Challenge: Large Language Models (LLMs) excel in single-step rule application but struggle with multi-step deductive reasoning when rules are presented non-sequentially.
Approach: They propose to augment LLMs with external working memory and introduce a neurosymbolic framework for rule application that stores facts and rules in both natural language and symbolic forms, enabling precise tracking.
Outcome: The proposed framework iteratively performs symbolic rule grounding and LLM-based rule implementation.

Similar Papers

Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language.
Approach: They propose a model that integrates symbolic data into LLM training without loss of generality ability.
Outcome: The proposed model performs better on symbol- and NL-centric tasks.
Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive human-like performance across various reasoning tasks, but their mastery of underlying inferential rules falls short of human capabilities.
Approach: They propose a logic scaffolding inferential rule generation framework to construct an infer- ential rule base, ULogic, comprising both primitive and compositional rules across five domains.
Outcome: The proposed model improves the ability to generate accurate, complex and abstract conclusions and premises and improves various commonsense reasoning tasks.
RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) struggle to use tools reliably in domain-specific settings.
Approach: They propose a neuro-symbolic approach to adapt large language models to task-specific tools . they propose reusable rules that are distilled from failure traces and injected into the prompt .
Outcome: Experiments show that the proposed approach outperforms prompting-based adaptation methods and complements finetuning.
Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series? (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) and Multimodal LLMs (MLLMs) show strong performance in complex reasoning tasks, but their ability to extract symbolic laws from time series data remains underexplored.
Approach: They propose a benchmark to assess symbolic reasoning over real-world time series across three tasks: multivariate symbolic regression, Boolean network inference, and causal discovery.
Outcome: The proposed framework integrates LLMs with genetic programming to form a closed-loop symbolic reasoning system.
Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) face challenges in reliably solving reasoning tasks, especially when solving tasks that require strict rule following.
Approach: They propose a method that encodes hidden states into neurosymbolic vectors and decodes them into a neurosample vector space to enable problem-solving within a neural space.
Outcome: The proposed method shows an average of 88.6% lower cross-entropy loss and 15.4 times more problems correctly solved on a suite of mathematical reasoning tasks compared to chain-of-thought prompting and supervised fine-tuning (LoRA).
Working Memory Identifies Reasoning Limits in Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Using large language models, we examine the limitations of their cognitive capabilities and their working memory.
Approach: They examine the limitations of large language models from a scaling perspective . they also assess various prompting strategies, revealing their diverse impacts on LLM performance.
Outcome: The proposed models perform poorly on n-back tasks and on prompting strategies.
Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling (2026.findings-acl)

Copied to clipboard

Challenge: Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear.
Approach: They evaluate how large language models learn multi-step reasoning without memorization . they find that most neural architectures trained from scratch can learn rule inference .
Outcome: The proposed framework fails to solve a natural-language proxy task with high accuracy.
Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition (2026.eacl-long)

Copied to clipboard

Challenge: Existing approaches to NLP are static and require manual formalization.
Approach: They propose an adaptive, multi-paradigm, neuro-symbolic inference framework that automatically identifies formal reasoning strategies from problems expressed in natural language and dynamically selects and applies specialized formal logical solvers.
Outcome: The proposed framework outperforms baselines on individual and multi-paradigm reasoning tasks by 17% and 6%.
In-Context Symbolic Regression: Leveraging Large Language Models for Function Discovery (2024.acl-srw)

Copied to clipboard

Challenge: State of the art Symbolic Regression (SR) methods build specialized models, while the application of Large Language Models (LLMs) remains largely unexplored.
Approach: They propose a framework which iteratively refines a functional form with an LLM and determines its coefficients with an external optimizer.
Outcome: The proposed method outperforms the best SR methods on four popular benchmarks while yielding simpler equations with better out of distribution generalization.
From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models excel at solving individual problems in isolation, but are they able to effectively collaborate over long-term interactions?
Approach: They propose to use a multi-session dataset to test LLMs' ability to track and execute simple coding instructions amid irrelevant information, simulating a realistic setting.
Outcome: The proposed model performs poorly when instructions are spread across sessions, suggesting that they are not able to integrate information over long interactions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations