A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation Paper • 2601.09274 • Published Jan 14 • 84
Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs Paper • 2505.15210 • Published May 21, 2025 • 19
φ-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation Paper • 2503.13288 • Published Mar 17, 2025 • 51
