Skip to main content
Bloss0m
⌕
EN 繁中
  • Projects
  • Blog
  • Paper Reading
  • Now
  • About & Contact
  • Search

Search

Find blog posts, paper notes, and projects

129 result(s), showing 12

  • SWE-Bench ProMax: Can Large-Scale Multilingual Refactoring Measure Long-Horizon Coding Agents?
    Paper Reading · AI Engineering · Aug 13, 2026

    A deep reading of SWE-Bench ProMax, which uses 170 cross-file, multilingual, behavior-preserving refactoring tasks to test whether coding agents can complete large changes rather than merely fix a nearby test.

    • Paper Reading
    • Agent Systems
    • Evaluation
    • Software Engineering
  • AI Software Development Environments: Choosing Between Vibe Coding and Verified Agent Workflows
    Blog · AI Engineering · Aug 12, 2026

    InfoWorld surveys GitHub Copilot, Google Antigravity, JetBrains Air, Kiro, Zed, and Zenflow; this article turns that tour into a selection framework based on autonomy, context, isolation, and verification.

    • AI Agent
    • Software Engineering
    • Vibe Coding
    • Developer Tools
  • Agentic Configuration Management: Treating Agent Systems as Governed Configuration, Not Just One Execution
    Paper Reading · AI Agent · Aug 12, 2026

    A deep reading of how ACM uses a framework-independent Configuration Graph, immutable revisions, dependency-aware impact propagation, and runtime provenance to govern heterogeneous agent configurations across LangGraph, CrewAI, and the OpenAI Agents SDK.

    • Paper Reading
    • AI Agent
    • Agent Security
    • Governance
  • ADIAS: Turning Agent Self-Improvement into Traceable Issue Repair
    Paper Reading · AI Engineering · Aug 12, 2026

    A deep reading of ADIAS: persistent issue state organizes failure evidence across optimization rounds so a full-code agent designer can remember what was tried, what regressed, and when a repair is actually confirmed.

    • Paper Reading
    • Agent Systems
    • Evaluation
    • AI Engineering
  • DocMemo: Letting Long-Document RAG Recover from a Bad First Retrieval
    Paper Reading · AI Engineering · Aug 12, 2026

    A deep reading of DocMemo: document schema, page belief, and question episodic memory preserve retrieval state across rounds, while Bayesian updates, Thompson sampling, and adaptive granularity recover missed evidence.

    • Paper Reading
    • RAG
    • Retrieval
    • Multimodal
  • GitHub Copilot MCP Governance: From Allowlist Semantics to Agent Adoption Telemetry
    Blog · Enterprise AI · Aug 11, 2026

    GitHub has added enterprise MCP allow and deny lists alongside third-party agent activity in usage metrics; this article explains the policy semantics, telemetry boundary, and a practical rollout loop.

    • AI Agent
    • MCP
    • Enterprise AI
    • Governance
  • Claude Managed Agents Become a Governed Runtime: Budgets, Delegation, Locality, and Inference Hooks
    Blog · Cloud & Platform · Aug 11, 2026

    Anthropic's Managed Agents now expose session budgets, advisors, inference geography, repository skills, and inference hooks as runtime controls; this article maps their value and remaining boundaries.

    • AI Agent
    • Anthropic
    • Claude
    • Platform Engineering
  • FinRank: Hard-Negative Retrieval Evaluation for Financial-Document RAG
    Paper Reading · NLP · Aug 11, 2026

    A deep reading of FinRank: how company, year, and disclosure boundaries create deceptively plausible evidence, and why pooled retrieval, hard negatives, and metadata filters must be evaluated together.

    • Paper Reading
    • RAG
    • Information Retrieval
    • Enterprise AI
  • A²E: A Traceable, Re-Evaluable Engine for Agent Auditing
    Paper Reading · AI Engineering · Aug 11, 2026

    A deep reading of A²E: ATP aligns benchmarks with agent harnesses, span-based traces preserve execution causality, and lifecycle-aligned metrics analyze correctness, tools, cost, and safety.

    • Paper Reading
    • Agent Systems
    • Evaluation
    • Observability
  • TREC RAG 2026: When RAG Evaluation Becomes an Agent Workflow
    Blog · AI Engineering · Aug 9, 2026

    A concise entry point to TREC RAG 2026, ClimbMix-400b, and RAGDoll, with a bridge to a technical guide for building a replayable enterprise RAG evaluation harness.

    • RAG
    • Evaluation
    • AI Agent
    • Enterprise AI
  • TREC RAG 2026 Technical Deep Dive: From Evidence Lineage to a Replayable RAG Evaluation Harness
    Blog · AI Engineering · Aug 9, 2026

    A practical design for an enterprise RAG evaluation harness based on TREC RAG 2026 and RAGDoll: data models, execution stages, citation support, agent traces, judge calibration, and production gates.

    • RAG
    • Evaluation
    • AI Agent
    • Enterprise AI
  • Cloudflare's Open Agentic Internet Blueprint: Readable, Discoverable, Callable, and Payable Web
    Blog · Cloud & Platform · Aug 7, 2026

    An architectural deep dive into Cloudflare's proposed Agentic Internet framework, spanning Web Bot Auth, Markdown for Agents, WebMCP browser tool exposure, and x402 micro-payments.

    • AI Agent
    • MCP
    • Platform Engineering
    • Enterprise AI

Huahua checked every note

Nothing matches this search yet.

Try a broader keyword, switch the content type, or continue from one of the curated paths below.

Start with AI agents Explore enterprise RAG

Bloss0m

An AI engineering research and practice brand by Justin — from frontier signals to inspectable systems.

Explore

  • Projects
  • Blog
  • Paper Reading

Meet Justin

About & Contact ↗
  • Now
  • Huahua Lab

Unless noted otherwise, articles and project write-ups are by the author; see each repository for code licences.