GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning

arXiv:2608.25583 · cs.CL · Submitted 2026-08-26 · Read on arXiv

cs.CL

Submitted: 2026-08-26

Updated: 2026-08-26

Comments: 13 pages, 8 figures

Code: https://github.com/THUDM/slime

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 27× in this paper · explained in 1 episode
• Benchmark — 11× in this paper · explained in 2 episodes
• Model Merging — 11× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Reward Function — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• GRPO — 2× in this paper · explained in 6 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Granular Reward-guided Interpolation of Parameters — 2× in this paper
• Pruning — 2× in this paper · explained in 4 episodes
• Reasoning Traces — 2× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Transferability — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Training Language Models to Reason Efficiently
• Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
• Training Verifiers to Solve Math Word Problems
• The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
• Merge Now, Regret Later: The Hidden Cost of Model Merging is Adversarial Transferability
• Token-Budget-Aware LLM Reasoning
• ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
• Editing Models with Task Arithmetic
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
• CoT-Valve: Length-Compressible Chain-of-Thought Tuning
• DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
• Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging
• Revisiting Model Interpolation for Efficient Reasoning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
• Kimi k1.5: Scaling Reinforcement Learning with LLMs
• TokenSkip: Controllable Chain-of-Thought Compression in LLMs

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering