IONS: A reasoning graph that stores claims, evidence, and reasoning paths outside the LLM
Summary
IONS is an open-source approach to AI memory and reasoning that uses a graph of evidence-backed claims called Cognitive Building Blocks (CBBs) to store knowledge outside model weights, making reasoning inspectable.
Similar Articles
The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis
MIMIC is a framework that uses executable code to synthesize reasoning trajectories for LLMs, enhancing their deterministic reasoning through code-instrumented rewards and achieving improved performance on reasoning benchmarks.
REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs
REAL is a reasoning-enhanced graph framework for long-term memory management of LLMs that uses temporal and confidence-aware directed property graphs with non-destructive temporal updates and hybrid beam search retrieval, achieving an average improvement of 22.72%.
Structure-Internalized Rule Language Model for Faithful Knowledge Graph Reasoning
This paper proposes the Structure-Internalized Rule Language Model (SIRLM) to address reasoning evidence perception drift in knowledge graph reasoning with LLMs, improving faithfulness and effectiveness by coupling structural and parametric knowledge, with experiments showing superiority over state-of-the-art methods.
AIPO: : Learning to Reason from Active Interaction
This paper introduces AIPO, a reinforcement learning framework that enhances LLM reasoning by allowing the model to actively consult collaborative agents during exploration to overcome capability boundaries.
LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger
This paper introduces LedgerMind, a provenance-constrained multimodal agentic reasoning framework that uses a Structured Evidence Ledger to ensure grounded, faithful reasoning in visual question answering, addressing failure patterns like hallucination and over-reasoning.