paper-with-me

Papers

Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development

2026-03-03 · Matteo Casserini, Alessandro Facchini, Andrea Ferrario arxiv

As autonomous coding agents become deeply embedded in software development workflows, their high operational velocity introduces a critical oversight challenge: the accumulating divergence between agentic actions and architectural intent. We term this process agentic entropy: a systemic drift that traditional code diff-based and HCXAI methods fail to capture, as they address local outputs rather than global agentic behaviour. To close this gap, we propose a process-oriented explainability framework that exposes how agentic decisions unfold across time, tool calls, and architectural boundaries. Built around three pillars (conformity seeding, reasoning monitoring, and a causal graph interface) our approach provides intent-level telemetry that complements, rather than replaces, existing review practices. We demonstrate its relevance across two user profiles: lay users engaged in vibe coding, who gain structural visibility otherwise masked by functional success; and professional developers, who gain richer contextual grounding for code review without increased overhead. By treating cognitive drift as a first-class concern alongside code quality, our framework supports the minimum level of human comprehension required for agentic oversight to remain substantive.

📄 PDF Abstract BibTeX arXiv:2604.16323

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning

2026-07-08 · Zetian Hu, Shunyu Liu, Junjie Zhang, Yongcheng Jing 외 arxiv

Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, existing efforts largely focus on single-task settings, whereas real-world…

Reinforcement Learning

Agentic Entropy-Balanced Policy Optimization

2025-10-16 · Guanting Dong, Licheng Bao, Zhongyuan Wang, Kangzhi Zhao 외 arxiv

Recently, Agentic Reinforcement Learning (Agentic RL) has made significant progress in incentivizing the multi-turn, long-horizon tool-use capabilities of web agents. While mainstream agentic RL algorithms autonomously e…

Reinforcement Learning

Demystifying Reinforcement Learning in Agentic Reasoning

2025-10-13 · Zhaochen Yu, Ling Yang, Jiaru Zou, Shuicheng Yan 외 arxiv

Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practices remain unclear. In this work, we condu…

Reinforcement Learning

Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems

2025-03-09 · Dany Moshkovich, Hadar Mulian, Sergey Zeltyn, Natti Eder 외

The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle…

Benchmarking

LiveNewsBench: Evaluating LLM Web Search Capabilities with Freshly Curated News

2026-02-14 · Yunfan Zhang, Kathleen McKeown, Smaranda Muresan arxiv

Large Language Models (LLMs) with agentic web search capabilities show strong potential for tasks requiring real-time information access and complex fact retrieval, yet evaluating such systems remains challenging. We int…

Question Generation