Papers › Symbolic Working Memory Enhances Language Models for Complex Rule Application

Symbolic Working Memory Enhances Language Models for Complex Rule Application

24 Aug 2024arXiv:2408.13654archive 2025-07-28

Siyuan Wang, Zhongyu Wei, Yejin Choi, Xiang Ren

Large Language Models (LLMs) have shown remarkable reasoning performance but struggle with multi-step deductive reasoning involving a series of rule application steps, especially when rules are presented non-sequentially. Our preliminary analysis shows that while LLMs excel in single-step rule application, their performance drops significantly in multi-step scenarios due to the challenge in rule grounding. It requires anchoring the applicable rule and supporting facts at each step, amidst multiple input rules, facts, and inferred facts. To address this, we propose augmenting LLMs with external working memory and introduce a neurosymbolic framework for rule application. The memory stores facts and rules in both natural language and symbolic forms, enabling precise tracking. Utilizing this memory, our framework iteratively performs symbolic rule grounding and LLM-based rule implementation. The former matches predicates and variables of symbolic rules and facts to ground applicable rules at each step. Experiments indicate our framework's effectiveness in rule application and its robustness across various steps and settings~\footnote{Code and data are available at \url{https://github.com/SiyuanWangw/RuleApplication}.}.

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="2408.13654")

Code

Syntology Ran 11 of 13 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 11 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

siyuanwangw/ruleapplication officialmentioned in papermentioned on GitHub 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; 11 ran; 0 honoured the contract we drafted; 2 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.

11ran
2unverified

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 siyuanwangw/ruleapplication. “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.

dispatch_openai_chat_requests siyuanwangw/ruleapplication/Src/models/openai_models.py official repository ran no licence file found · pointer only · 4e1c4ff342f96bc9 · report
dispatch_openai_prompt_requests siyuanwangw/ruleapplication/Src/models/openai_models.py official repository ran no licence file found · pointer only · 94928eafb9afc8c7 · report
find_individual siyuanwangw/ruleapplication/Src/evaluation_utils.py official repository ran fingerprinted no licence file found · pointer only · 76bc3e42fa9a54a8 · report
load_prompt_fact_init siyuanwangw/ruleapplication/Src/utils.py official repository ran no licence file found · pointer only · 83acc70202392615 · report
load_prompt_final_predict siyuanwangw/ruleapplication/Src/final_predict.py official repository ran no licence file found · pointer only · e19b01a83156528a · report
load_prompt_rule_implementation siyuanwangw/ruleapplication/Src/utils.py official repository ran no licence file found · pointer only · 6f2aab0105d6de70 · report
load_raw_dataset siyuanwangw/ruleapplication/Src/evaluate.py official repository ran no licence file found · pointer only · d8e076b666a81e08 · report
parse_answer siyuanwangw/ruleapplication/Src/evaluation_utils.py official repository ran no licence file found · pointer only · 1675e6f35d4f8ba4 · report
post_process_fact siyuanwangw/ruleapplication/Src/response_postprocess.py official repository ran no licence file found · pointer only · 7c03c8915ba5c271 · report
post_process_implement siyuanwangw/ruleapplication/Src/response_postprocess.py official repository ran no licence file found · pointer only · 11e3e3ef0f5ff617 · report
post_process_rule siyuanwangw/ruleapplication/Src/response_postprocess.py official repository ran no licence file found · pointer only · 29bba7fd8c210dad · report
evaluate_performance siyuanwangw/ruleapplication/Src/evaluate.py official repository unverified no licence file found · pointer only · bf4cfef1d50731f1 · report
load_prompt_rule_init siyuanwangw/ruleapplication/Src/utils.py official repository unverified no licence file found · pointer only · f6f5e08416631644 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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