meddler.tech - meddler (Page 3)

SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments

Modern Large Language Model (LLM) agents promise end to end assistance with real-world software tasks, yet existing benchmarks evaluate LLM agents almost exclusively in pre-baked environments where every dependency is pr...

Ethan Shaw

11 Jul 2025 · 1 min read

Unified Software Engineering Agent as AI Software Engineer

The growth of Large Language Model (LLM) technology has raised expectations for automated coding. However, software engineering is more than coding and is concerned with activities including maintenance and evolution of...

Maya Collins

17 Jun 2025 · 1 min read

SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling

Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE). Recent LLM-powered toolkits, such as OpenAI Co...

Noah Bennett

9 Jun 2025 · 1 min read

From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents

We introduce CTIM-Rover, an AI agent for Software Engineering (SE) built on top of AutoCodeRover (Zhang et al., 2024) that extends agentic reasoning frameworks with an episodic memory, more specifically, a general and re...

Liam Carter

29 May 2025 · 1 min read

SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents

Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains chal...

Ava Brooks

11 Apr 2025 · 1 min read

New tools for building agents

Covers modern agent building blocks: Responses API, tool use, and SDK-level orchestration primitives.

Owen Blake

11 Mar 2025 · 1 min read

LLM Agents Making Agent Tools

Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance b...

Nina Reed

17 Feb 2025 · 1 min read

Building effective agents

Excellent practical patterns for deciding when to use workflows vs autonomous agents, with implementation tradeoffs from production teams.

Leo Parker

19 Dec 2024 · 1 min read

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale

Large Language Models (LLMs) have revolutionized software engineering (SE), showcasing remarkable proficiency in various coding tasks. Despite recent advancements that have enabled the creation of autonomous software age...

Aria Patel

9 Sep 2024 · 1 min read

Agentless: Demystifying LLM-based Software Engineering Agents

Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and...

Zoe Walker

1 Jul 2024 · 1 min read

Ask-before-Plan: Proactive Language Agents for Real-World Planning

The evolution of large language models (LLMs) has enhanced the planning capabilities of language agents in diverse real-world scenarios. Despite these advancements, the potential of LLM-powered agents to comprehend ambig...

Ethan Shaw

18 Jun 2024 · 1 min read

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

Foundational multi-agent orchestration framework paper with concrete conversation patterns.

Maya Collins

16 Aug 2023 · 1 min read

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Planning and search strategy that informs branching and verification-heavy agent workflows.

Noah Bennett

17 May 2023 · 1 min read

Toolformer: Language Models Can Teach Themselves to Use Tools

Seminal work on tool API invocation and self-supervised tool selection strategies.

Liam Carter

9 Feb 2023 · 1 min read

ReAct: Synergizing Reasoning and Acting in Language Models

Core thought-action-observation loop design used in many modern agents.

Ava Brooks

7 Oct 2022 · 1 min read