An empirical study of harness design for coding agents (arxiv.org)

Screenshot of arxiv.org: An empirical study of harness design for coding agents

First screen, captured 1 month ago.

Looks similar

Screenshot of arxiv.org: Context Language Models

Context Language Models (arxiv.org)

164 points by emersonmacro 25 days ago | 44 comments

arXiv paper introducing Context Language Models, LLMs that natively manage their own context by treating it as an editable file, with benchmarks on agent tasks.

context-management language-models llm-agents multi-agent-systems

Screenshot of arxiv.org: Hybrid Reasoning Agents: LLM agents that think in latent space, act through text

Hybrid Reasoning Agents: LLM agents that think in latent space, act through text (arxiv.org)

497 points by allinonai 8 days ago | 231 comments

arXiv paper introducing HybridAgent, LLM agents that switch between latent-space reasoning and text-based tool interaction, trained with HybridSFT and HybridRL.

llm-agents latent-reasoning reinforcement-learning tool-use

Screenshot of arxiv.org: Self-Harness: Harnesses That Improve Themselves

Self-Harness: Harnesses That Improve Themselves (arxiv.org)

68 points by jonnonz 4 months ago | 3 comments

Screenshot of arxiv.org: Paper2Agent: Stanford Reimagining Research Papers as Interactive AI Agents

Paper2Agent: Stanford Reimagining Research Papers as Interactive AI Agents (arxiv.org)

134 points by Gaishan 1 year ago | 34 comments

Screenshot of arxiv.org: Handbook.md shows that long policy documents do not reliably govern agents

Handbook.md shows that long policy documents do not reliably govern agents (arxiv.org)

309 points by spIrr 2 months ago | 186 comments

Screenshot of arxiv.org: Coding agents think ahead of time

Coding agents think ahead of time (arxiv.org)

79 points by andre15silva 3 months ago | 60 comments

Looks similar

Context Language Models(arxiv.org)

Hybrid Reasoning Agents: LLM agents that think in latent space, act through text(arxiv.org)

Self-Harness: Harnesses That Improve Themselves(arxiv.org)

Paper2Agent: Stanford Reimagining Research Papers as Interactive AI Agents(arxiv.org)

Handbook.md shows that long policy documents do not reliably govern agents(arxiv.org)

Coding agents think ahead of time(arxiv.org)