Retrieval

A telecom diagnosis pipeline structures telemetry before forcing a decision path and evidence-grounded explanation. The pattern is relevant to agents reasoning over heterogeneous operational data.

DIASENTINEL combines deterministic extraction, guideline retrieval, risk prediction, and hybrid verification on-premise. It is a useful architecture reference for auditable agents handling sensitive data.

California’s financial regulator built an offline AI pipeline around replayable data, hardware-backed redaction, model routing, and one-way updates for court-defensible evidence.

Agents often stop after finding plausible code context. Werry argues for task-specific retrieval that also surfaces decisions, conventions, PR history, and expertise before planning or review.

For fast-changing libraries, ship concise agent-facing docs inside the package as well as on the web; agents may inspect installed code before visiting your site.

Plausible outputs can hide consequential omissions that generic LLM judges miss. Production evals need real failure discovery and retrieved expert judgments, not a frozen rubric alone.

Re³Cap uses multimodal retrieval to find caption omissions and hallucinations before refinement, offering a concrete retrieval-and-review pattern for vision agents.

A coding agent with repository access still recommended a known outage trigger. Background agents need reconciled decisions and incident context, not just more raw MCP results.

IAR turns a fixed document corpus into parametric knowledge through separate injection, QA alignment, and recovery stages. It improved domain QA while retaining more general capability than vanilla SFT.

LFU was the strongest simple semantic-cache default, but answer validity mattered far more than eviction policy. Raw hit rates above 50% fell near 2% after quality adjustment.

In this AI-tutor evaluation, keeping full history beat compaction on recall and cost because cached tokens were cheap. Measure your constraint before shortening agent context.

Fresh web retrieval becomes product infrastructure once agents need sub-second responses and sustained scale. The talk’s failed client demo shows why dev latency alone says little about production resilience.

SheetCompass keeps spreadsheet structure as a hierarchical relation graph instead of flattening cells into text. Its agent memory retains task-relevant context across sheets, tables, and columns.

A small company-enrichment test suggests rented web context is convenient for changing queries, while repeated stable queries may justify owning the pipeline. The reported crossover was around 15,000 queries.

Persistent memory is a compute and product tradeoff, not just retrieval. Profiles need conflict detection, visibility, editing, and deliberate update cadence before agents can rely on them.

Training directly on a private corpus can memorize it without producing useful behavior. Durable context learning likely needs synthetic study tasks and recursive self-improvement, not a single fine-tuning pass.

AI Gateway now exposes Exa search as a keyless tool for any gateway model, and eve uses it by default. The free period ends August 31, so keep cost assumptions temporary.

PsychoAgent separates factual and affective memory, then reranks relevant memories by salience. It retrieved more conflict-critical context, but output-quality differences were not significant.

A Greek RAG study shows generic multilingual embeddings can lose to BM25 in specialist domains, while targeted adaptation sharply improves retrieval and grounded answers. Language-specific evaluation still matters.

PRECOG precomputes SSM corpus states and injects them at query time, avoiding context re-ingestion. On a 1.2B edge model, reported prefill fell from about 27 seconds to under 6 ms.

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.

Finance agents need claim-level provenance, explicit uncertainty, consistency checks, surfaced contradictions, and logged approval. Fluent output without those controls will not survive diligence.

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.

MemLens scores individual agent memories, stores them by value, and exposes quality, latency, and token tradeoffs—an inspectable alternative to retaining every interaction equally.

Hugging Face’s Hub shows how to scale model search: precompute tokens, separate metadata from artifacts, isolate heavy reads, and autoscale from workload signals.

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.

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.

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.

SIE consolidates retrieval, document conversion, structured output, safety, and generation models behind one self-hosted, OpenAI-compatible API for agent stacks.

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.

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.

A local-first Obsidian system gives coding agents durable, cited context while keeping Markdown portable and serializing writes into recoverable transactions.

Claude-Mem records agent activity, compresses it into persistent project memory, and retrieves selected history later, trading extra local services and stored data for cross-session continuity.

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.

RAGFlow packages document ingestion, retrieval, citations, agent workflows, memory and MCP into one self-hostable context layer. It is useful when an agent needs traceable answers across mixed private data.

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.

code-review-graph gives coding agents a local, incrementally updated dependency map over MCP, narrowing review context while exposing affected callers, dependents, and tests.

Crawl4AI turns browser-rendered pages into Markdown or structured data for agent and RAG pipelines. v0.9.2 fixes streaming leaks and deployment issues after two security-focused releases.

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.

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.