等能力，让 Agent 越用越聪明、越用越懂用户。另一种是企业的业务场景 ，比如企业对外提供的客服 Agent，对内提供智能分析的 Data Agent。关于前者，Anthropic 发布的 Economic Index 给过...

7. 千问大模型正式发布Qwen-AgentWorld

• Link: https://36kr.com/newsflashes/3866712419193860?f=rss
• Source: 36Kr
• Language: zh-CN
• Published: 2026-06-24
• Matched topics: llm, agent, eval
• Score: 7
• Draft summary: 36氪获悉，千问大模型正式发布Qwen-AgentWorld，这是首个原生语言世界模型（Language World Model, LWM）。单一模型同时覆盖文本类环境（MCP、Search、Terminal、SWE）与GUI类环境（Web、OS、Android），实现跨领域知识迁移。同步发布的还有 AgentWorldBench，覆盖七大领域的语言世界模型评测基准，每条测试样本均配备真实环境执行所得的真实环境观测数据。

8. ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning

• Link: https://arxiv.org/abs/2606.24601v1
• Source: arXiv cs.LG
• Language: en
• Published: 2026-06-23
• Matched topics: agent, rag, safety, training
• Score: 7
• Draft summary: Multi-agent reinforcement learning (MARL) addresses the problem of training multiple agents that pursue collaborative, competitive, or mixed objectives. Prior work has investigated transfer learning between source and target domains in MARL; however, the majority of existing a...

9. AsyncOPD: How Stale Can On-Policy Distillation Be?

• Link: https://arxiv.org/abs/2606.24143v1
• Source: arXiv cs.LG
• Language: en
• Published: 2026-06-23
• Matched topics: llm, training
• Score: 7
• Draft summary: On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like reinforcement learning (RL), however, OPD faces an on-policy systems bottleneck, as rollouts c...

10. Litefuse 开源发布：一行命令部署 Agent 可观测与评估平台，单机版比 Langfuse 快 5.5 倍

• Link: https://my.oschina.net/selectdb/blog/19708736
• Source: OSChina AI
• Language: zh-CN
• Published: 2026-06-23
• Matched topics: agent, eval, infra
• Score: 7
• Draft summary: 今天，我们将 Litefuse 开源，并推出业界第一个极致轻量的单机单进程模式。如果你已经迫不及待想要尝试，运行下面一条命令，大约 25 秒就能完成 Litefuse 单机版下载、安装和部署。

11. Embed the world: Multimodal AI for searchable aerial imagery at scale

• Link: https://aws.amazon.com/blogs/machine-learning/embed-the-world-multimodal-ai-for-searchable-aerial-imagery-at-scale/
• Source: AWS Machine Learning Blog
• Language: en
• Published: 2026-06-22
• Matched topics: rag, eval, multimodal
• Score: 7
• Draft summary: In this post, we walk through the problem space, our architecture on Amazon Bedrock and Amazon OpenSearch Serverless, the evaluation methodology we built on OpenStreetMap ground truth, four experiments that compared embedding models, fusion strategies, captioning, and search m...

12. 刚刚，Claude Code大升级！卡帕西：LLM第三次变革

• Link: https://www.qbitai.com/2026/06/437734.html
• Source: 量子位
• Language: zh-CN
• Published: 2026-06-24
• Matched topics: llm, coding-agent
• Score: 6
• Draft summary: 目前A社约65%的产品代码已经由Claude Tag参与完成

13. Daybreak: Tools for securing every organization in the world

• Link: https://openai.com/index/daybreak-securing-the-world
• Source: OpenAI News
• Language: en
• Published: 2026-06-22
• Matched topics: llm, agent, coding-agent, safety
• Score: 6
• Draft summary: OpenAI introduces new Daybreak tools, including Codex Security and GPT-5.5-Cyber, to help organizations find, validate, and patch vulnerabilities at scale.

14. Temporary Cloudflare Accounts for AI agents

• Link: https://simonwillison.net/2026/Jun/21/temporary-cloudflare-accounts/#atom-everything
• Source: Simon Willison
• Language: en
• Published: 2026-06-21
• Matched topics: llm, agent, coding-agent, infra
• Score: 6
• Draft summary: Temporary Cloudflare Accounts for AI agents The announcement says this is "for AI agents" but (as is pretty common these days) the AI hook isn't really necessary, this is an interesting feature for everyone else as well. Short version: you can now create a Cloudflare Workers p...

15. Introducing LangSmith’s No Code Agent Builder

• Link: https://www.langchain.com/blog/langsmith-agent-builder
• Source: LangChain Blog
• Language: en
• Published: 2026-06-18
• Matched topics: agent, coding-agent
• Score: 6
• Draft summary: Build AI agents without code using LangSmith Agent Builder. Create agents with memory, guided prompts, and MCP tools—no technical expertise needed.

16. Amazon Bedrock AgentCore harness is now generally available: Go from idea to production-grade agent in minutes

• Link: https://aws.amazon.com/blogs/machine-learning/amazon-bedrock-agentcore-harness-is-now-generally-available-go-from-idea-to-production-grade-agent-in-minutes/
• Source: AWS Machine Learning Blog
• Language: en
• Published: 2026-06-18
• Matched topics: agent, coding-agent
• Score: 6
• Draft summary: Today, Amazon Bedrock AgentCore harness is generally available. Two API calls (CreateHarness to define an agent, and InvokeHarness to run it), and you have an agent running in seconds. The agent runs in its own isolated environment with a filesystem and shell, so it can read f...

17. Boost Inference Performance up to 15x on NVIDIA Blackwell Using DFlash Speculative Decoding

• Link: https://developer.nvidia.com/blog/boost-inference-performance-up-to-15x-on-nvidia-blackwell-using-dflash-speculative-decoding/
• Source: NVIDIA Generative AI Blog
• Language: en
• Published: 2026-06-23
• Matched topics: agent, infra
• Score: 5
• Draft summary: As AI systems move from single-turn interactions to coordinated multiagent workflows, low-latency inference becomes increasingly important. Autoregressive LLMs...

18. 腾讯云发布边缘 Web 与 AI Agent 托管平台 EdgeOne Makers：一键开发部署，分钟级全球上线

• Link: https://www.infoq.cn/article/5iz5ew8NpQXIvvpFphDk?utm_source=rss&utm_medium=article
• Source: InfoQ 中国
• Language: zh-CN
• Published: 2026-06-23
• Matched topics: agent, infra
• Score: 4
• Draft summary: 点击查看原文>

19. 使用Azure Container Apps Sandboxes安全运行不受信任的AI智能体代码

• Link: https://www.infoq.cn/article/2yiUMe6JxKGXK61luSIJ?utm_source=rss&utm_medium=article
• Source: InfoQ 中国
• Language: zh-CN
• Published: 2026-06-23
• Matched topics: agent, safety
• Score: 4
• Draft summary: 点击查看原文>

20. Helping build shared standards for advanced AI

• Link: https://openai.com/index/helping-build-shared-standards-for-advanced-ai
• Source: OpenAI News
• Language: en
• Published: 2026-06-23
• Matched topics: eval, safety
• Score: 4
• Draft summary: OpenAI helps build shared standards for advanced AI, supporting evaluation frameworks, safety practices, and global cooperation through the Appia Foundation.

21. How Telcos Build Autonomous Networks with Agentic AI

• Link: https://developer.nvidia.com/blog/how-telcos-build-autonomous-networks-with-agentic-ai/
• Source: NVIDIA Generative AI Blog
• Language: en
• Published: 2026-06-23
• Matched topics: agent
• Score: 4
• Draft summary: Telecom operators are adopting AI across network operations, customer care, and back-office workflows, but most are still early in the journey to autonomy. In...

22. Temporary Cloudflare Accounts for AI agents

• Link: https://blog.cloudflare.com/temporary-accounts/
• Source: Cloudflare AI Blog
• Language: en
• Published: 2026-06-19
• Matched topics: agent
• Score: 4
• Draft summary: The moment an agent needs to deploy something, it slams face-first into a wall built for humans. Today we're rolling out Temporary Accounts on Cloudflare Workers. Any agent can now run wrangler deploy — temporary and get a live Worker in seconds.

23. Bringing more agent harnesses and frameworks to Cloudflare, starting with Flue

• Link: https://blog.cloudflare.com/agents-platform-flue-sdk/
• Source: Cloudflare AI Blog
• Language: en
• Published: 2026-06-17
• Matched topics: agent
• Score: 4
• Draft summary: The Agents SDK is now a runtime any agent framework can build on. Today we're opening up the Agents SDK primitives, with Flue as a first framework targeting Agents SDK, and rolling out agents in the dashboard.