Deep Papers
Deep Papers
✓

CUGA Agent: From Benchmarks to Business Impact of IBM's Generalist Agent

00:23:04
Podcasts
RSS
Link
L'audio di questo episodio potrebbe essere danneggiato. How to fix it?

INFORMAZIONI SU QUESTO EPISODIO

We dive into the latest paper from a team of researchers at IBM: "From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production." We're excited to host several of the paper's authors, who walk us through the research and its implications. The paper reports IBM’s experience developing and piloting the Computer Using Generalist Agent (CUGA), which has been open-sourced for the community. CUGA adopts a hierarchical planner–executor architecture with strong analytical foundations, achieving state-of-the-art performance on AppWorld and WebArena. Beyond benchmarks, it was evaluated in a pilot within the Business-Process-Outsourcing talent acquisition domain, addressing enterprise requirements for scalability, auditability, safety, and governance. 

CUGA code: https://github.com/cuga-project/cuga-agent 

Paper: https://arxiv.org/abs/2510.23856

Learn more about AI observability and evaluation, join the Arize AI Slack community or get the latest on LinkedIn and X.

Affari
Tecnologia
Matematica
Scienza e medicina
Inglese
Stati Uniti
UsaAPIper recuperare questo episodio inJSON

CERCA TRA GLI EPISODI PASSATI

Cerca gli episodi passati di Deep Papers.
Incorpora questa barra di ricerca nel tuo sito web

ALTRI EPISODI IN QUESTO PODCAST

The Illusion of Thinking: What the Apple AI Paper Says About LLM Reasoning

The Illusion of Thinking: What the Apple AI Paper Says About LLM Reasoning

This week we discuss The Illusion of Thinking, a new paper from researchers at Apple that challenges today’s evaluation methods and introduces a new benchmark: synthetic puzzles with controllable complexity and clean logic.  Their findings? Large Reasoning Models (LRMs) show surprising failure mode…
00:30:35
CONDIVIDI
SALVA
Accurate KV Cache Quantization with Outlier Tokens Tracing

Accurate KV Cache Quantization with Outlier Tokens Tracing

We discuss Accurate KV Cache Quantization with Outlier Tokens Tracing, a deep dive into improving the efficiency of LLM inference. The authors enhance KV Cache quantization, a technique for reducing memory and compute costs during inference, by introducing a method to identify and exclude outlier t…
00:25:11
CONDIVIDI
SALVA
Self-Adapting Language Models: Paper Authors Discuss Implications

Self-Adapting Language Models: Paper Authors Discuss Implications

The authors of the new paper *Self-Adapting Language Models (SEAL)* shared a behind-the-scenes look at their work, motivations, results, and future directions. The paper introduces a novel method for enabling large language models (LLMs) to adapt their own weights using self-generated data and trai…
00:31:26
CONDIVIDI
SALVA
Scalable Chain of Thoughts via Elastic Reasoning

Scalable Chain of Thoughts via Elastic Reasoning

In this week's episode, we talk about Elastic Reasoning, a novel framework designed to enhance the efficiency and scalability of large reasoning models by explicitly separating the reasoning process into two distinct phases: thinking and solution.  This separation allows for independent alloca…
00:28:54
CONDIVIDI
SALVA
Sleep-time Compute: Beyond Inference Scaling at Test-time

Sleep-time Compute: Beyond Inference Scaling at Test-time

What if your LLM could think ahead—preparing answers before questions are even asked? In this week's paper read, we dive into a groundbreaking new paper from researchers at Letta, introducing sleep-time compute: a novel technique that lets models do their heavy lifting offline, well before the…
00:30:24
CONDIVIDI
SALVA
Dichiarazione di non responsabilità: Il podcast e la grafica incorporati in questa pagina provengono da Arize AI, che è di proprietà del suo proprietario e non è affiliato o approvato da Listen Notes, Inc.
PROMOTED
We’re selling some of our podcast-related domain names, including breaker.fm, Podcast.mov, and Listen.Host. Place your bid on eBay.
We’re selling some of our podcast-related domain names, including breaker.fm, Podcast.mov, and Listen.Host. Place your bid on eBay.
Bid on eBay

CONSIGLI
Utilizza l'API per recuperare questo episodio