Agent Engineering

Every agent in 2026 — Claude Code, Cursor, Devin, Operator — is a variant of the ReAct loop from 2022. Reasoning tokens interleave with tool calls and observations until a stop …

ReAct interleaves thought and action in one stream. ReWOO separates them: one big plan up front, then execute. 5x fewer tokens, +4% accuracy on HotpotQA, and you can distill the…

Gradient-based RL needs thousands of trials and a GPU cluster to fix a failure mode. Reflexion (Shinn et al., NeurIPS 2023) does it in natural language: after each failed trial,…

A single chain-of-thought trajectory has no room to backtrack. ToT (Yao et al., 2023) turns reasoning into a tree with self-evaluation on each node. LATS (Zhou et al., 2024) uni…

Self-Refine (Madaan et al., 2023) uses one LLM in three roles — generate, feedback, refine — in a loop. Average gain: +20 absolute on 7 tasks. CRITIC (Gou et al., 2023) hardens …

Toolformer (Schick et al., 2023) started self-supervised tool annotation. Berkeley Function Calling Leaderboard V4 (Patil et al., 2025) sets the 2026 bar: 40% agentic, 30% multi…

Context windows are finite. Conversations, documents, and tool traces are not. MemGPT (Packer et al., 2023) frames this as OS virtual memory — main context is RAM, external stor…

MemGPT became Letta in 2024. The 2026 evolution adds two ideas: discrete functional memory blocks the model can edit directly, and a sleep-time agent that consolidates memory as…

Mem0 (Chhikara et al., 2025) treats memory as three stores in parallel — vector for semantic similarity, KV for fast fact lookup, graph for entity-relationship reasoning. A scor…

Voyager (Wang et al., TMLR 2024) treats executable code as a skill. Skills are named, retrievable, composable, and refined by environment feedback. This is the reference archite…

Symbolic planning handles the cases where the plan is provably correct. Evolutionary code search handles the cases where the fitness function is machine-checkable. ChatHTN (2025…

Schluntz and Zhang (Anthropic, Dec 2024) distinguish workflows (predefined paths) from agents (dynamic tool-use). Five workflow patterns cover most cases. Start with direct API …

LangGraph is the 2026 reference for low-level stateful orchestration. Agent is a state machine; nodes are functions; edges are transitions; state is immutable and checkpointed a…

AutoGen v0.4 (Microsoft Research, Jan 2025) redesigned agent orchestration around the actor model. Async message exchange, event-driven agents, fault isolation, natural concurre…

CrewAI is the 2026 role-based multi-agent framework. Four primitives: Agent, Task, Crew, Process. Two top-level shapes: Crews (autonomous, role-based collaboration) and Flows (e…

OpenAI Agents SDK is the lightweight multi-agent framework built on the Responses API. Five primitives: Agent, Handoff, Guardrail, Session, Tracing. Handoffs are tools named `tr…

The Claude Agent SDK is the library form of the Claude Code harness. Built-in tools, subagents for context isolation, hooks, W3C trace propagation, session store parity. Claude …

Agno (Python) and Mastra (TypeScript) are the 2026 production-runtime pairing. Agno aims at microsecond agent instantiation and stateless FastAPI backends. Mastra ships agents, …

Three benchmarks anchor agent evaluation in 2026. SWE-bench tests code patching. GAIA tests generalist tool use. AgentBench tests multi-environment reasoning. Know their composi…

WebArena tests web-agent capability across four self-hosted apps. OSWorld tests desktop-agent capability across Ubuntu, Windows, macOS. At release (2023–2024) both showed a big …

Three production computer-use models in 2026. All three are vision-based. All three treat screenshots, DOM text, and tool outputs as untrusted input. Only direct user instructio…

Voice agents are a first-class production category in 2026. Pipecat gives you a Python frame-based pipeline (VAD → STT → LLM → TTS → transport). LiveKit Agents bridges AI models…

OpenTelemetry's GenAI SIG (launched April 2024) defines the standard schema for agent telemetry. Span names, attributes, and content-capture rules converge across vendors so age…

Three open-source agent observability platforms dominate 2026. Langfuse (MIT) — 6M+ installs/month, tracing + prompt management + evals + session replay. Arize Phoenix (Elastic …

Du et al. (ICML 2024, "Society of Minds") run N model instances that independently propose answers, then iteratively critique each other over R rounds to converge. Improves fact…

MASFT (Berkeley, 2025) catalogs 14 multi-agent failure modes in 3 categories. Microsoft's Taxonomy documents how existing AI failures amplify in agentic settings. Industry field…

Greshake et al. (AISec 2023) established indirect prompt injection as the defining agent security problem. Attacker plants instructions in data the agent retrieves; on ingest, t…

Four orchestration patterns recur across 2026 frameworks: supervisor-worker, swarm / peer-to-peer, hierarchical, debate. Anthropic's guidance: "It's about building the right sys…

Production agents run on six runtime shapes: request-response, streaming, durable execution, queue-based background, event-driven, and scheduled. Pick the shape before you pick …

Anthropic's guidance: "start with simple prompts, optimize them with comprehensive evaluation, and add multi-step agentic systems only when needed." Evaluation is not the last s…

A capable model is not enough. Reliable agents need a workbench: instructions, state, scope, feedback, verification, review, and handoff. Strip those away and even a frontier mo…

The smallest useful workbench is three files: a root instructions router, a state file, and a task board. Everything else is layered on top. If a repo cannot carry these three, …

Instructions written as prose are wishes. Instructions written as constraints are tests. The workbench turns each rule into something an agent can check at runtime and a reviewe…

Chat history is volatile. The repo is durable. The workbench stores agent state in versioned files so the next session, the next agent, and the next reviewer all read from the s…

Every session that starts cold pays a tax. The agent reads the same files, retries the same probes, and rediscovers the same paths. An init script pays the tax once and writes t…

The model does not know where the work ends. A scope contract is a per-task file that says where the work begins, where it ends, and how to roll back if it spills. The contract …

Agents that do not see real command output guess. A feedback runner captures stdout, stderr, exit code, and timing into a structured record the next turn can read. Then the agen…

The agent does not get to mark its own work as done. A verification gate reads the scope contract, the feedback log, the rule report, and the diff, and answers a single question…

The agent that wrote the code cannot grade it. A reviewer is a second loop with a different system prompt, a different goal, and read-only access to everything the builder produ…

The session is going to end. The work is not. The handoff packet is the artifact that turns "the agent worked for an hour" into "the next session is productive in the first minu…

Eleven lessons of surfaces are worth nothing if they do not survive contact with a real codebase. This lesson runs the same task twice on a small sample app: prompt-only versus …

The mini-track ends with a pack you drop into any repo. Eleven lessons of surfaces compressed into a directory you can `cp -r` and have an agent working reliably the next mornin…