cs.SE · 2026-06-22 · No. 31
Software Engineering, 2026-06-22.
6 new papers in cs.SE. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
6 entries-
01
Probe-and-Refine Tuning of Repository Guidance for Coding Agents
Asa Shepard, Jeannie Albrecht
cs.SE · cs.LG
LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test suite, which workflows have historically led to wrong fixes) that does not exist in the code itself. Engineers typically maintain \texttt{AGENTS.md} files to supply this context as instructions for coding agents, but whether they help is contested: recent studies disagree on whether LLM-generated guidance...
-
02
AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning
Zepeng Li, Jie Ren, Zhanyong Tang, Jie Zheng, Zheng Wang
cs.SE · cs.AI
Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements. We present AutoPass, a multi-agent framework for compiler performance tuning that uses compiler and runtime evidence to guide LLM-generated optimization decisions. Rather than treating the compiler as a black box like prior auto-tuning...
-
03
A Model-Driven Approach for Developing Families of Reinforcement Learning Environments
Xiaoran Liu, Istvan David
cs.SE · cs.LG
Virtual training environments are software-intensive systems in which reinforcement learning (RL) agents learn, adapt, and demonstrate meaningful behavior. Virtual training environments offer a safe and cost-efficient alternative to training agents in real-world settings. However, to converge, most realistic RL problems require training in multiple, mostly similar but slightly different environments - i.e., families of environment variants....
-
04
The Correctness Illusion in LLM-Generated GPU Kernels
Dipankar Sarkar
cs.SE · cs.DC · cs.LG
Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks. The number of inputs varies between benchmarks. The shape, dtype, and tolerance are fixed for each kernel. We test that oracle empirically. We construct a controlled corpus of 24 Triton and CPU stand-in kernels (15 correct controls and 9 LLM-style buggy variants seeded with documented...
-
05
When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
Kaiyue Yang, Yuyan Bu, Jingwei Yi, Yuchi Wang, Biyu Zhou, Juntao Dai, Songlin Hu, Yaodong Yang
cs.SE · cs.AI · cs.CL
As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, prior tool-selection studies focus on safety-agnostic metadata preferences, leaving privilege-sensitive choices underexplored. To address this gap, we study over-privileged tool selection, in which an agent selects or escalates to a higher-privilege tool despite a sufficient lower-privilege alternative. We...
-
06
Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
Mugeng Liu, Shuoqi Li, Yixuan Zhang, Yun Ma
cs.SE · cs.AI
In the agentic web era, LLM-based agents increasingly invoke web services as tools, yet most interfaces remain \emph{static endpoints} that poorly express long-horizon workflows with loops, conditionals, joins, and retries. We present ToolPro, which represents an agent's tool intent as an \emph{executable tool program} that compactly encodes multi-step service interactions with explicit effect types. ToolPro combines constraint-guided program...
This edition is part of The Daily Abstract — cs.SE archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.