Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents
cs.LG, cs.AI
Submitted: 2026-04-06
Updated: 2026-11-15
Terminology
Sources
- Concise Reasoning via Reinforcement Learning
- Hierarchical Reasoning Models: Perspectives and Misconceptions
- AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting
- ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers
- xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning
- Hierarchical Reasoning Model
- Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
- Budget-Aware Agentic Routing via Boundary-Guided Training
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis