PAPERS · REPRODUCTION · ENGINEERING NOTES

Paper reading for working engineers

Structured readings that extract architecture decisions, reproducible methods, evaluation limits, and what changes when research meets a real system.

reading notes
23
research fields
5
guided series
13

START WITH A PATH

Choose the question you want to learn

Three bounded routes turn the library into a sequence. Start at your level and stop when you have the engineering answer you need.

Intro → Intermediate 2 reads

Build the foundations first

Start with AlexNet and practice separating architecture, training evidence, and historical constraints.

  1. AlexNet Part 1: Reading the Evidence Behind an ImageNet Turning Point
  2. AlexNet Part 2: Turning the Training Recipe into Testable Design Choices
Start this path
Intermediate → Advanced 11 reads

Retrieval, memory, and production RAG

Move from multimodal parsing and tool retrieval to memory, GraphRAG, scaling, and runtime controls.

  1. RAG-Anything: Multimodal Document Retrieval Is Not Just Text Conversion
  2. RAG-MCP: Retrieve Tool Discovery, but Account for Routing Failure
  3. RAG without Forgetting: Writing Successful Query Expansion Back into the Index

+ 8 more steps

Start this path
Advanced 8 reads

Agent runtime, safety, and evaluation

Follow reward models, long-horizon memory, runtime control, safety signals, repair, and persistence evaluation.

  1. OSReward Deep Read: Why Agent Success Cannot Be Judged by Another Model Alone
  2. ContextWeave Deep Read: Does Memory Actually Make Agents Better at Work?
  3. Argus Deep Read: Long-Running Agents Need a Runtime, Not a Longer Prompt

+ 5 more steps

Start this path
Intro — problem and intuition Intermediate — method and experiments Advanced — evidence boundaries and adoption

READING LIBRARY

Find a paper by engineering question

Filter by field, reading depth, or the paper’s publication year.

  • SWE-Bench ProMax: Can Large-Scale Multilingual Refactoring Measure Long-Horizon Coding Agents?

    Advanced
    Note · Aug 13, 2026 · Paper · 2026 · AI Engineering

    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.

    Understand it in 90 seconds
    Problem
    Existing coding-agent benchmarks are often Python-heavy and centered on one issue or bug fix. An agent may make a visible test pass while missing cross-file call sites, configuration, documentation, or tests. That does not answer whether it can complete a large, behavior-preserving refactor.
    Design
    The authors mine GitHub refactoring commits, validate Docker environments, use expert and LLM-assisted analysis, and manually review candidates. The final 170 tasks cover Python, Java, TypeScript, Go, C, C++, and Rust.
    Strongest result
    Under the paper's mini-SWE-agent and OpenHands scaffolds, with at most 300 steps and $10 per instance, OpenHands + GPT-5.2 reaches a 41.2% resolve rate. The same model reaches only 21.8% with mini-SWE-agent. This is first a scaffold-and-model result, not a model-only leaderboard.
    Main boundary
    Resolve is a binary outcome—every test must pass. It does not score maintainability, untested behavior, review quality, or the action trace. TypeScript tasks come from only two repositories, with 25 from Angular; language scores are not an independent, balanced experiment in language difficulty.
    Read the full deep dive

  • Agentic Configuration Management: Treating Agent Systems as Governed Configuration, Not Just One Execution

    Advanced
    Agent Security · Part 2 · Note · Aug 12, 2026 · Paper · 2026 · AI Agent

    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.

    Understand it in 90 seconds
    Problem
    an agent system's behavior is determined not only by code, but also by prompts, models, tools, skills, workflows, policies, frameworks, and runtime state. Existing frameworks and AgentOps tools each manage part of this surface, but do not easily pin down the complete configuration that produced an execution.
    Core insight
    ACM normalizes heterogeneous artifacts into typed, independently versioned Agentic Configuration Items (ACIs), managed through four connected Configuration, Evolution, Assurance, and Runtime Graphs. Execution frameworks project into this representation; the governance kernel operates on the common form.
    Strongest evidence
    27 controlled governance scenarios across LangGraph, CrewAI, and the OpenAI Agents SDK, plus 9 quantitative impact cases. Within the evaluated scope, all three frameworks produce equivalent governance outcomes, and repeated impact sets and metrics are stable (Sections 7.2–7.6; Tables 8, 10, and 12).
    Main boundary
    this is conformance and feasibility evidence for a reference model and prototype. Distributed execution, learning, long-term memory, native MCP/A2A protocols, and large-scale industrial validation are outside the current scope (Tables 13–14; Sections 8.4 and 9).
    Read the full deep dive

  • ADIAS: Turning Agent Self-Improvement into Traceable Issue Repair

    Advanced Agent runtime, safety, and evaluation
    Note · Aug 12, 2026 · Paper · 2026 · AI Engineering

    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.

    Understand it in 90 seconds
    Problem
    Automated agent design is usually candidate-centric. Each round re-reads candidate code, scores, and trajectories, but it does not explicitly remember whether the same failure has already been repaired, which intervention worked, or which change caused a regression.
    Core insight
    Make the issue being repaired, rather than the candidate agent, the persistent control state. Each issue has a stable identity, priority, supporting evidence, lifecycle status, and intervention-outcome history.
    Strongest evidence
    ADIAS is evaluated on Tau-Bench, ALFWorld, TextCraft, WebShop, and ScienceWorld against five baselines. Table 1 reports an average score of 78.4 versus 62.6 for DGM-H, with shared wrappers, splits, action interfaces, scoring scripts, a ten-iteration optimization budget, and 15 training episodes per iteration (paper Section 4 and Table 1).
    Main boundary
    The paper holds trajectory diagnosis and issue association fixed rather than measuring their accuracy separately, and evaluates only text-based interactive benchmarks. The GitHub repository still says Coming Soon as of 2026-08-12, so this article does not treat a paper-level code claim as a currently reproducible artifact.
    Read the full deep dive

  • DocMemo: Letting Long-Document RAG Recover from a Bad First Retrieval

    Advanced Retrieval, memory, and production RAG
    Note · Aug 12, 2026 · Paper · 2026 · AI Engineering

    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.

    Understand it in 90 seconds
    Problem
    Evidence in long documents can be spread across dozens of pages, tables, figures, and cross-page clues. Static retrieval fixes a top-k page pool at the start; if the first pass misses evidence, the reasoner has no state that explains which pages may still help, which were ruled out, or what remains missing.
    Core insight
    Turn retrieval into dynamic evidence exploration. Document Schema Memory stores document structure, Page Belief Memory updates page relevance beliefs, and Question Episodic Memory records discoveries and query refinement for the current question.
    Strongest evidence
    On MMLongBench-Doc, LongDocURL, and PaperTab, DocMemo reports accuracy of 71.3, 81.1, and 80.4, for a 77.6 average. Table 4 also shows MMLongBench-Doc accuracy falling from 71.3 to 68.5 or 68.8 when memory or Bayesian updating is removed.
    Main boundary
    Evaluation depends on a GPT-4.1 binary judge, PDF rendering, Qwen3.5-VL-9B, ColQwen2.5, MinerU, and annotations from three benchmarks. It does not establish citation faithfulness, access-control correctness, freshness, or total cost on arbitrary enterprise corpora.
    Read the full deep dive

  • FinRank: Hard-Negative Retrieval Evaluation for Financial-Document RAG

    Intermediate Retrieval, memory, and production RAG
    Financial Retrieval Evaluation · Part 1 · Note · Aug 11, 2026 · Paper · 2026 · NLP

    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.

    Understand it in 90 seconds
    Problem
    Financial-document QA fails for more than one reason. The same term can appear in different companies, filing years, and notes, while a metadata filter can remove the true supporting passage. FinRank asks whether a retriever can preserve the right evidence among these plausible but wrong alternatives.
    Core insight
    The authors build 1,185 human-authored financial QA records, a 5,230-passage pooled corpus, and 6,021 curated hard negatives, then test generalization across multiple splits, query rewrites, and provenance boundaries.
    Strongest evidence
    On the pooled corpus, the reported Recall@10 is 44.8 for e5-mistral-7b-instruct and 32.1 for BM25. Metadata-filtered BM25 reaches 55.0, but Section 7.1 notes that first-occurrence metadata can exclude the gold passage. In Section 7.3, curated hard negatives lower pairwise accuracy by 13.0–20.5 percentage points versus random negatives.
    Main boundary
    The paper does not measure answer generation, citation correctness, or faithfulness. The data is concentrated in U.S. 10-K/10-Q filings from 2024–2025, with annotation and distribution caveats. This is a strong retrieval-evaluation starting point, not proof of safe financial RAG deployment.
    Read the full deep dive

  • A²E: A Traceable, Re-Evaluable Engine for Agent Auditing

    Intermediate Agent runtime, safety, and evaluation
    Agent Auditing · Part 1 · Note · Aug 11, 2026 · Paper · 2026 · AI Engineering

    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.

    Understand it in 90 seconds
    Problem
    A correct final answer does not tell you whether an agent took a reliable, cheap, or safe path. A wrong answer does not tell you whether the failure came from planning, tool use, memory, judging, or runtime. When each harness stores its own text log, cross-framework comparison and later metric iteration become difficult.
    Core insight
    A²E separates Task, Monitor, and Evaluation. The Agent Task Protocol (ATP) separates benchmark tasks from harness execution; the Monitor turns model calls, tool calls, state, and errors into parent-child traces; Evaluation organizes process, outcome, and runtime metrics under one lifecycle-aligned taxonomy.
    Strongest evidence
    The experiment covers 23 benchmarks, 9 harnesses, 5 tasks per cell, and 1,035 scored runs while holding the DeepSeek-V4-pro FP4 backbone, inference configuration, tool setup, step limit, and timeout fixed. Section 6 reports success-rate gaps of 0.20 on GDPVal, 0.30 on MMLU-Pro, and 0.66 on tau³-bench.
    Main boundary
    This is a platform architecture and diagnostic demonstration, not a universal ranking of nine harnesses. The prose and displayed tasksucceeded/correctness values in Table 2 conflict; paper commit, judge calibration, API drift, and component-level ablations are not fixed enough for strong causal claims.
    Read the full deep dive

  • ContextWeave Deep Read: Does Memory Actually Make Agents Better at Work?

    Advanced Agent runtime, safety, and evaluation
    Agent Evaluation · Part 2 · Note · Aug 7, 2026 · Paper · 2026 · AI Agent

    A close reading of how ContextWeave reconstructs multi-month workflows into an executable benchmark and measures memory's effect on workspace outcomes, preference adherence, continuity, and misleading recall.

    Understand it in 90 seconds
    Problem
    memory benchmarks often count whether history is retrieved, not whether it makes the next executable task better.
    Core insight
    reconstruct multi-month workflows as fixed executable task streams, then change only access to prior trajectories for the same target task. Measure workspace quality and preference adherence, not a retrieval hit alone.
    Strongest evidence
    with 14 participants and 1,005 reconstructed tasks (568 core evaluation tasks), the strongest component raises Workspace Score from 68.08 to 78.20 and Preference Score from 41.50 to 70.60 (Section 5.2, Table 2).
    Main boundary
    Docker reconstruction, mock APIs, and LLM-based rubrics make the comparison controlled; they do not establish the uplift of every memory implementation on live enterprise data or drifting tools.
    Read the full deep dive

  • Argus Deep Read: Long-Running Agents Need a Runtime, Not a Longer Prompt

    Advanced Agent runtime, safety, and evaluation
    Multi-Agent Coordination · Part 1 · Note · Aug 7, 2026 · Paper · 2026 · AI Agent

    A critical reading of Argus's Manager–Planner–Engineer–Reviewer runtime, durable state, verification-gated evolution, and rollback, separating benchmark results from author-operated case studies and unproven self-learning claims.

    Understand it in 90 seconds
    Problem
    a longer prompt does not give a long-running agent explicit task authority, auditable state, verification gates, or recovery boundaries.
    Core insight
    Argus cycles Manager, Planner, Engineer, and Reviewer over durable project state; memory, skills, routing, and procedures persist only after role-owned review.
    Strongest evidence
    across seven task-native arenas, the report gives breadth evidence and reports 78% for Argus versus 59% for Direct Copilot on SWE-Bench Pro under GPT-5.5, at roughly 1.41x aggregate tokens (Figure 1; Section 5).
    Main boundary
    this is an arXiv v1 technical report. The implementation, prompts, traces, checkpoints, and complete benchmark package are not public, so the reported outcome is not a reproducible adoption proof.
    Read the full deep dive

  • AskChem: Making Provenance-Carrying Claims the Retrieval Unit

    Advanced Retrieval, memory, and production RAG
    Retrieval Systems · Part 1 · Note · Aug 7, 2026 · Paper · 2026 · NLP

    A critical reading of AskChem's atomic claims, source locators, faceted taxonomy, evidence graph, and AskChem-Bench results, with a clear boundary between citation traceability and scientific correctness.

    Understand it in 90 seconds
    Problem
    paper/chunk retrieval leaves a reader or agent to find the supporting sentence, establish claim location, and synthesize across papers.
    Core insight
    AskChem makes typed atomic claims with DOI and quote/evidence locators the retrieval unit, then connects them through taxonomy, an evidence graph, and shared REST/SDK/MCP interfaces.
    Strongest evidence
    the 2.4M-claim, 147K-paper system reports 100% DOI resolvability for AskChem-grounded answers versus 88.3% for LLM-only on 30 chemistry synthesis questions (Section 7; Table 1).
    Main boundary
    DOI resolvability and citation density are provenance proxies, not proof of claim truth, complete literature coverage, or usable chemical conclusions.
    Read the full deep dive

  • AgentS4D Deep Read: The Task Finished—Is the Runtime Safe?

    Advanced Agent runtime, safety, and evaluation
    Agent Security · Part 1 · Note · Aug 7, 2026 · Paper · 2026 · AI Agent

    A critical reading of how AgentS4D places workspace-agent risk entry, induction strategy, target harm, and lifecycle evidence in one sandbox benchmark, and why completion rate cannot stand in for safety.

    Understand it in 90 seconds
    Problem
    a workspace agent can finish its task while creating unsafe side effects through prompts, skills, files, web content, memory, or user messages.
    Core insight
    AgentS4D evaluates the complete harness–LLM–task environment, crossing risk source, induction strategy, harm, and execution-lifecycle evidence while scoring completion separately from safety.
    Strongest evidence
    328 risk-injected cases across 20 harness/backend configurations yield 6,560 runs; 4,461 (68.0%) trigger a prespecified unsafe signal and 4,344 (66.22%) are both unsafe and complete (Section 4; Table 2).
    Main boundary
    assets, effects, and cases are synthetic/controlled, and v1 has no executable code or data. These rates are not production incident rates or a universal safety ranking.
    Read the full deep dive

  • BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

    Intermediate Retrieval, memory, and production RAG
    Retrieval Systems Deep Dive · Part 2 · Note · Aug 7, 2026 · Paper · 2026 · NLP

    A deep reading of Wang et al.'s arXiv v3 study: across 28 nested enterprise-shaped corpus tiers with fixed questions, evidence, and adversarial documents, why BM25 crosses over at roughly 10 million corpus tokens and why agents should begin after global candidate discovery.

    Understand it in 90 seconds
    Problem
    RAG paradigms are often compared at one corpus size, hiding joint accuracy, construction-cost, query-cost, and latency scaling.
    Core insight
    28 nested corpus tiers (1,144 to 511,959 documents) hold reader/judge and adversarial bedrock fixed while comparing lexical, dense, graph, and file-system agency; a retrieval-swap control isolates access substrate.
    Strongest evidence
    at large shared tiers, BM25 reportedly overtakes raw file-system agency around 10M corpus tokens; a matched 150-question resweep gives Agent+BM25 69.4 versus raw-file agency 36.9 (Section 5.1; Figure 4; Table 4).
    Main boundary
    EnterpriseRAG-Bench is fictional and enterprise-shaped, with 500 questions and one main reader/judge; no public executable data/benchmark artifact is confirmed, so this is not “BM25 always wins.”
    Read the full deep dive

  • Real-Time Detection and Repair of LLM Agent Failures: A Deep Read of AgentTrajectorySentinel

    Advanced Agent runtime, safety, and evaluation
    Agent Evaluation · Part 3 · Note · Aug 7, 2026 · Paper · 2026 · AI Agent

    A critical reading of AgentTrajectorySentinel's low-cost healthy-only temporal monitor, deterministic verification, and rollback-and-retry loop, separating measured detection and repair gains from calibration dependence, content blind spots, and reproducibility limits.

    Understand it in 90 seconds
    Problem
    agent failures begin before the final answer; an LLM judge at every step can be too slow and costly.
    Core insight
    a temporal monitor trained on healthy trajectories works with deterministic verification; supported interventions roll state back to a trusted checkpoint for targeted retry.
    Strongest evidence
    across 2,823 committed episodes, three frameworks, and several models, the repair study compares monitor, verifier, and policy and reports task success from 52% to 73% (Section 5; Table 4).
    Main boundary
    healthy-only calibration, short trajectories, injected failures, and weak textual-hallucination detection limit transfer to a new production stack.
    Read the full deep dive

  • Before Reasoning Can Fail: Pre-Evidence Procedural Failures in Agentic RAG

    Advanced Retrieval, memory, and production RAG
    Production RAG Controls · Part 1 · Note · Aug 7, 2026 · Paper · 2026 · Retrieval Systems

    A deep read of how Before Reasoning Can Fail turns answer-before-reading into an observable trajectory failure, and tests whether Read-Gate actually improves multi-hop QA.

    Understand it in 90 seconds
    Problem
    an agentic RAG system can search snippets but finalize before reading. That is a procedural failure before evidence-conditioned reasoning, distinct from being wrong after reading gold evidence.
    Core insight
    saved tool traces, retrieved/read passages, and final answers define discipline and post-gold-read failure; Read-Gate requires at least one read after search and before final, without changing model, retriever, or reasoning budget.
    Strongest evidence
    12,000 paired trajectories over HotpotQA, 2WikiMultiHopQA, and MuSiQue; forced reading adds 14.9–19.9 LLM-Acc points on the zero-read subset and 3.2–9.4 on full minimal-reasoning cells (Table 1; Section 5.2).
    Main boundary
    it applies to systems with observable search/read/final actions; reading does not guarantee the right evidence or reasoning, and incomplete MuSiQue gold chunks limit post-gold-read analysis.
    Read the full deep dive

  • PAST-Bench: What Did a Persistent Agent Actually Learn from the Past?

    Advanced Agent runtime, safety, and evaluation
    Agent Evaluation · Part 4 · Note · Aug 7, 2026 · Paper · 2026 · AI Agent

    A deep read of how PAST-Bench uses fresh-session task families, matched persistence controls, and trace-level mechanism evidence to separate genuine retained-experience gains from higher scores with unrelated causes.

    Understand it in 90 seconds
    Problem
    a persistent agent's later score can improve because of model, prompt, task difficulty, or residual context—not because it used prior experience correctly.
    Core insight
    PAST-Bench uses fresh-session task families, holds prompt, grader, and tool stack fixed, and switches persistence on/off while reporting task-score gap and write/read/artifact mechanism evidence.
    Strongest evidence
    26 scenarios, 204 episodes, four capabilities, seven models, and four frameworks; Hermes+ reports its overall gap from +0.13 to +0.15 and Mech from 0.64 to 0.73 (Table 2; Section 4.3).
    Main boundary
    the gap difference is smaller than run-to-run variation, tasks are authored by the proposing team, and matched ablation is a strong control rather than complete causal proof.
    Read the full deep dive

  • RubricRanker Deep Read: RAG Needs the Right Document Set, Not Just the Most Relevant Documents

    Advanced Retrieval, memory, and production RAG
    Retrieval Systems · Part 3 · Note · Aug 7, 2026 · Paper · 2026 · Retrieval Systems

    A close reading of how RubricRanker uses query-specific search rubrics, SFT, and GRPO to train a document reranker, and what its deep-research and RAG benchmark results actually establish.

    Understand it in 90 seconds
    Problem
    Traditional rerankers score documents independently, so the top k need not be complete, concise, consistent, or authoritative as a set.
    Core insight
    Change the output target from a document ranking to an evidence set that jointly supports the answer, using query-specific rubrics for labels and rewards.
    Strongest evidence
    Tables 1–3 show downstream gains, while the ablation points to rubric labels and cold-start SFT rather than RL alone.
    Main boundary
    Final answers are still produced by agents and scored by LLM judges; a better evidence set does not guarantee correct citation, reasoning, or facts.
    Read the full deep dive

  • OSReward Deep Read: Why Agent Success Cannot Be Judged by Another Model Alone

    Advanced Agent runtime, safety, and evaluation
    Agent Evaluation · Part 1 · Note · Aug 2, 2026 · Paper · 2026 · AI Agent

    A complete reading of OSReward's data construction, 27 VLM judges, Hard and Multi subsets, error and cost analyses, OS-Shepherd-100K training, and a deployable hybrid verification architecture.

    Understand it in 90 seconds
    Previous approach's limitation
    Traditional model judges infer success from compressed screens and text histories, making them vulnerable to an agent's completion narrative.
    Core insight
    Use a human-gold benchmark to expose false-success bias, then separate verifiable state, model judgment, and human arbitration into distinct evidence layers.
    Strongest evidence
    Table 1 and Figures 5–7 show judges near 90% on the full set falling to roughly 70% on the Hard set, with directional failure-recall and cross-platform errors.
    Main boundary
    OS-Shepherd improves cost and some accuracy, but its labels still come from strong-judge agreement and the full artifact and production-verifier stack is incomplete.
    Read the full deep dive

  • Beyond RAG for Agent Memory: Detailed Notes on xMemory

    Intermediate Retrieval, memory, and production RAG
    Beyond RAG for Agent Memory Deep Dive · Part 1 · Note · Mar 24, 2026 · Paper · 2026 · NLP

    An interpretation of arXiv:2602.02007 covering xMemory's four-tier hierarchy, sparsity–semantics objective, two-stage top-down retrieval, and empirical results on LoCoMo/PerLTQA.

    Understand it in 90 seconds
    Problem
    agent memory is a temporally connected, near-duplicate, highly relevant interaction stream; fixed top-k chunks can crowd into one local region, while pruning can sever dependencies.
    Core insight
    xMemory decouples and aggregates raw messages into message, episode, semantic, and theme levels, uses a sparsity–semantics objective for split/merge, and retrieves top-down to spend detail only when needed.
    Strongest evidence
    LoCoMo, PerLTQA, and long-dialogue comparisons use Table 1, Figure 2, Figure 3, and appendix ablations to support hierarchy, retrieval, and efficiency claims.
    Main boundary
    hierarchy quality depends on segmentation, embeddings, and budget; benchmark QA does not establish safe production updates or governance of long-term memory.
    Read the full deep dive

  • RAG vs GraphRAG: A Systematic Evaluation and Hybrid Strategies (Detailed Notes)

    Intermediate Retrieval, memory, and production RAG
    GraphRAG vs RAG Deep Dive · Part 1 · Note · Mar 24, 2026 · Paper · 2025 · NLP

    Interpreting the unified evaluation protocol, four types of GraphRAG, figures in Tables 1-5, efficiency trade-offs, and Selection/Integration hybrid strategies based on arXiv:2502.11371.

    Understand it in 90 seconds
    Problem
    GraphRAG systems change graph construction, retrieval, context budget, and generation at once, so individual papers do not answer when graph cost is worthwhile.
    Core insight
    under unified preprocessing, retrieval budgets, and generation scripts, the paper separates RAG from KG-based, community-based, text-centric, and hierarchical GraphRAG, then proposes Selection/Integration hybrids.
    Strongest evidence
    QA and query-based-summarization comparisons in Tables 1–5 and Sections 4–5 show that benefits vary by query type, global context, and graph-building cost.
    Main boundary
    tested systems, corpora, Llama-3.1-8B-Instruct, and fixed budgets limit transfer; a benchmark win is not ROI for your documents or SLA.
    Read the full deep dive

  • RAG-Anything: Multimodal Document Retrieval Is Not Just Text Conversion

    Intermediate Retrieval, memory, and production RAG
    RAG-Anything Deep Dive · Part 1 · Note · Mar 23, 2026 · Paper · 2025 · NLP

    A source-grounded reading of RAG-Anything's dual graph, experimental evidence, failure cases, artifact status, and engineering adoption boundary.

    Understand it in 90 seconds
    Problem
    Traditional approaches often collapse figures and tables into captions, losing cells, panels, axes, and cross-page relationships.
    Core insight
    Use textual proxies for retrieval while preserving dereferenceable raw artifacts; combine explicit graph relations with dense similarity to find evidence.
    Strongest evidence
    Tables 2–4 and Figure 2 show an overall lead, attribute most of the gain to graph construction, and show a larger gap on long-document slices.
    Main boundary
    Abstention, parser errors, entity alignment, cost, and latency are not solved by aggregate accuracy.
    Read the full deep dive

  • RAG-MCP: Retrieve Tool Discovery, but Account for Routing Failure

    Intermediate Retrieval, memory, and production RAG
    RAG-MCP Deep Dive · Part 1 · Note · Mar 23, 2026 · Paper · 2025 · NLP

    A source-grounded reading of RAG-MCP's tool-routing pipeline, 11,100-tool stress test, MCPBench result, scale failure, and incomplete artifacts.

    Understand it in 90 seconds
    Problem
    placing every MCP tool schema in a prompt increases tokens, distractors, and wrong-tool selection.
    Core insight
    index MCP metadata, retrieve a small top-k schema set, then validate and invoke inside that set. Retrieval generates candidates; it does not authorize a decision.
    Strongest evidence
    on MCPBench web search, RAG-MCP reports 43.13% ground-truth MCP top-1 accuracy versus 18.20% for keyword pre-filter and 13.62% for all-schema prompting (Section 4.2; Table 1).
    Main boundary
    v1 does not fully expose retriever metadata, embedding/version, schema drift, permission, p95 latency, or real invocation success; top-1 routing is not task success.
    Read the full deep dive

  • RAG without Forgetting: Writing Successful Query Expansion Back into the Index

    Intermediate Retrieval, memory, and production RAG
    RAG without Forgetting Deep Dive · Part 1 · Note · Mar 23, 2026 · Paper · 2026 · NLP

    A source-grounded assessment of ERM's correctness gate, selective attribution, bounded key updates, BEIR/BRIGHT results, and missing artifacts.

    Understand it in 90 seconds
    Problem
    query expansion can bridge query–document mismatch but regenerates work on every request; persistent key expansion can write bad feedback into the index.
    Core insight
    ERM accepts an expansion unit only through a correctness gate, attributes it to document keys whose similarity it improves, and applies a bounded update. It updates keys, not retriever parameters.
    Strongest evidence
    the paper reports retrieval and generation results across 13 BEIR/BRIGHT domains, with Table 1, Table 2, Figure 3, and Appendix B.9 separating quality, latency, budget, and transfer.
    Main boundary
    there is no public implementation, live A/B, attack/privacy, or rollback study; a bad gate can turn a wrong association into persistent index state.
    Read the full deep dive

  • AlexNet Part 2: Turning the Training Recipe into Testable Design Choices

    Intermediate Build the foundations first
    AlexNet Deep Dive · Part 2 · Note · Mar 19, 2026 · Paper · 2012 · CV

    A source-grounded reading of ReLU, multi-GPU splitting, overlapping pooling, augmentation, and dropout in Figure 1–3 and Sections 3–6.

    Understand it in 90 seconds
    Problem
    a 60M-parameter CNN can overfit even with 1.2M images, and its training recipe must be separated from the competition result.
    Core insight
    random crop/flip, RGB PCA lighting jitter, and dropout change or regularize the effective training distribution; SGD, momentum, weight decay, and a learning-rate schedule make Part 1's architecture converge.
    Strongest evidence
    color augmentation reduces top-1 error by over 1%, overlapping pooling by 0.4/0.3 points, and the full system reaches 37.5/17.0 on ILSVRC-2010 and 15.3 top-5 in 2012 (Sections 4–6; Table 1).
    Main boundary
    these ablations belong to the era's architecture, data, and compute; they do not show every modern vision model needs ten-crop, LRN, or the same schedule.
    Read the full deep dive

  • AlexNet Part 1: Reading the Evidence Behind an ImageNet Turning Point

    Introductory Build the foundations first
    AlexNet Deep Dive · Part 1 · Note · Mar 18, 2026 · Paper · 2012 · CV

    A source-grounded rereading of AlexNet’s problem, evaluation, historical result, and evidence boundary.

    Understand it in 90 seconds
    Problem
    in 2012, training a deep CNN on millions of high-resolution images was constrained by optimization speed, GPU memory, and overfitting.
    Core insight
    AlexNet is not one “big network” trick: convolutional locality, ReLU, a constrained two-GPU split, and an eight-layer architecture form a trainable system.
    Strongest evidence
    ILSVRC-2010 top-1/top-5 error is 37.5%/17.0%; the 2012 competition top-5 error is 15.3% versus 26.2% for second place (Section 6; Table 1).
    Main boundary
    LRN, the two-GPU split, and some kernel choices are hardware-era tradeoffs, not claims of modern optimality.
    Read the full deep dive

RESEARCH EXCHANGE

Turn a paper into an engineering discussion

Speaking & contact