Papers

Filtered to task robustness · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

49 upvotes · 24 AUG 2026 · Sungho Park, Wonjoong Kim, Rongyuan Tan et al.

This paper develops a system to automatically optimize the design of harnesses for LLM agents, which can improve their reliability on long-horizon tasks. Practitioners might care about this because it could lead to more robust and performant agent systems.

reinforcement learningagent-based systemsharness optimizationoffline learningtask robustness