Research map / Large language models / Agents, code and math
Simulation-Based Approach to Efficient Commonsense Reasoning in Very Large Knowledge Bases
Abhishek Sharma, Keith M. Goolsbey
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace Cyc default heuristic policy with MCTS-learned policy | Cyc inference engine · Experiment 1 | % queries answered: 46 -> 92 | Improved |
| replace Cyc default heuristic policy with MCTS-learned policy | Cyc inference engine · Experiment 1 | speedup: 7.1 | Improved |
| replace default policy with MCTS policy | Cyc inference engine · Experiment 2 | % queries answered: 66 -> 94 | Improved |
| replace default policy with MCTS policy | Cyc inference engine · Experiment 3 | % queries answered: 76 -> 94 | Improved |
| replace default policy with MCTS policy | Cyc inference engine · Experiment 4 | % queries answered: 82 -> 94 | Improved |
| replace default policy with MCTS policy | Cyc inference engine · Experiment 4 | speedup: 3.3 | Improved |
| use MCTS policy on easy queries (0-100 s in baseline) | Cyc inference engine · 597 easiest queries | speedup: 1.23 | No clear effect |
| larger exploration constant c = 1000 at ~100k simulations (ablation) | MCTS policy · Cyc queries | speedup / Q/A | Improved |
| increase number of simulations (ablation) | MCTS policy · Cyc queries | speedup / Q/A | No clear effect |
| use small to medium c (10 or 100) with more simulations (ablation) | MCTS policy · Cyc queries | speedup / Q/A | Improved |
Closest papers by meaning
- Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities (AAAI 2026 · similarity 0.87)
- Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization (ICML 2025 · similarity 0.87)
- Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens (NeurIPS 2025 · similarity 0.86)
- Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models (NeurIPS 2025 · similarity 0.86)
- Training Language Models to Reason Efficiently (NeurIPS 2025 · similarity 0.86)
- Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
