KG-Hopper uses RL to embed full multi-hop KG traversal and backtracking into a single LLM inference round, enabling a 7B model to outperform larger multi-step systems and compete with GPT-3.5/GPT-4o-mini on eight benchmarks.
Math-shepherd: Verify and reinforce llms step-by-step without human annotations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
VERGSA trains a process reward model on MCTS-labeled subtask outcomes and uses it to select scene configurations and subtask supervisions, improving simulated task success rates.
Proposes a three-layer framework using formal AI reasoning for verification, derivation, and discovery in wireless communications theory.
citing papers explorer
-
KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning
KG-Hopper uses RL to embed full multi-hop KG traversal and backtracking into a single LLM inference round, enabling a 7B model to outperform larger multi-step systems and compete with GPT-3.5/GPT-4o-mini on eight benchmarks.
-
Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition
VERGSA trains a process reward model on MCTS-labeled subtask outcomes and uses it to select scene configurations and subtask supervisions, improving simulated task success rates.
-
Rethinking Wireless Communications through Formal Mathematical AI Reasoning
Proposes a three-layer framework using formal AI reasoning for verification, derivation, and discovery in wireless communications theory.