Coding Agents
Overview
Coding agents are language-model systems that inspect repositories, edit files, run commands and tests, and iterate toward software goals, sometimes coordinating subagents or asking users for clarification. Common approaches combine planning and tool-use harnesses with context management, retrieval or memory, reusable skills, and execution feedback; training methods include supervised trajectories and reinforcement learning. Evaluation has expanded from issue-fixing suites such as SWE-bench to interactive, long-horizon repository work, testing and refactoring, scientific software, and real developer sessions, measuring cost, process, policy compliance, and maintainability alongside correctness. A central challenge is making agents dependable beyond passing tests: they must preserve evolving specifications, avoid out-of-scope actions, produce maintainable changes, and collaborate transparently, while outcomes also depend on the model, tools, and harness.
Latest papers
151 papers26 papers in the last four weeks, down 28% on the four weeks before. 0.2% of all new papers.
Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents
TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization
Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation Data
Agentic Synthesis against Counterexample-Supplemented Sketches
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
When Does Restricting a Coding Agent to execute_code Help? A Regime Agent-Design Ablation
Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation
3100 Opinions on Code Review in an AI World: Building Causal Theory from Practitioner Discourse
Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development
Latent Programming Horizons in Coding Agents
GameEngineBench: Evaluating Coding Agents on Real C++ Runtime Environments
Steerability via constraints: a substrate for scalable oversight of coding agents
docs CLI), with substrate and tools contributing independently. We choose Python deliberately: substrate-level oversight gains are largest where the language gives the fewest guarantees by default; the principles extend to languages like Rust.