Pith. sign in

REVIEW 16 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

arxiv 2208.03188 v3 pith:2VZRFUUD submitted 2022-08-05 cs.CL cs.AI

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

classification cs.CL cs.AI
keywords modelagentsblenderbotdeployeddeploymentdialogueincludingopen-domain
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Evaluating Very Long-Term Conversational Memory of LLM Agents

    cs.CL 2024-02 unverdicted novelty 8.0

    Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.

  2. GAIA: a benchmark for General AI Assistants

    cs.CL 2023-11 unverdicted novelty 7.0

    GAIA benchmark shows humans at 92% accuracy on simple real-world questions far outperform current AI systems at 15%, proposing this gap as a key milestone for general AI.

  3. Momentum Based Reward Design for Low Emission Traffic Signal Control

    cs.LG 2026-05 conditional novelty 6.0

    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.

  4. Towards Reliable Agentic Progressive Text-to-Visualization with Verification Rules

    cs.DB 2026-05 unverdicted novelty 6.0

    PMVisAgent uses multi-turn progressive interactions and a validation agent with ReAct-style verification to achieve up to 23.21% higher execution accuracy on the new PMVisBench dataset for text-to-vis tasks.

  5. Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI

    cs.CR 2025-07 unverdicted novelty 6.0

    Optimus mitigates toxicity during LLM fine-tuning by combining repurposed LLM safety alignments for detection with synthetic data and DPO alignment, remaining effective even with highly biased classifiers and against attacks.

  6. Chain-of-Verification Reduces Hallucination in Large Language Models

    cs.CL 2023-09 unverdicted novelty 6.0

    Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.

  7. Gorilla: Large Language Model Connected with Massive APIs

    cs.CL 2023-05 conditional novelty 6.0

    Gorilla is a fine-tuned LLM that surpasses GPT-4 in accurate API call generation and uses retrieval to handle documentation updates.

  8. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

    cs.AI 2023-03 conditional novelty 6.0

    CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.

  9. Agentic AI and Retrieval-Augmented Models in Straight-Through Underwriting

    cs.AI 2026-07 conditional novelty 5.0

    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.

  10. WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversational AI

    cs.HC 2026-05 unverdicted novelty 5.0

    WhiteTesseract deploys XR-based diminished reality and LLM dialogue in a Monet exhibition, raising average viewing time from 35.3 to 98.3 seconds and shifting 60% of 529 interactions toward analytical and emotional queries.

  11. DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation

    cs.CL 2026-05 unverdicted novelty 5.0

    DebiasRAG uses a three-stage RAG process to generate and rerank query-specific debiasing contexts that act as fairness constraints for LLM outputs.

  12. From 'Here' to 'There': Exploring Proximity Semantics in Multimodal Data Exploration

    cs.HC 2026-05 unverdicted novelty 5.0

    A user study with 20 participants shows that closeness between sketches, annotations, and language in a shared space helps disambiguate multimodal queries, leading to the concept of proximity semantics for data explor...

  13. Retrieval-Augmented Generation for AI-Generated Content: A Survey

    cs.CV 2024-02 accept novelty 5.0

    A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.

  14. Real-Time Language Model Jamming: A Case Study for Live Music Accompaniment Generation

    cs.SD 2026-06 unverdicted novelty 4.0

    StreamMUSE performs frame-synchronous streaming inference for language models by having a client send high-frequency requests and a server return outputs aligned to an external clock, shown on live music accompaniment...

  15. Momentum Based Reward Design for Low Emission Traffic Signal Control

    cs.LG 2026-05 unverdicted novelty 4.0

    A momentum-based reward for DRL traffic signal control yields better throughput-emission trade-offs and more stable learning than delay or queue rewards in SUMO simulations.

  16. WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversational AI

    cs.HC 2026-05 unverdicted novelty 3.0

    WhiteTesseract integrates XR diminished reality and LLM dialogue to increase viewing duration and interaction depth in physical cultural heritage exhibitions, shown in a 26-participant Monet exhibition study with stat...