SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
cs.AI
Submitted: 2026-09-24
Updated: 2026-09-24
Code: https://github.com/Susan571/SAGE-NeurIPS2026
Terminology
Sources
- Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
- Reinforced Self-Training (ReST) for Language Modeling
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
- Solving Quantitative Reasoning Problems with Language Models
- Let's Verify Step by Step
- Evaluating the Logical Reasoning Abilities of Large Reasoning Models
- Decoupled Weight Decay Regularization
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
- Training language models to follow instructions with human feedback
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- R-PRM: Reasoning-Driven Process Reward Modeling
- What makes math problems hard for reinforcement learning: a case study
- GRPO is Secretly a Process Reward Model
- Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection