AgentDSE uses an LLM agent in a simulator-in-the-loop setup to achieve competitive or superior architectural designs with up to 100x fewer evaluations than traditional black-box optimization methods.
hub
Ai agentic programming: A survey of techniques, challenges, and opportunities
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 14roles
background 1polarities
background 1representative citing papers
StaminaBench evaluates coding agents over 100 procedurally generated change requests to a REST API, finding that tested models fail within 5-6 turns without feedback but improve up to 12x with test feedback and good harnesses.
Coding agents struggle to infer least-privilege file permissions by omitting needed accesses while granting unused or sensitive ones, but Sufficiency-Tightness Decomposition improves sensitive-task success by up to 15.8% and reduces attacks.
DeInfer reduces parallel inference communication cost for decomposed LLMs by up to 78% by moving collective operations into the low-rank latent space and redesigning KV-cache reconstruction for static graph compatibility.
Mixed-methods study creates taxonomy of AI IDE rules from 7310 instances, analyzes evolution drivers, and reports that rule updates raise average artifact compliance from 49.14% to 72.13%.
A new LLM-based system generates and validates runnable modular MCMC samplers directly from natural-language Bayesian model descriptions, reporting success on 120 of 132 benchmark models.
AI-generated security pull requests frequently contain a small set of recurring weaknesses, with many flawed ones merged and rejections driven by process factors rather than technical issues.
TacEvo is an LLM-driven self-evolving search method that discovers neural architectures for robotic tactile force regression and grating classification, reporting fitness gains of 56.1% and 96.1% over 20 generations.
ProjectMem implements a local event-sourced memory and judgment layer for AI coding agents that logs typed events, projects them to MCP summaries, and applies deterministic pre-action gates to avoid known failures.
Empirical benchmarks on four SE tasks show grammar-constrained decoding and TTMG eliminate most syntax errors in LLM outputs while structural and semantic errors persist and cascade in downstream tools.
A-ProS uses a hybrid multi-model feedback framework with stateful refinement to improve success rates on competitive programming problems, achieving over 2x gains compared to baseline agent loops.
The Productivity-Reliability Paradox arises because AI code generators produce variable output while developers lack sufficient specification discipline, making governance models focused on specifications the binding constraint rather than model improvements.
The paper introduces KISS Sorcar, a simple open-source AI agent framework with a five-layer hierarchy and git worktree isolation to address context limits, error propagation, and reviewability in software engineering tasks.
citing papers explorer
-
AgentDSE: Reasoning-Augmented Architectural Design Space Exploration
AgentDSE uses an LLM agent in a simulator-in-the-loop setup to achieve competitive or superior architectural designs with up to 100x fewer evaluations than traditional black-box optimization methods.
-
StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns
StaminaBench evaluates coding agents over 100 procedurally generated change requests to a REST API, finding that tested models fail within 5-6 turns without feedback but improve up to 12x with test feedback and good harnesses.
-
Do Coding Agents Understand Least-Privilege Authorization?
Coding agents struggle to infer least-privilege file permissions by omitting needed accesses while granting unused or sensitive ones, but Sufficiency-Tightness Decomposition improves sensitive-task success by up to 15.8% and reduces attacks.
-
Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
DeInfer reduces parallel inference communication cost for decomposed LLMs by up to 78% by moving collective operations into the low-rank latent space and redesigning KV-cache reconstruction for static graph compatibility.
-
Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study
Mixed-methods study creates taxonomy of AI IDE rules from 7310 instances, analyzes evolution drivers, and reports that rule updates raise average artifact compliance from 49.14% to 72.13%.
-
AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers
A new LLM-based system generates and validates runnable modular MCMC samplers directly from natural-language Bayesian model descriptions, reporting success on 120 of 132 benchmark models.
-
Insights into Security-Related AI-Generated Pull Requests
AI-generated security pull requests frequently contain a small set of recurring weaknesses, with many flawed ones merged and rejections driven by process factors rather than technical issues.
-
TacEvo: Self-Evolving Architecture Discovery for Robotic Tactile Perception via LLM-Driven Quality-Diversity Search
TacEvo is an LLM-driven self-evolving search method that discovers neural architectures for robotic tactile force regression and grating classification, reporting fitness gains of 56.1% and 96.1% over 20 generations.
-
PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents
ProjectMem implements a local event-sourced memory and judgment layer for AI coding agents that logs typed events, projects them to MCP summaries, and applies deterministic pre-action gates to avoid known failures.
-
Empirical Study for Structured Output Control in LLMs for Software Engineering
Empirical benchmarks on four SE tasks show grammar-constrained decoding and TTMG eliminate most syntax errors in LLM outputs while structural and semantic errors persist and cascade in downstream tools.
-
A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback
A-ProS uses a hybrid multi-model feedback framework with stateful refinement to improve success rates on competitive programming problems, achieving over 2x gains compared to baseline agent loops.
-
The Productivity-Reliability Paradox: Specification-Driven Governance for AI-Augmented Software Development
The Productivity-Reliability Paradox arises because AI code generators produce variable output while developers lack sufficient specification discipline, making governance models focused on specifications the binding constraint rather than model improvements.
-
KISS Sorcar: A Stupidly-Simple General-Purpose and Software Engineering AI Assistant
The paper introduces KISS Sorcar, a simple open-source AI agent framework with a five-layer hierarchy and git worktree isolation to address context limits, error propagation, and reviewability in software engineering tasks.
- What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants