Compositional Neuro-Symbolic Reasoning

Researchers propose a neuro-symbolic architecture that combines neural priors with symbolic filtering to significantly improve AI performance on the Abstraction and Reasoning Corpus (ARC). The system improves LLM reasoning capabilities from 16% to 30.8% without task-specific finetuning.

Computer Science > Artificial Intelligence

Title:Compositional Neuro-Symbolic Reasoning

Abstract:We study structured abstraction-based reasoning for the Abstraction and Reasoning Corpus (ARC) and compare its generalization to test-time approaches. Purely neural architectures lack reliable combinatorial generalization, while strictly symbolic systems struggle with perceptual grounding. We therefore propose a neuro-symbolic architecture that extracts object-level structure from grids, uses neural priors to propose candidate transformations from a fixed domain-specific language (DSL) of atomic patterns, and filters hypotheses using cross-example consistency. Instantiated as a compositional reasoning framework based on unit patterns inspired by human visual abstraction, the system augments large language models (LLMs) with object representations and transformation proposals. On ARC-AGI-2, it improves base LLM performance from 16% to 24.4% on the public evaluation set, and to 30.8% when combined with ARC Lang Solver via a meta-classifier. These results demonstrate that separating perception, neural-guided transformation proposal, and symbolic consistency filtering improves generalization without task-specific finetuning or reinforcement learning, while reducing reliance on brute-force search and sampling-based test-time scaling. We open-source the ARC-AGI-2 Reasoner code.

Source: arXiv cs.AI Recent

More in this category

agentic-systems

VAMPS: Visual-Assisted Mathematical Problem Solving Benchmark

Researchers have introduced VAMPS, a new benchmark designed to evaluate how multimodal large language models leverage visualization tools for mathematical reasoning. The study reveals a surprising gap, showing that models still perform better with direct analytical solving than with tool-enabled visual plotting.

agentic-systems

StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis

Researchers have introduced StepPRM-RTL, a novel framework combining process-reward modeling (PRM) and Monte Carlo Tree Search (MCTS) to enhance LLM-based RTL code generation. The method improves functional correctness and reasoning fidelity by over 10%, setting a new standard for hardware design automation.

NOW LET US Related – The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents

agentic-systems

The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents

A new study reveals critical flaws in timing interventions on autonomous AI agents, showing that both affect-based triggers and LLM judges fail due to the 'saturation trap' and highly subjective human standards.

EXPLORE TOPICS