Papers

Filtered to phase-local context · 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

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

311 upvotes · 15 AUG 2026 · Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang et al.

This paper introduces StateM, a runtime system that improves the performance of long-horizon agents by organizing their execution around durable states, phase-local context, and other components. Practitioners might care because StateM can help agents achieve higher accuracy and efficiency, especially in complex tasks.

agent-native runtimelong-horizon agentsdurable statesphase-local contextrunbooksversioned procedural practices