paper-with-me

Papers

Agentic Code Reasoning

2026-03-02 · Shubham Ugare, Satish Chandra arxiv

Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we call agentic code reasoning, and introduce semi-formal reasoning: a structured prompting methodology that requires agents to construct explicit premises, trace execution paths, and derive formal conclusions. Unlike unstructured chain-of-thought, semi-formal reasoning acts as a certificate: the agent cannot skip cases or make unsupported claims. We evaluate across three tasks (patch equivalence verification, fault localization, and code question answering) and show that semi-formal reasoning consistently improves accuracy on all of them. For patch equivalence, accuracy improves from 78% to 88% on curated examples and reaches 93% on real-world agent-generated patches, approaching the reliability needed for execution-free RL reward signals. For code question answering on RubberDuckBench Mohammad et al. (2026), semi-formal reasoning achieves 87% accuracy. For fault localization on Defects4J Just et al. (2014), semi-formal reasoning improves Top-5 accuracy by 5 percentage points over standard reasoning. These results demonstrate that structured agentic reasoning enables meaningful semantic code analysis without execution, opening practical applications in RL training pipelines, code review, and static program analysis.

📄 PDF Abstract BibTeX arXiv:2603.01896

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research

2025-02-07 · Junde Wu, Jiayuan Zhu, Yuyuan Liu

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Unlike conventional LLM-based reasoning approaches, which rely solely on internal …

Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+3

KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA

2025-10-29 · Zhuo Chen, Fei Wang, Zixuan Li, Zhao Zhang 외 arxiv

Knowledge Base Question Answering (KBQA) aims to answer natural-language questions over a structured Knowledge Base (KB). Recent work improves KBQA by adopting an agentic reasoning paradigm, in which Large Language Model…

Knowledge Base Question AnsweringReinforcement 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

AgenticRec: A Recommendation-Oriented Agentic Framework with Progressive Tool-Integrated Reasoning Optimization

2026-03-23 · Tianyi Li, Zixuan Wang, Guidong Lei, Xiaodong Li 외 arxiv

Recommender agents built on Large Language Models offer a promising paradigm for personalized recommendation. However, existing agents typically suffer from a misalignment between their tool-integrated reasoning trajecto…

ALRM: Agentic LLM for Robotic Manipulation

2026-01-27 · Vitor Gaboardi dos Santos, Ibrahim Khadraoui, Ibrahim Farhat, Hamza Yous 외 arxiv

Large Language Models (LLMs) have recently empowered agentic frameworks to exhibit advanced reasoning and planning capabilities. However, their integration in robotic control pipelines remains limited in two aspects: (1)…

Robot ManipulationCode Generation