self-correction 开源项目推荐（131 个）

rohitg00 /pro-workflow

Claude Code 从你的纠正中学习：经过50+次会话积累的自我纠正记忆。上下文工程、并行工作树、代理团队，以及17项经过实战考验的技能。

1105216375-alt /resimind

Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.

codelion /ellora

使用 LoRA 增强 LLM

tsunghan-wu /SLD

🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)

IAAR-Shanghai /ICSFSurvey

Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.

Cranot /agi-in-md

Cognitive prisms for structural analysis — any domain, any model. 1000+ experiments, 58 prisms, 27 scan modes. The cheapest model + right prism beats the most expensive without one. Cross-architecture validated: Claude + Gemini converge on the same structural laws.

YangLing0818 /SuperCorrect-llm

[ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction

ryokamoi /llm-self-correction-papers

List of papers on Self-Correction of LLMs.

bobxwu /learning-from-rewards-llm-papers

A comrephensive collection of learning from rewards in the post-training and test-time scaling of LLMs, with a focus on both reward models and learning strategies across training, inference, and post-inference stages.

Tibsfox /gsd-skill-creator

为引导软件开发（GSD）引入了一个全面的基于代理的框架

morispi /CONSENT

可扩展长读自校正和装配抛光，支持多序列对齐

OSU-NLP-Group /llm-planning-eval

[ACL'24] Code and data of paper "When is Tree Search Useful for LLM Planning? It Depends on the Discriminator"

MraDonkey /DMAD

[ICLR 2025] Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate

BY571 /SCoRe

SCoRe: Training Language Models to Self-Correct via Reinforcement Learning

prakashkagitha /evolving-agent-harnesses

Evolving agent harnesses: a research program on how far N orchestrated calls of a small model can rival a frontier model. We evolve the harness (structure + prompts) with reflective optimizers + a verified-acceptance gate.

VityaVitalich /STASC

[ICLR 2025 SSI-FM] Self-Taught Self-Correction for Small Language Models

JieMaMagic /SAGE

SAGE: self-correcting autonomous research via Multi-Hypothesis Failure Attribution (MHFA). Diagnose many causes of a failed experiment, verify the most critical, and route the fix to the right level.

rohansx /reflect

Self-correction engine for AI coding agents - implements the Reflexion paper (Shinn et al., 2023) as a Rust MCP server. Turns failures into persistent, searchable lessons that prevent the same mistakes across sessions.

songxiaoshuai /progco

Official Implementation of "ProgCo: Program Helps Self-Correction of Large Language Models" (Accpeted at ACL2025 Main)

NellInc /sottovoce

Residual-stream confabulation detection and self-correction for language models.