Pith. sign in

REVIEW 39 cited by

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

arxiv 2203.14465 v2 pith:4RY3WEJC submitted 2022-03-28 cs.LG cs.AIcs.CL

STaR: Bootstrapping Reasoning With Reasoning

classification cs.LG cs.AIcs.CL
keywords modelrationalereasoningrationalesstaranswerslanguageanswer
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 39 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

    cs.CL 2022-01 accept novelty 9.0

    Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.

  2. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

    cs.CL 2023-10 conditional novelty 8.0

    DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.

  3. RL Post-Training Builds Compositional Reasoning Strategies

    cs.AI 2026-07 conditional novelty 7.0

    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.

  4. TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

    cs.LG 2026-06 unverdicted novelty 7.0

    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.

  5. A Verifiable Search Is Not a Learnable Chain-of-Thought

    cs.LG 2026-06 unverdicted novelty 7.0

    Verifiable search procedures cannot be learned as forward chain-of-thought by language models; they instead learn memorization, verification, or require precomputed catalogs.

  6. Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

    cs.CL 2026-06 unverdicted novelty 7.0

    ZPPO improves distillation to small vision-language models by using binary and negative candidate prompts plus a replay buffer for hard questions, outperforming standard distillation and GRPO on a 31-benchmark suite w...

  7. Alpha-RTL: Test-Time Training for RTL Hardware Optimization

    cs.LG 2026-06 unverdicted novelty 7.0

    TTT-RTL performs per-design test-time RL on an LLM policy with EDA-derived PPA rewards and an adaptive KL controller, reducing geometric-mean PPA product by 65.1% on RTLLM v2.0 and ADP by 59.4% on an industrial FPU unit.

  8. PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media

    cs.CL 2026-05 unverdicted novelty 7.0

    PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic onlin...

  9. Large Language Models are Zero-Shot Reasoners

    cs.CL 2022-05 accept novelty 7.0

    Adding the fixed prompt 'Let's think step by step' enables large language models to achieve substantial zero-shot gains on arithmetic, symbolic, and logical reasoning benchmarks without any task-specific examples.

  10. Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops

    cs.AI 2026-07 conditional novelty 6.0

    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...

  11. Answer Engineering: Local Trajectory Editing for Protocol-Constrained Decision Making in Large Language Models

    cs.AI 2026-06 unverdicted novelty 6.0

    Answer Engineering uses local trajectory editing during autoregressive generation to raise protocol compliance on a clinical SSNHL benchmark from 25.1% to 83.5% and balanced accuracy from 42.0% to 80.7%.

  12. RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

    cs.LG 2026-06 unverdicted novelty 6.0

    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...

  13. ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning

    cs.AI 2026-06 unverdicted novelty 6.0

    ThoughtFold applies introspective redundancy detection within correct CoT trajectories to create sub-trajectory spectra, then uses masked preference optimization to penalize redundant explorations, yielding 56% token ...

  14. Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection

    cs.AI 2026-06 unverdicted novelty 6.0

    Traj-Evolve combines non-parametric experience retrieval and multi-agent RL with a leave-one-out unification strategy to outperform baselines on lung cancer prediction from up to five years of multimodal EHRs, includi...

  15. Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

    cs.AI 2026-05 unverdicted novelty 6.0

    LRS trains a latent reward model on final-answer correctness to steer SAE states during inference, improving reasoning performance and implicitly encouraging better cognitive behaviors.

  16. Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation

    cs.AI 2026-05 unverdicted novelty 6.0

    Self-evolving LLM agents exhibit capability erosion under continual adaptation, which Capability-Preserving Evolution mitigates by raising retained simple-task performance from 41.8% to 52.8% in workflow evolution und...

  17. HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering

    cs.AI 2026-04 unverdicted novelty 6.0

    HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.

  18. SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning

    cs.CV 2025-10 unverdicted novelty 6.0

    SSL4RL reformulates self-supervised learning objectives into dense, verifiable reward signals for RL-based fine-tuning of vision-language models, yielding performance gains on reasoning benchmarks.

  19. Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models

    cs.CL 2025-09 unverdicted novelty 6.0

    PAS automates activation steering for LLMs using labeled data to improve behavior control on tasks like bias and alignment, with gains over ICL and SFT but limited effect on intelligence tasks.

  20. LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA

    cs.CV 2025-09 unverdicted novelty 6.0

    LaV-CoT introduces a multi-stage visual CoT pipeline and GRPO training with language-consistency rewards, delivering up to 9.5% accuracy gains on multilingual VQA benchmarks over similar-sized open models.

  21. Grounded Reinforcement Learning for Visual Reasoning

    cs.CV 2025-05 unverdicted novelty 6.0

    ViGoRL introduces visually grounded RL that anchors reasoning steps to image coordinates and uses multi-turn zooming to outperform standard RL and supervised baselines on spatial and GUI reasoning benchmarks.

  22. DataComp-LM: In search of the next generation of training sets for language models

    cs.LG 2024-06 unverdicted novelty 6.0

    DCLM-Baseline dataset lets a 7B model reach 64% 5-shot MMLU accuracy after 2.6T tokens, beating prior open-data models by 6.6 points on MMLU with 40% less compute.

  23. Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

    cs.CL 2023-05 conditional novelty 6.0

    Distilling step-by-step uses LLM-generated rationales as additional supervision in a multi-task framework so that 770M-parameter models outperform 540B-parameter models on NLP benchmarks with only 80% of the data.

  24. Solving math word problems with process- and outcome-based feedback

    cs.LG 2022-11 unverdicted novelty 6.0

    On GSM8K, outcome-based supervision achieves similar final-answer error rates to process-based with less labeling, but process-based or learned reward models are needed to reach 3.4% reasoning error among correct solutions.

  25. Large Language Models Are Human-Level Prompt Engineers

    cs.LG 2022-11 unverdicted novelty 6.0

    APE generates instruction candidates via LLM and selects the best by zero-shot performance of a second LLM, matching or beating human prompts on 19 of 24 NLP tasks.

  26. Large Language Models Can Self-Improve

    cs.CL 2022-10 unverdicted novelty 6.0

    A 540B-parameter LLM improves reasoning performance on GSM8K, DROP, OpenBookQA, and ANLI-A3 by fine-tuning on self-generated high-confidence CoT solutions from unlabeled data.

  27. Automatic Chain of Thought Prompting in Large Language Models

    cs.CL 2022-10 conditional novelty 6.0

    Auto-CoT automatically builds chain-of-thought demonstrations by sampling diverse questions and letting the LLM generate reasoning chains, matching manual CoT performance on ten reasoning tasks with GPT-3.

  28. Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

    cs.LG 2026-07 unverdicted novelty 5.0

    Neuron-OPSD uses neuron activations to guide data selection and teacher construction for annotation-free on-policy self-distillation in LLMs, claiming better in-domain results without harming cross-domain performance ...

  29. A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization

    cs.CL 2026-06 unverdicted novelty 5.0

    A single LLM rewrite of skill descriptions using false positive and negative cases matches manual optimization performance in production, with most other pipeline components adding little value.

  30. Predicate Importance Estimation and Decoupled Rationale-Score Distillation for Entity Alignment

    cs.CL 2026-06 unverdicted novelty 5.0

    PIE creates predicate-aware embeddings by weighting subjectless triples and DRSD distills LLM reasoning into an SLM while decoupling confidence from rationales to improve entity alignment and enable human-in-the-loop ...

  31. Teacher-Free Self-Training Amplifies but Does Not Compound: A Pass@$K$ Crossover on a Free-Verifier Domain

    cs.LG 2026-06 unverdicted novelty 5.0

    Self-training on verified outputs in a free-verifier DSL amplifies performance at pass@8 but does not expand reach, as the base model overtakes at pass@64 across trajectories.

  32. q0: Primitives for Hyper-Epoch Pretraining

    cs.LG 2026-06 unverdicted novelty 5.0

    q0 turns multi-epoch budgets into diverse model populations using three primitives that outperform single-model training and strong ensembles with fewer epochs on a 1.8B model.

  33. CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO

    cs.AI 2026-05 unverdicted novelty 5.0

    CAST adds non-privileged self-teacher scoring and bidirectional advantage flipping to GRPO so that zero-variance groups still produce verifier-signed token gradients.

  34. Automating Formal Verification with Reinforcement Learning and Recursive Inference

    cs.LG 2026-05 unverdicted novelty 5.0

    RLVR training raises verified Dafny pass rates from 9.7% to 31.1% on a filtered benchmark while a Lean proof scaffold lifts success from 46.2% to 69.2% on a pilot set and solves 7 of 42 prior unsolved tasks.

  35. Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information

    cs.AI 2026-05 unverdicted novelty 5.0

    JTS trains reasoning models via supervised warm-up and missing-premise RL to make an explicit answerability commitment that triggers early termination on unanswerable inputs, raising Abstention@Detection near saturation.

  36. Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning

    cs.CL 2026-04 unverdicted novelty 4.0

    EduQwen 32B models optimized via RL then SFT set new SOTA on the Cross-Domain Pedagogical Knowledge Benchmark and surpass Gemini-3 Pro.

  37. Token-Operations-Oriented Inference Optimization Techniques for Large Models

    cs.SE 2026-06 unverdicted novelty 3.0

    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.

  38. The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

    cs.AI 2026-06 unverdicted novelty 2.0

    A comprehensive reference book organizing existing techniques for agentic AI systems across LLM substrate, reasoning, agent design patterns, inter-agent coordination, and production deployment.

  39. Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

    cs.AI 2025-03 unverdicted novelty 2.0

    This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.