Papers › THREAD: Thinking Deeper with Recursive Spawning

THREAD: Thinking Deeper with Recursive Spawning

27 May 2024arXiv:2405.17402archive 2025-07-28

Philip Schroeder, Nathaniel Morgan, Hongyin Luo, James Glass

Large language models (LLMs) have shown impressive capabilities across diverse settings, but still struggle as the length and complexity of the context increases. To address this challenge, we propose Thinking Recursively and Dynamically (ThReaD). THREAD frames model generation as a thread of execution that, based on the context, can run to completion or dynamically spawn new threads. By spawning, threads can offload work (e.g., thinking, retrieving information) to child threads, which only return tokens needed for the parent thread to do its work. In effect, this enables the model to adapt, as needed, the amount of intermediate work used to produce tokens. We apply THREAD in the settings of LLM task solving and question answering, where the dynamic threading allows the model to recursively decompose the given task or question into progressively simpler sub-problems that can be solved by separate child threads. We test THREAD, implemented using a few-shot learning approach, on diverse benchmarks for agent tasks and data-grounded question answering. THREAD achieves state-of-the-art performance with GPT-4 and GPT-3.5 on these benchmarks, including ALFWorld, TextCraft, and WebShop, along with two new benchmarks, DataCommons QA and MIMIC-III ICU QA. In addition, THREAD outperforms existing frameworks by 10% to 50% absolute points with smaller models, including Llama-3-8b and CodeLlama-7b.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.17402")

Code

Syntology Ran 7 of 11 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

philipmit/thread officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 7 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
6ran
4unverified

Licence: 11 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from philipmit/thread. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

check_answer philipmit/thread/datacommons_qa/run_datacommons_qa.py official repository ran fingerprinted no licence file found · pointer only · 069b0f9b21a6a04c · report
check_answer philipmit/thread/mimiciii_icu_qa/run_mimiciii_icuqa.py official repository ran fingerprinted no licence file found · pointer only · 1ef20761472016e0 · report
clean_str philipmit/thread/webshop/run_webshop.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 961911bec23c09ff · report
item_id_to_str philipmit/thread/textcraft/textcraft/utils.py official repository ran fingerprinted no licence file found · pointer only · 59d29c6276268221 · report
phi philipmit/thread/alfworld/run_alfworld.py official repository ran fingerprinted no licence file found · pointer only · 9eae20ece0fa12fe · report
phi philipmit/thread/mimiciii_icu_qa/run_mimiciii_icuqa.py official repository ran fingerprinted no licence file found · pointer only · 923f66a00de77f15 · report
psi philipmit/thread/alfworld/run_alfworld.py official repository ran fingerprinted no licence file found · pointer only · 142de1580a8559de · report
collect_data_commons philipmit/thread/datacommons_qa/build_datacommonsqa.py official repository unverified no licence file found · pointer only · f08c01dc55851d32 · report
collect_data_commons philipmit/thread/datacommons_qa/run_datacommons_qa.py official repository unverified no licence file found · pointer only · 9cbb7bfaa1ce61f3 · report
thread philipmit/thread/datacommons_qa/run_datacommons_qa.py official repository unverified no licence file found · pointer only · 30f614f80935dac8 · report
thread philipmit/thread/mimiciii_icu_qa/run_mimiciii_icuqa.py official repository unverified no licence file found · pointer only · 92df047c013d5b4e · report

Tasks

Few-Shot LearningQuestion Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3GPT-4Label SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections