Agentic Software Engineering Computer Science > Software Engineering
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering
Computer Science > Software Engineering [Submitted on 20 Jan 2026] Title:Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering View PDF HTML (experimental)Abstract:LLM-based Multi-Agent (LLM-MA) systems are increasingly applied to automate complex software engineering tasks such as requirements engineering, code generation, and testing.
SPOQ: Specialist Orchestrated Queuing for Multi-Agent Software Engineering
Announce Type: new Abstract: Multi-agent AI systems show promise for automating software engineering tasks, yet existing approaches suffer from coordination overhead, quality control gaps, and limited human oversight. We introduce SPOQ (Specialist Orchestrated Queuing), a methodology combining three innovations: (1) wave-based topological dispatch that computes parallel execution waves from task dependency graphs; (2) dual validation gates applying quality metrics before execution (planning...
ASE-26: a curriculum for agentic software engineering as a discipline
arXiv:2606.01152v1 Announce Type: new Abstract: The work of a professional software engineer has begun to consist, increasingly, of directing agents rather than writing code, and the empirical evidence for the shift is now several years deep. Anthropic's Economic Index puts automation at 79 per cent of Claude Code interactions [2]; Handa and colleagues at Anthropic find AI exposure for Computer Programmer tasks at approximately 75 per cent of the role's distinct activities [3]; Brynjolfsson...
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards. Constructing such data for CUAs requires consistent task instruction, executable environment, and verifiable reward. However, hand-curated benchmarks achieve high reward fidelity but...
MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
arXiv:2601.22859v3 Announce Type: replace Abstract: The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bottleneck stemming from the complexity of constructing executable environments across diverse languages. To address this, we introduce MEnvAgent, a Multi-language framework for automated Environment construction that facilitates scalable generation of verifiable task instances. MEnvAgent employs a...
Enhancing Software Engineering Through Closed-Loop Memory Optimization
arXiv:2606.05646v1 Announce Type: new Abstract: Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues. However, these agents remain fundamentally episodic: they fail to retain, refine, and reuse experiences across tasks, repeatedly reconstructing context from scratch and reproducing similar mistakes. Even with memory support, they offer no remedy for the absence of a principled,...
Anthropic’s Boris Cherny, Claude Code creator, on future of software engineering
Anthropic's Boris Cherny, Claude Code creator, doesn't think the software engineer is going anywhere. He just thinks there are going to be a lot more of them, under a different name. The creator of Claude Code, speaking to tech journalist Casey Newton on the Platformer podcast, predicted that people writing code or directing agents to do it will multiply by 100x in the years ahead.
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
arXiv:2606.07412v1 Announce Type: new Abstract: LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks. Existing synthetic data methods typically create tasks through fixed mutation or bug-injection procedures, making the resulting distributions largely independent of the agent's own weaknesses and training progress. We introduce Socratic-SWE, a closed-loop...
DeployBench: Benchmarking LLM Agents for Research Artifact Deployment
arXiv:2606.05238v1 Announce Type: new Abstract: LLM agents have made rapid progress on software engineering and ML research tasks, but these advances often assume access to a working runnable environment. For research artifacts released alongside published papers, setting up such an environment from a fresh machine remains a major bottleneck. Existing environment setup benchmarks do not cover the full scope of research artifact deployment, which involves multi-language toolchains,...
FASE: Fast Adaptive Semantic Entropy for Code Quality
arXiv:2606.09800v1 Announce Type: new Abstract: Multi-agent code generation offers a promising paradigm for autonomous software development by simulating the human software engineering lifecycle. However, system reliability remains hindered by LLM hallucinations and error propagation across interacting agents. While semantic entropy provides a principled way to quantify uncertainty without ground-truth answers, current methods often rely on costly LLM-driven equivalence checks.