---
type: "raw_signal"
id: "introducing-exa-agent-ultra-lists-without-limits-2611cf"
slug: "introducing-exa-agent-ultra-lists-without-limits-2611cf"
title: "Introducing Exa Agent Ultra – Lists without Limits"
description: "Exa announced Agent Ultra, a new highest-effort mode for its research agent aimed at exhaustive web research, list-building, and entity enrichment."
retrieval_nugget: "Exa announced Agent Ultra, a new highest-effort mode for its research agent aimed at exhaustive web research, list-building, and entity enrichment."
observed_at: "2026-09-24"
record_date: "2026-09-24"
date_kind: "observed_at"
why_it_matters: "Source: https://exa.ai/blog/exa-agent-ultra"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "exa.ai"
topics: []
entities: []
related_patterns: []
source_url: "https://exa.ai/blog/exa-agent-ultra"
source_urls: ["https://exa.ai/blog/exa-agent-ultra"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:introducing-exa-agent-ultra-lists-without-limits-2611cf"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/signals/introducing-exa-agent-ultra-lists-without-limits-2611cf/","markdown":"https://newruntime.com/signals/introducing-exa-agent-ultra-lists-without-limits-2611cf.md","json":"https://newruntime.com/signals/introducing-exa-agent-ultra-lists-without-limits-2611cf.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# Introducing Exa Agent Ultra – Lists without Limits

## Retrieval answer

Exa announced Agent Ultra, a new highest-effort mode for its research agent aimed at exhaustive web research, list-building, and entity enrichment.

Exa announced Agent Ultra, a new highest-effort mode for its research agent aimed at exhaustive web research, list-building, and entity enrichment. The company says the agent decomposes a task into subtasks, researches multiple domains in parallel, and uses a mix of frontier and cost-effective models.

In its launch post, Exa reports results across WANDR, WideSearch, DeepSearchQA, and its internal Find-All Company benchmark. It reports 81.4% soft recall on WANDR at a $18.53 median cost per task, 58.9% on WideSearch at $3.85 per task, and 229 successful rows per task on Find-All Company. The company also notes that some competitor figures were published results while others were run by Exa.

Source: https://exa.ai/blog/exa-agent-ultra

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)