Pith. sign in

REVIEW 8 cited by

RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2305.13304 v1 pith:NE6SQSZA submitted 2023-05-22 cs.CL cs.LG

Wangchunshu Zhou , Yuchen Eleanor Jiang , Peng Cui , Tiannan Wang , Zhenxin Xiao , Yifan Hou , Ryan Cotterell , Mrinmaya Sachan This is my paper · ORCID
classification cs.CLcs.LG
keywords recurrentgptinteractivelongtextlanguagemechanismaigcarbitrarily
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The fixed-size context of Transformer makes GPT models incapable of generating arbitrarily long text. In this paper, we introduce RecurrentGPT, a language-based simulacrum of the recurrence mechanism in RNNs. RecurrentGPT is built upon a large language model (LLM) such as ChatGPT and uses natural language to simulate the Long Short-Term Memory mechanism in an LSTM. At each timestep, RecurrentGPT generates a paragraph of text and updates its language-based long-short term memory stored on the hard drive and the prompt, respectively. This recurrence mechanism enables RecurrentGPT to generate texts of arbitrary length without forgetting. Since human users can easily observe and edit the natural language memories, RecurrentGPT is interpretable and enables interactive generation of long text. RecurrentGPT is an initial step towards next-generation computer-assisted writing systems beyond local editing suggestions. In addition to producing AI-generated content (AIGC), we also demonstrate the possibility of using RecurrentGPT as an interactive fiction that directly interacts with consumers. We call this usage of generative models by ``AI As Contents'' (AIAC), which we believe is the next form of conventional AIGC. We further demonstrate the possibility of using RecurrentGPT to create personalized interactive fiction that directly interacts with readers instead of interacting with writers. More broadly, RecurrentGPT demonstrates the utility of borrowing ideas from popular model designs in cognitive science and deep learning for prompting LLMs. Our code is available at https://github.com/aiwaves-cn/RecurrentGPT and an online demo is available at https://www.aiwaves.org/recurrentgpt.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 10 citations worldwide. Full citation record

  1. From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents

    cs.CL 2026-07 conditional novelty 6.0 of 10

    MSCE, a training-free memory–skill co-evolution framework, converts grounded traces into callable skills through reflection-weighted value backfilling and outperforms prior agent memory/skill baselines on EvoAgentBenc...

  2. Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness

    cs.AI 2026-06 unverdicted novelty 6.0 of 10

    Xcientist is a research harness that externalizes an AI scientist's literature grounding, idea evolution, experiments, and repairs into auditable artifacts, demonstrated on memory, traffic forecasting, and PDE-solving tasks.

  3. DTBench: A Synthetic Benchmark for Document-to-Table Extraction

    cs.DB 2026-02 conditional novelty 6.0 of 10

    A new synthetic benchmark shows LLMs doing document-to-table extraction are far weaker on indirect cells requiring reasoning, faithfulness, or conflict resolution than on direct text copying.

  4. TaskCraft: Automated Generation of Agentic Tasks

    cs.CL 2025-06 conditional novelty 6.0 of 10

    TaskCraft automatically generates verifiable, multi-tool agentic tasks with execution trajectories via atomic task construction and depth/width extension, and fine-tuning on the resulting 36,000-task dataset improves ...

  5. Writing Like the Best: Exemplar-Based Expository Text Generation

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Exemplar-based expository generation: a recurrent plan-then-adapt LLM framework converts a source topic's exemplar into target-topic text by question transfer, retrieval, and confidence-gated answering.

  6. OAgents: An Empirical Study of Building Effective Agents

    cs.AI 2025-06 reject novelty 5.0 of 10

    OAgents reports a framework and ablation study claiming open-source state-of-the-art on GAIA, but the empirical evidence is weakened by benchmark fitting and missing statistics.

  7. Scaling Test-time Compute for LLM Agents

    cs.AI 2025-06 conditional novelty 5.0 of 10

    On the GAIA benchmark, Best-of-N sampling with list-wise answer selection gives the largest agent gains, and selective (score-triggered) reflection beats reflection at every step.

  8. MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models

    cs.CL 2025-05 conditional novelty 5.0 of 10

    MiniLongBench, a 237-sample compression of LongBench, is claimed to reproduce model rankings with a 0.97 Spearman correlation at 4.5% of the evaluation cost.

Pith tools