Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:MDR67XGRrecord.jsonopen to challenge →
read the original abstract
This paper introduces rStar, a self-play mutual reasoning approach that significantly improves reasoning capabilities of small language models (SLMs) without fine-tuning or superior models. rStar decouples reasoning into a self-play mutual generation-discrimination process. First, a target SLM augments the Monte Carlo Tree Search (MCTS) with a rich set of human-like reasoning actions to construct higher quality reasoning trajectories. Next, another SLM, with capabilities similar to the target SLM, acts as a discriminator to verify each trajectory generated by the target SLM. The mutually agreed reasoning trajectories are considered mutual consistent, thus are more likely to be correct. Extensive experiments across five SLMs demonstrate rStar can effectively solve diverse reasoning problems, including GSM8K, GSM-Hard, MATH, SVAMP, and StrategyQA. Remarkably, rStar boosts GSM8K accuracy from 12.51% to 63.91% for LLaMA2-7B, from 36.46% to 81.88% for Mistral-7B, from 74.53% to 91.13% for LLaMA3-8B-Instruct. Code will be available at https://github.com/zhentingqi/rStar.
This paper has not been read by Pith yet.
Forward citations
Cited by 23 Pith papers
-
DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination
DICE formalizes multi-agent LLM coordination as discounted incomplete-information Markov games and introduces Heterogeneous Quantal Response Equilibrium (HQRE) to achieve unique stable equilibria with bounded regret, ...
-
DISA: Offline Importance Sampling for Distribution-Matching LLM-RL
DISA decouples partition function estimation using offline importance sampling for distribution-matching LLM-RL, matching or exceeding online baselines like FlowRL on math and code benchmarks while retaining more stra...
-
MetaPS: Adaptive Programmatic Strategy Selection for Market Agents
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
-
RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning
RASFT is an adaptive SFT method that strengthens or relaxes expert imitation per problem based on on-policy rollout solvability and adds clipped reference-policy ratio to limit drift, reporting better results than sta...
-
Self-Improving Small Object Grounding in LVLMs
Attention maps in LVLMs enable an IoU regressor (Pearson r > 0.67) and a training-free entropy-based selector that improves small-object localization by up to 19% on COCO and Objects365.
-
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
SPEX delivers 1.2-3x speedup on ToT algorithms via speculative path selection, dynamic budget allocation, and adaptive early termination, reaching up to 4.1x when combined with token-level speculative decoding.
-
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
SPEX accelerates Tree-of-Thought LLM reasoning 1.2-3x via speculative path selection, dynamic budget allocation across queries, and adaptive early termination, with up to 4.1x when combined with token speculative decoding.
-
APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation
APCD reduces LLM hallucinations by expanding decoding paths adaptively when entropy signals uncertainty and by contrasting divergent paths to control their interaction.
-
OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving
OmniDrive-R1 boosts VLM reasoning score from 51.77% to 80.35% and answer accuracy from 37.81% to 73.62% on DriveLMM-o1 via reinforcement-driven interleaved multi-modal chain-of-thought with annotation-free grounding.
-
Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs
A conditional scaling law fitted on over 200 models from 80M to 3B parameters identifies architectures that deliver up to 2.1% higher accuracy and 42% higher inference throughput than LLaMA-3.2 under the same training budget.
-
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
DeepSearch embeds MCTS into RLVR training with global frontier selection, entropy guidance, and adaptive replay to achieve 62.95% average accuracy on math reasoning benchmarks while using 5.7x fewer GPU hours than ext...
-
Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework
DRP decouples reasoning from perception in LMMs by using an LLM reasoner to query an LMM observer for visual details as needed, reducing visual grounding loss.
-
Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search
DITS replaces Q-value guidance in MCTS with influence scores for synthetic data synthesis in multi-agent LLM training, claiming better efficiency and performance on eight datasets.
-
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
MILES dynamically expands step-wise memory with learnable selection heads that rerank candidates and guide reasoning, improving LLM test-time performance under limited supervision.
-
Tree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design Patterns
Synthesizes existing Tree-of-Thoughts work into a unified taxonomy using classical heuristic search terminology and identifies design patterns across shallow and deep reasoning tasks.
-
APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation
APCD adaptively branches LLM decoding paths based on token entropy and contrasts divergent paths to improve factual accuracy while preserving efficiency.
-
Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
Introduces IBPO, a counterfactual credit assignment method that turns sparse terminal rewards into process-level advantage estimates for more stable LLM reasoning training.
-
SVSR: A Self-Verification and Self-Rectification Paradigm for Multimodal Reasoning
SVSR trains multimodal models to verify and correct their own reasoning using a preference dataset, supervised fine-tuning, and semi-online DPO with a teacher model.
-
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
APMPO boosts average Pass@1 scores on math reasoning benchmarks by 3 points over GRPO by using an adaptive power-mean policy objective and feedback-driven clipping bounds in RLVR training.
-
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
-
Search-Based Multi-Trajectory Refinement for Safe C-to-Rust Translation with Large Language Models
LAC2R uses MCTS to systematically explore multiple LLM refinement trajectories for C-to-Rust translation and reports superior safety and correctness on small-scale benchmarks.
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
-
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
A comprehensive reference book organizing existing techniques for agentic AI systems across LLM substrate, reasoning, agent design patterns, inter-agent coordination, and production deployment.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.