20 results for “structured feedback”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper studies the design of context for self-distillation in language models, finding that step-aligned feedback yields the largest gains.
Wenhan Xiao, Ziwei Zhang, Chuanyue Yu, Xingcheng Fu +3 more
CRITIC-R1 introduces a structured critic framework that treats RAG critique as an explicit error diagnosis problem using reinforcement learning, significantly improving answer quality over strong RAG…
This paper introduces GLOBE, an agentic framework for continual self-improvement in product listing optimization.
The paper presents Tahoe, a system that optimizes Text-to-SQL performance through dynamic data management and hint learning.
Tongyan Fang, Siyuan Huang, Naiyu Fang, Ganlong Zhao +5 more
The paper proposes Hierarchical Advantage-Weighted Behavior Cloning (HABC) to improve online reinforcement learning by addressing issues with existing approaches.
Yanze Zhang, Hao Liu, Haochang Hao, Zhixiang Shen +2 more
The paper presents a solution to the MetaFine Open Competition's fine-grained manipulation tasks using a scripted teacher and imitation learning.
Wenwu Li, Yuran Song, Mingze Zhao, Bo Jin +1 more
The paper proposes a novel temporal and structural credit assignment framework to efficiently optimize multi-agent LLM systems by decomposing the error signal and using targeted, discrete gradient upd…
This paper introduces Themis, a framework that combines explainability and human feedback for safe Reinforcement Learning.
This paper surveys 1,250 arXiv papers on self-improving AI systems, categorizing them based on what they improve and the degree of loop closure. It identifies a distinctive feature of self-evaluation…
This paper introduces skill-space shooting, a method that uses foundation model guidance to explore corrections through reusable skills and improve policies autonomously.
Youting Wang, Yuan Tang, Bowen Liu, Xuan Liu +1 more
The paper introduces a diagnostic-driven iterative refinement process for improving LLM-generated reward functions in sparse, structured reinforcement learning tasks, significantly boosting agent perf…
This paper evaluates the ability of Large Language Models to rectify their own code through execution feedback.
This paper proposes Reinforcement Learning with Calibrated Pruning (RLCP) to adaptively adjust the slate size in sequential recommenders.
The paper introduces SkillAxe, a framework that enables Large Language Model (LLM) agents to iteratively diagnose and refine their own skills.
Sizhong Qin, Yi Gu, Yao Jiang, Ao Cai +12 more
This paper introduces StructureClaw, an artifact-centered workbench for evaluating structural-engineering agents, and presents StructureClaw-Bench, an executable benchmark for testing these agents.