paper-with-me

Papers

Reflect before Act: Proactive Error Correction in Language Models

2025-09-23 · Qiuhai Zeng, Sarvesh Rajkumar, Di Wang, Narendra Gyanchandani, Wenbo Yan arxiv

Large Language Models (LLMs) have demonstrated remarkable capabilities in interactive decision-making tasks, but existing methods often struggle with error accumulation and lack robust self-correction mechanisms. We introduce "Reflect before Act" (REBACT), a novel approach that enhances LLM-based decision-making by introducing a critical reflect step prior to taking the next action. This approach allows for immediate error correction, ensuring smooth action path and adaptibity to environment feedback. We evaluate REBACT on three diverse interactive environments: ALFWorld, WebShop, and TextCraft. Our results demonstrate that REBACT significantly outperforms strong baselines, improving success rates by up to 24% on WebShop (achieving 61%), 6.72% on ALFWorld (achieving 98.51%), and 0.5% on TextCraft (achieving 99.5%) using Claude3.5-sonnet as the underlying LLM. Further analysis reveals that REBACT's performance improvements are achieved with only a few modification steps, demonstrating its computational efficiency.

📄 PDF Abstract BibTeX arXiv:2509.18607

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

SAMULE: Self-Learning Agents Enhanced by Multi-level Reflection

2025-09-24 · Yubin Ge, Salvatore Romeo, Jason Cai, Monica Sunkara 외 arxiv

Despite the rapid advancements in LLM agents, they still face the challenge of generating meaningful reflections due to inadequate error analysis and a reliance on rare successful trajectories, especially in complex task…

Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction

2025-12-21 · Qinglin Zeng, Jing Yang, Keze Wang arxiv

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency whi…

Mathematical Reasoning

Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction

2025-06-16 · Didi Zhang, Yaxin Fan, Peifeng Li, Qiaoming Zhu

Goal-oriented proactive dialogue systems are designed to guide user conversations seamlessly towards specific objectives by planning a goal-oriented path. However, previous research has focused predominantly on optimizin…

Decoder

CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decoding

2026-01-05 · Chenyang Ma, Guangyu Yang, Kai Lu, Shitong Xu 외 arxiv

Current work on robot failure detection and correction typically operates in a post hoc manner, analyzing errors and applying corrections only after failures occur. This work introduces CycleVLA, a system that equips Vis…

PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents

2026-02-06 · Hanyu Wang, Yuanpu Cao, Lu Lin, Jinghui Chen arxiv

Advanced large language model agents typically adopt self-reflection for improving performance, where agents iteratively analyze past actions to correct errors. However, existing reflective approaches are inherently retr…