ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition
cs.AI
Submitted: 2026-01-07
Updated: 2026-10-13
Terminology
Sources
- Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning
- Training Verifiers to Solve Math Word Problems
- Agentic Reinforced Policy Optimization
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
- GPT-4o System Card
- Steering LLM Thinking with Budget Guidance
- Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- Understanding R1-Zero-Like Training: A Critical Perspective
- Contrastive Losses and Solution Caching for Predict-and-Optimize
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization
- Qwen2.5 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
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
- Agents' Last Exam
- 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