Papers › AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning

AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning

25 Nov 2024arXiv:2411.16495archive 2025-07-28

Amy Xin, Jinxin Liu, Zijun Yao, Zhicheng Lee, Shulin Cao, Lei Hou, Juanzi Li

Recent advancements in large language models (LLMs) have led to significant improvements in various natural language processing tasks, but it is still challenging for LLMs to perform knowledge-intensive complex question answering due to LLMs' inefficacy in reasoning planning and the hallucination problem. A typical solution is to employ retrieval-augmented generation (RAG) coupled with chain-of-thought (CoT) reasoning, which decomposes complex questions into chain-like sub-questions and applies iterative RAG at each sub-question. However, prior works exhibit sub-optimal reasoning planning and overlook dynamic knowledge retrieval from heterogeneous sources. In this paper, we propose AtomR, a novel heterogeneous knowledge reasoning framework that conducts multi-source reasoning at the atomic level. Drawing inspiration from the graph modeling of knowledge, AtomR leverages large language models (LLMs) to decompose complex questions into combinations of three atomic knowledge operators, significantly enhancing the reasoning process at both the planning and execution stages. We also introduce BlendQA, a novel evaluation benchmark tailored to assess complex heterogeneous knowledge reasoning. Experiments show that AtomR significantly outperforms state-of-the-art baselines across three single-source and two multi-source reasoning benchmarks, with notable performance gains of 9.4% on 2WikiMultihop and 9.5% on BlendQA.

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="2411.16495")

Code

Syntology Ran 0 of 13 code samples harvested from 1 repository linked to this paper; 13 have no recorded run.

By repository: official repository: 13 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

THU-KEG/AtomR officialmentioned in papermentioned on GitHubpytorch 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

13 samples harvested; 0 ran; 0 honoured the contract we drafted; 13 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.

13unverified

Licence: 13 of the 13 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 THU-KEG/AtomR. “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.

calculate_em THU-KEG/AtomR/src/calculate_metrics.py official repository unverified no licence file found · pointer only · 195f8f58bad34ea5 · report
calculate_f1 THU-KEG/AtomR/src/calculate_metrics.py official repository unverified no licence file found · pointer only · 06bd0fab42352980 · report
extract_function_parameters THU-KEG/AtomR/src/utils.py official repository unverified no licence file found · pointer only · d8246404fe3d07ac · report
extract_json_tree THU-KEG/AtomR/src/utils.py official repository unverified no licence file found · pointer only · d416633bc4a27d59 · report
extract_ref_indices THU-KEG/AtomR/src/utils.py official repository unverified no licence file found · pointer only · fc0dde79121e724b · report
format_direct_answer_prompt_2wiki THU-KEG/AtomR/src/prompts/answer_formulation_prompts.py official repository unverified no licence file found · pointer only · 0e84913598fcef69 · report
format_direct_answer_prompt_hotpotqa THU-KEG/AtomR/src/prompts/answer_formulation_prompts.py official repository unverified no licence file found · pointer only · e3d56dc72fde480c · report
format_kb_retrieval_answers THU-KEG/AtomR/src/global_reasoner.py official repository unverified no licence file found · pointer only · 0c95c3f6f273a570 · report
format_knowledge_source_selection_prompt THU-KEG/AtomR/src/prompts/answer_formulation_prompts.py official repository unverified no licence file found · pointer only · c8789437204b7582 · report
format_text_retrieval_answers THU-KEG/AtomR/src/global_reasoner.py official repository unverified no licence file found · pointer only · cc1c3b57c07cc796 · report
format_web_retrieval_answers THU-KEG/AtomR/src/global_reasoner.py official repository unverified no licence file found · pointer only · d4c571e9d833c51e · report
normalize_answer THU-KEG/AtomR/src/calculate_metrics.py official repository unverified no licence file found · pointer only · 702b1281050dbc40 · report
overlap_coefficient THU-KEG/AtomR/src/knowledge_sources.py official repository unverified no licence file found · pointer only · c499bbf79b863287 · report

Tasks

HallucinationQuestion AnsweringRAGRetrievalRetrieval-augmented Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBARTBERTBPEDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionRAGResidual ConnectionSoftmaxWeight DecayWordPiece

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