{
  "schema_version": "1.1",
  "id": "atlas-retrieval",
  "slug": "retrieval",
  "title": "Retrieval",
  "url": "https://feed7.dev/atlas/retrieval",
  "current_answer": null,
  "implementation_consequence": null,
  "agent_context": null,
  "confidence": "auto_collected",
  "last_verified": null,
  "last_updated": null,
  "evidence": [],
  "conflicting_sources": [],
  "superseded_claims": [],
  "corpus_evidence": [
    {
      "title": "ReToken: One Token to Improve Vision-Language Models for Visual Retrieval",
      "url": "https://arxiv.org/abs/2607.28627v1",
      "source_name": "arXiv",
      "published_at": "2026-07-30T17:59:56+00:00",
      "summary": "ReToken adds one learned retrieval embedding to select relevant visual tokens from a cached context, improving long-image and video benchmarks while fitting training and inference on one H100."
    },
    {
      "title": "Build for the Memo, Not the Demo — Shawn Chan, China Resources Holdings",
      "url": "https://www.youtube.com/watch?v=tJFjeMBKbIY",
      "source_name": "AI Engineer",
      "published_at": "2026-07-30T02:00:06+00:00",
      "summary": "Finance agents need claim-level provenance, explicit uncertainty, consistency checks, surfaced contradictions, and logged approval. Fluent output without those controls will not survive diligence."
    },
    {
      "title": "UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams",
      "url": "https://arxiv.org/abs/2607.26017v1",
      "source_name": "arXiv",
      "published_at": "2026-07-28T17:28:21+00:00",
      "summary": "UniMem routes novel experience into retrieval memory and consolidates recurring patterns into expandable parameters, offering a design for agents that learn across unlabelled task streams."
    },
    {
      "title": "MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents",
      "url": "https://arxiv.org/abs/2607.25992v1",
      "source_name": "arXiv",
      "published_at": "2026-07-28T17:08:56+00:00",
      "summary": "MemLens scores individual agent memories, stores them by value, and exposes quality, latency, and token tradeoffs—an inspectable alternative to retaining every interaction equally."
    },
    {
      "title": "Serving 2 Million Models Without Melting: Scaling the Hugging Face Hub — Arek Borucki, Hugging Face",
      "url": "https://www.youtube.com/watch?v=lyL5QhgIOxc",
      "source_name": "AI Engineer",
      "published_at": "2026-07-28T13:41:11+00:00",
      "summary": "Hugging Face’s Hub shows how to scale model search: precompute tokens, separate metadata from artifacts, isolate heavy reads, and autoscale from workload signals."
    },
    {
      "title": "AI on Your Lakehouse: Context Comes in Shapes, Not Queries — Zach Blumenfeld, Neo4j",
      "url": "https://www.youtube.com/watch?v=kRkcNOsRyYg",
      "source_name": "AI Engineer",
      "published_at": "2026-07-23T07:00:23+00:00",
      "summary": "Graph-shaped context can expose relationships and document structure that vector search or Text-to-SQL misses. Treat it as an additional retrieval surface, then benchmark it against your own data."
    },
    {
      "title": "Citation Needed: Provenance for LLM-Built Knowledge Graphs — Daniel Chalef, Zep AI",
      "url": "https://www.youtube.com/watch?v=H7puB0RwJMM",
      "source_name": "AI Engineer",
      "published_at": "2026-07-23T04:00:02+00:00",
      "summary": "LLM synthesis breaks simple source pointers when facts merge, change, or outlive one input. Model provenance inside the context graph so agents can filter trust, debug derivation, and apply deletion policies."
    },
    {
      "title": "virgiliojr94/book-to-skill",
      "url": "https://github.com/virgiliojr94/book-to-skill",
      "source_name": "GitHub",
      "published_at": null,
      "summary": "book-to-skill compiles books and document sets into on-demand agent skills, reducing repeated context loading while preserving chapter-level references and reusable decision rules."
    },
    {
      "title": "How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?",
      "url": "https://arxiv.org/abs/2607.11783v1",
      "source_name": null,
      "published_at": null,
      "summary": "A RAG study finds that retrieved ideology carries into answers and varies with sampling temperature, so source audits and decoding tests should be evaluated together."
    },
    {
      "title": "Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation",
      "url": "https://arxiv.org/abs/2607.05382v1",
      "source_name": null,
      "published_at": null,
      "summary": "SearchGen-Bench shows open image generators score 21–28/100 on long-tail entities, and naive search retrieval only adds noise; a teach-then-search co-training recipe learns when to retrieve versus rely on weights."
    },
    {
      "title": "Shubhamsaboo/awesome-llm-apps",
      "url": "https://github.com/Shubhamsaboo/awesome-llm-apps",
      "source_name": null,
      "published_at": null,
      "summary": "This Apache-2.0 collection provides runnable agent, skill, MCP, memory, multi-agent, and RAG examples across major model providers, useful for borrowing patterns before choosing a stack."
    },
    {
      "title": "Graphify-Labs/graphify",
      "url": "https://github.com/Graphify-Labs/graphify",
      "source_name": null,
      "published_at": null,
      "summary": "Graphify gives coding agents a queryable project graph with provenance-tagged relationships, reducing repeated repository scans while keeping inferred links visibly distinct from extracted facts."
    },
    {
      "title": "RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI",
      "url": "https://www.youtube.com/watch?v=8oyalrfwgjw",
      "source_name": null,
      "published_at": null,
      "summary": "RLMs treat a large repository as external data that an agent inspects with code, returning bounded evidence to the main context instead of loading or summarizing everything upfront."
    },
    {
      "title": "ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning",
      "url": "https://arxiv.org/abs/2607.02509v1",
      "source_name": null,
      "published_at": null,
      "summary": "ReContext is a training-free harness that replays query-relevant evidence from long inputs before answering, taking the best average rank across 8 long-context benchmarks up to 128K on Qwen3-4B/8B and Llama3-8B."
    },
    {
      "title": "Panniantong/Agent-Reach",
      "url": "https://github.com/Panniantong/Agent-Reach",
      "source_name": "GitHub",
      "published_at": null,
      "summary": "Agent Reach installs, checks, and routes web-access tools for coding agents, reducing the setup work behind research across social platforms, video sites, GitHub, RSS, and the open web."
    }
  ]
}