Tagged articles
Self-Correction
17 articles · Page 1 of 1
Researchers from NTU, SJTU, and UTokyo propose UMM-Reflection, enabling unified multimodal models to self-correct generated images through native reflection and reinforcement learning, achieving 64.9% repair success (up from 20.6%) and GenEval 0.84 (from 0.72) without external verifiers at inference.
BAGELGenEvalImage Generation
0 likes · 19 min read

Alibaba's 1683 shares its production-grade Agent evaluation framework combining offline golden sets with online log sampling, using Task×Trial×Trace×Outcome decomposition, executable Rubrics with deterministic gates, LLM Judges constrained by evidence citations and rule-based scoring, and a closed loop that routes failures to targeted fixes and regression testing.
AI AgentAgent EvaluationDual-Track Evaluation
0 likes · 20 min read

This paper introduces GRC, a generation-reflection-correction framework for generative recommendation that enables models to self-diagnose and correct full draft semantic ID sequences via structured reflection labels, GRPO reinforcement learning, and entropy-guided scheduling, achieving state-of-the-art results on public and industrial datasets with minimal latency overhead.
CIKM 2026GRPOReflection
0 likes · 12 min read

AgentVLN introduces a VLM-as-Brain architecture for vision-language navigation, using cross-space representation mapping to translate 3D paths into 2D visual prompts, context-driven self-correction for error recovery, and query-driven perceptual chain-of-thought for active information gathering, achieving state-of-the-art results on R2R-CE and RxR-CE benchmarks with a 3B model deployable on Jetson edge devices.
AgentVLNCross-Space Representation MappingECCV 2026
0 likes · 10 min read

The article examines how Xiaohongshu’s large‑language model dots‑note‑3.0 achieved a flawless 42‑point score at IMO 2026 by repeatedly generating, verifying, and refining natural‑language proofs, and discusses how this recursive self‑criticism signals a shift toward agents that can audit and improve their own reasoning for complex, real‑world problems.
AIIMOSelf-Correction
0 likes · 10 min read

Lance Martin explains that the next stage of agent engineering shifts focus from clever prompts to designing self‑correction loops and cross‑session memory, using Claude Fable 5’s parameter‑golf experiment and continual‑learning benchmarks to show how robust loops turn powerful models into trustworthy work systems.
AIAgent EngineeringClaude Fable 5
0 likes · 17 min read

FusionRoute introduces a token‑level routing framework that dynamically selects the most suitable expert LLM for each token and adds a complementary generation step, enabling fine‑grained, stable multi‑model collaboration that outperforms existing sequence‑level and expert‑selection methods across diverse benchmarks.
AI researchSelf-Correctionexpert routing
0 likes · 11 min read

This article explains why Claude repeatedly makes the same coding errors, introduces a CLAUDE.md rule file and a series of hooks (PostToolUse, PreToolUse, Stop) plus an automatic retry loop and cross‑session memory, and shows a before‑after comparison that reduces manual debugging from 45 minutes to about 10 minutes per feature.
AIClaudeConfiguration
0 likes · 11 min read

The CPL++ framework equips weakly supervised visual grounding models with confidence‑aware pseudo‑label learning, self‑supervised association correction, and dynamic validation, enabling the model to detect and amend erroneous region‑query links during training, which yields absolute performance gains of 1–6 % across five benchmark datasets.
Computer VisionSelf-CorrectionVisual Grounding
0 likes · 9 min read

The article introduces the Plan‑Execute‑Verify (PEV) agent pattern added to langgraphgo, explains its three‑stage workflow, core features, configuration, concrete Go examples, implementation details, comparisons with ReAct and Reflection, and discusses best practices, limitations, and trade‑offs for high‑risk automation.
GoLLM AgentsLangGraphGo
0 likes · 9 min read

Meeseeks, a new benchmark released by Meituan’s M17 team, systematically evaluates large language models’ instruction‑following ability with a three‑tier framework, multi‑round self‑correction, and extensive real‑world data, revealing performance gaps among models such as OpenAI o‑series, Claude, DeepSeek and Qwen2.5.
AILLM EvaluationMeeseeks
0 likes · 13 min read


DevOpsMay 6, 2025 · Artificial Intelligence
PPTAgent, an open‑source AI tool jointly developed by the Chinese Academy of Sciences and Shanghai Jiexin Technology, automatically creates high‑quality PowerPoint slides by analyzing reference decks, extracting layout patterns, and iteratively editing content with a self‑correction mechanism, achieving superior content, design, and coherence scores compared to existing methods.
AIMultimodal ModelsPPTAgent
0 likes · 6 min read

The article explores DeepSeek’s innovative self‑correction system—combining a Mixture‑of‑Experts architecture with reinforcement‑learning feedback—to achieve real‑time error detection, dynamic knowledge‑graph updates, and enhanced safety in high‑risk fields like autonomous driving and medical diagnostics.
AI safetyDeepSeekMixture of Experts
0 likes · 9 min read


NewBeeNLPDec 3, 2024 · Artificial Intelligence
The article reflects on open‑source LLMs like Qwen2 and Llama 3.1, questioning whether models should self‑review answers, how hidden states might signal uncertainty, the role of loss‑function design, scaling laws, and the trade‑offs between PPO and DPO in alignment.
Scaling LawSelf-Correctionlarge language models
0 likes · 9 min read

Examining OpenAI’s o1 model, this article explores its self‑correction capability by linking test‑time scaling, MCTS‑style reasoning, and DeepMind’s SCoRe reinforcement‑learning framework, illustrating step‑by‑step demos, hypothesizing internal judgment mechanisms, and proposing training pipelines that combine self‑generated data with post‑training RL.
LLM reasoningMCTSOpenAI
0 likes · 12 min read

This article presents the Fudan University Knowledge Workshop Lab's comprehensive research on domain large models, covering background, domain adaptation, capability enhancement, collaborative workflows, challenges such as inference cost and alignment, and proposed solutions including source‑enhanced training, self‑correction mechanisms, and hybrid retrieval‑augmented generation.
AI researchSelf-Correctiondomain adaptation
0 likes · 16 min read

This article presents Fudan University's Knowledge Factory Lab research on domain large models, covering background, challenges, data selection, source‑enhanced tagging, capability improvements, self‑correction, collaborative workflows, and retrieval‑augmented generation for practical AI deployment.
AI researchSelf-Correctiondomain adaptation
0 likes · 16 min read
