REVIEW 40 cited by
STaR: Bootstrapping Reasoning With Reasoning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Generating step-by-step "chain-of-thought" rationales improves language model performance on complex reasoning tasks like mathematics or commonsense question-answering. However, inducing language model rationale generation currently requires either constructing massive rationale datasets or sacrificing accuracy by using only few-shot inference. We propose a technique to iteratively leverage a small number of rationale examples and a large dataset without rationales, to bootstrap the ability to perform successively more complex reasoning. This technique, the "Self-Taught Reasoner" (STaR), relies on a simple loop: generate rationales to answer many questions, prompted with a few rationale examples; if the generated answers are wrong, try again to generate a rationale given the correct answer; fine-tune on all the rationales that ultimately yielded correct answers; repeat. We show that STaR significantly improves performance on multiple datasets compared to a model fine-tuned to directly predict final answers, and performs comparably to fine-tuning a 30$\times$ larger state-of-the-art language model on CommensenseQA. Thus, STaR lets a model improve itself by learning from its own generated reasoning.
Forward citations
Cited by 40 Pith papers
-
The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale
Across 0.8B-12B models plus a frontier arm, apparent self-correction effects are dominated by format-recovery and format-loss artifacts, with near-zero content-level change at capable scale.
-
RL Post-Training Builds Compositional Reasoning Strategies
RL post-training composes primitive rewrite skills into reusable macro and parallel contraction strategies that solve problems inaccessible to the base model under large sampling budgets.
-
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
TRIAGE augments GRPO with role-typed segment rewards derived from a judge that detects regression and exploration, yielding higher success rates and fewer turns on ALFWorld, Search-QA, and WebShop.
-
The Verifier is the Curriculum: Execution-Gated Self-Distillation for Cross-Family Game Generation
Strict-launch-gated rejection-sampling self-distillation compounds cross-family clean Godot generation from 8.8% to 42.2% and full best-of-K coverage, while gold duplication and a lenient BUILD filter erase the gain.
-
On-Policy Self-Distillation without Any Supervision
A model self-improves on math reasoning by majority-voting its own rollouts, using the winning answer as a pseudo-solution, and distilling itself on the disagreeing rollouts, without any labeled data.
-
Cybersecurity Detection Classification with Reasoning-enabled Language Models
CoT-trained triage plus a separate reasoning calibrator reaches 82.6% accuracy and large high-confidence recall gains over direct-label LLM classifiers on real SOC detections.
-
Search Hardness-Aware LLM-Based Problem Formulation for Expensive Simulation-Driven Design
SHA-PF uses initial simulation data to select a 'hard but promising' anchor satisfaction state and evolves LLM-generated formulations that prioritize it, reaching target designs with fewer expensive simulations on ant...
-
Cura 1T: Specialized Model for Agentic Healthcare
A healthcare LLM trained with an agent-driven loop that converts benchmark failures into new training data outperforms frontier baselines on most healthcare tests while staying competitive on general reasoning.
-
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to...
-
Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing
A bootstrapping algorithm that trains program synthesis models on their own successful outputs and on repaired failures modestly improves pass@k over regular fine-tuning on MBPP, with mixed results on APPS.
-
Intent Factored Generation: Unleashing the Diversity in Your Language Model
Intent Factored Generation samples a high-temperature intent, such as keywords or a summary, and then samples the final response at lower temperature conditioned on that intent, increasing semantic diversity while kee...
-
How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning
On three controlled tasks, the optimal number of backtracks in SFT warm-up data grows with task difficulty, while trajectory correctness has little effect on final RL performance.
-
Decomposing Elements of Problem Solving: What "Math" Does RL Teach?
Reinforcement learning (GRPO) on math LLMs primarily increases execution robustness on already-solvable problems, not planning or coverage of new problems.
-
REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing
REACT edits LLM facts by adding a learned belief-shift vector to hidden states only when a classifier decides the context is edit-relevant, reducing overfitting on EVOKE while keeping balanced editing metrics.
-
BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation
BARE generates diverse, high-quality synthetic training data from only three seed examples by having a base model draft and an instruction-tuned model refine, improving downstream fine-tuning accuracy in few-shot settings.
-
T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
A training pipeline called T1 scales RL for LLM reasoning via diverse sampling and rewards, and claims that longer allowed generations directly improve math accuracy without verifiers.
-
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
A fast flow-matching text-to-audio model aligned via CLAP-ranked self-generated preference pairs reports state-of-the-art AudioCaps and human-evaluation scores.
-
Refining Answer Distributions for Improved Large Language Model Reasoning
RAD iteratively refines a distribution over answers by marginalizing over refinement samples, improving accuracy on six arithmetic benchmarks over self-consistency and hint-based prompting.
-
HARP: A challenging human-annotated math reasoning benchmark
HARP, a new benchmark of 5,409 US math competition problems with human solutions and choices, keeps frontier LLMs far from saturation: the best model scores 75.9% overall and only 41.1% on the hardest 197 problems.
-
AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
AlphaVerus bootstraps a Llama-70B model to generate Rust code that passes the Verus verifier by iteratively translating Dafny programs and refining candidates with tree search.
-
Open Security Benchmark: Towards Autonomous Enterprise Cyber Defense
OSB proposes frozen synthetic-enterprise snapshots with gold posture answers so AI agents can be benchmarked on security investigation via SQL or native vendor APIs.
-
Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning
A T5-based sentence splitter trained on verbalized knowledge-graph triples extracts prefix–tail pairs from raw text, and the resulting structure-aware supervision raises few-shot CommonsenseQA and ATOMIC completion scores.
-
A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data
A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.
-
Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents
A game-theoretic framework converts global success/failure evaluations of multi-LLM agents into signed, credit-conserving per-message training signals.
-
Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
RL post-training forgets less than SFT because it trains on on-policy data; refreshing SFT data each epoch also reduces forgetting.
-
Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic
A vector computed as the weight difference between GRPO-trained and SFT-trained models, when added to a base model, transfers chain-of-thought reasoning improvements across benchmarks.
-
Hermes 4 Technical Report
Hermes 4 releases three open-weight reasoning models (14B, 70B, 405B) trained with synthetic data and a length-control SFT stage, evaluated on mathematics, code, knowledge, and alignment benchmarks.
-
EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making
EvoCurr couples an LLM curriculum designer with an LLM code-generating solver, but its only reported success is 1 of 5 runs and no direct baseline is shown.
-
Pheromone-based Learning of Optimal Reasoning Paths
An ant-colony-optimization-guided tree-of-thought method with multiple fine-tuned LLM experts reports accuracy gains on GSM8K, ARC-Challenge, and MATH over CoT, ToT, and IRPO baselines.
-
In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR
Graph-PReFLexOR trains a small LLM to construct knowledge graphs and symbolic abstractions during reasoning, with demonstrations in materials design and creative tasks but only qualitative, self-referential evaluation.
-
Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers
GIN-style graph aggregation inside Transformer attention and during fine-tuning improves validation perplexity and generalization compared with standard attention and LoRA in the tested settings.
-
Compute-Accuracy Pareto Frontiers for Open-Source Reasoning Large Language Models
Across five reasoning benchmarks, sparse MoE models dominate the accuracy-vs-FLOPs Pareto frontier, inference-compute gains saturate, and wrong answers systematically consume more compute than correct ones.
-
AI Reasoning for Wireless Communications and Networking: A Survey and Perspectives
A survey that organizes LLM and AI reasoning methods into a taxonomy and maps them onto the physical, link, network, transport, and application layers of wireless networks.
-
ReasonBridge: Efficient Reasoning Transfer from Closed to Open-Source Language Models
ReasonBridge distills 1,000 curated reasoning traces from a closed model into open-source models via hierarchical adapters and guided inference, claiming up to 23% benchmark gains.
-
Enhancing Generalization in Chain of Thought Reasoning for Smaller Models
PRADA combines P-Tuning and domain-adversarial training with CoT distillation and claims improved cross-domain reasoning in small models, though the evaluation is confounded by target-data access.
-
The Race to Efficiency: A New Perspective on AI Scaling Laws
A simple formula generalizes static AI scaling laws to time-varying efficiency, showing that efficiency-doubling rates around 2 per year keep loss reduction on a near-exponential path.
-
SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs
Higher learning-rate-to-batch-size ratios improve reasoning-task performance in small language models, and the resulting SmolTulu-1.7B reports top sub-2B scores on IFEval and GSM8K.
-
Token-Operations-Oriented Inference Optimization Techniques for Large Models
The paper introduces a four-layer technical architecture for token-operations-oriented inference optimization in large models and reviews key technologies and industry status at each layer.
-
Industrial brain: a human-like autonomous neuro-symbolic cognitive decision-making system
The paper presents an 'industrial brain' framework for supply-chain resilience prediction, but the reported improvements are not supported by the paper's own inconsistent tables and missing baselines.
-
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
A survey-style reference book mapping the full agentic-AI stack from transformer internals to production deployment, with no new research result.
Discussion (0). Continue with ORCID to comment.