REVIEW 14 cited by
BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory, and having been trained on a large number of user defined tasks. We release both the model weights and code, and have also deployed the model on a public web page to interact with organic users. This technical report describes how the model was built (architecture, model and training scheme), and details of its deployment, including safety mechanisms. Human evaluations show its superiority to existing open-domain dialogue agents, including its predecessors (Roller et al., 2021; Komeili et al., 2022). Finally, we detail our plan for continual learning using the data collected from deployment, which will also be publicly released. The goal of this research program is thus to enable the community to study ever-improving responsible agents that learn through interaction.
Forward citations
Cited by 14 Pith papers
-
Momentum Based Reward Design for Low Emission Traffic Signal Control
A progressive multi-turn text-to-vis agent with rule-guided ReAct validation beats one-shot baselines by large execution-accuracy margins on a new reverse-constructed benchmark.
-
How Stylistic Similarity Shapes Preferences in Dialogue Dataset with User and Third Party Evaluations
A new open-domain dialogue dataset shows that users' own judgments of stylistic similarity correlate with their preference (Spearman r=0.67-0.75), but third-party stylistic similarity judgments do not, indicating a ga...
-
Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems
An energy-based retriever that jointly scores sets of knowledge items improves retrieval accuracy and semi-supervised dialog performance over independently-scoring baselines.
-
Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning
Rule-based RL with a binary format-and-tool-match reward produces tool-calling LLMs that outperform GPT-4o on BFCL, API-Bank, and ACEBench, and can rival or beat SFT-then-RL under equal data budgets.
-
Dialogue Language Model with Large-Scale Persona Data Engineering
A T5-based persona extraction pipeline creates a 189M-session persona dialogue dataset, and pre-training a UniLM-style dialogue model on it improves persona consistency over strong baselines.
-
Agentic AI and Retrieval-Augmented Models in Straight-Through Underwriting
On 635 synthetic BOP applications, multi-agent Agentic RAG reaches 86.5% decision accuracy versus 77.6% single-LLM and 76.9% naive RAG, with largest gains on multi-step and missing-information cases.
-
Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations
With Python tool augmentation, DeepSeek-R1 and Qwen 3 Thinking outperform their non-thinking counterparts on River Crossing and Blocks World, but the advantage does not appear on Hanoi or Checker Jumping.
-
Exchange of Perspective Prompting Enhances Reasoning in Large Language Models
A two-branch prompting method that exchanges answers between an original math question and a paraphrased version improves accuracy on several math benchmarks, but the gain is not separated from the extra compute or ru...
-
Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidance
UPC uses LLM-judge feedback to generate better training dialogues and an easy-to-hard curriculum, improving user-oriented proactivity in open-domain chatbots.
-
Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems
A label taxonomy and answer-first generation strategies help RAG developers build evaluation datasets whose question mix matches real usage.
-
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
Autonomous AI becomes dependable when tool use is embedded in persistent workspaces with reusable skills, shifting evaluation from answers to task closure.
-
Embodied AI Agents: Modeling the World
Embodied AI agents should be built around physical world models plus a mental world model of the user, with virtual, wearable, and robotic agents sharing this core.
-
A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
A systematic review of retrieval-augmented generation that organizes progress by year and application but introduces no new measurements or results.
-
A Survey on Multi-Turn Interaction Capabilities of Large Language Models
A comprehensive review of how large language models are evaluated, trained, and improved for multi-turn interaction, organized into evaluation practices, core capabilities, and general algorithms.
Discussion (0). Continue with ORCID to comment.