Skip to content
GenAI BR
Trails

Understand agents in six readings

From the 2022 think-act-observe loop to the benchmark showing where 2026 agents still fail. In order, each reading prepares the next.

6 readings
  1. Reading 1 of 6

    ReAct: interleaving reasoning and action is what made the first language agents work

    If you are going to build an agent, this is the conceptual starting point: the think-act-observe loop.

    Agentsintroductorytechnical, beginnerpaper · Princeton / Google Brain · ICLR 2023 · 06 Oct 2022
  2. Reading 2 of 6

    Workflows are not agents: the distinction that prevents most failed agent projects

    It is the vocabulary product and engineering teams need to share before discussing “putting an agent” on anything.

    Agentsintroductorytechnical, decision-makerpost · Anthropic · 19 Dec 2024
  3. Reading 3 of 6

    MCP became the tool standard for agents — and since December 2025 it no longer belongs to Anthropic

    Anyone building agent integrations today builds on MCP; knowing who governs the standard is knowing who your integration depends on.

    Agentstechnicaltechnicalcode · Agentic AI Foundation · 28 Jul 2026
  4. Reading 4 of 6

    SWE-bench: the coding benchmark that went from 2% to 97% in three years — and what that says about benchmarks

    It is the number every launch cites; knowing how it is measured is the difference between reading an announcement and understanding it.

    Evaluationtechnicaltechnicalpaper · Princeton / UChicago · ICLR 2024 · 10 Oct 2023
  5. Reading 5 of 6

    Terminal-Bench: 89 hand-verified terminal tasks, and the benchmark that replaced SWE-bench in launch decks

    It is the benchmark that currently discriminates between frontier models on agentic work — and what will appear in the next headlines.

    Evaluationtechnicaltechnicalpaper · Laude Institute / Stanford · 17 Jan 2026
  6. Reading 6 of 6

    On real scientific software, the best coding agent solves fewer than half the bugs

    It quantifies the gap between saturated leaderboards and real domain-heavy engineering — exactly where engineers will be asked to deploy agents next.

    Evaluationtechnicaltechnicalpaper · Universidade Fudan · 01 Sept 2026

Get the next Cinco

Tuesday, 7am BRT, in your inbox. Five items, with sources. No daily newsletter, no promotions, and unsubscribing is one click.

Just the e-mail. No third-party trackers on this page. Privacy policy.