PulseAugur
EN
LIVE 21:11:03

StateM runtime boosts AI agent accuracy via harness scaling · 2 sources tracked

By PulseAugur Editorial · [2 sources] ·

Researchers have developed StateM, a new runtime system designed to enhance the performance of long-horizon AI agents without modifying their underlying model weights. This system organizes agent execution around durable states, recoverable runbooks, and enforceable procedural controls. StateM has demonstrated significant improvements on benchmarks like Terminal-Bench 2.1, boosting GPT-5.5 xhigh to 92.1% and achieving 95.3% raw accuracy with GPT-5.6 Sol xhigh. It also improved DeepSeek-V4 Flash's accuracy from 82.7% to 88.1% with minimal adaptation costs. AI

IMPACT Enhances long-horizon agent capabilities and reduces inference costs, potentially accelerating adoption in complex task automation.

RANK_REASON The cluster describes a new research paper detailing a novel system for improving AI agent performance.

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

StateM runtime boosts AI agent accuracy via harness scaling · 2 sources tracked

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster describes a new research paper detailing a novel system for improving AI agent performance.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
50 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang, Kai Wang ·

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

    arXiv:2608.15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate lessons from earlier executions, skip known procedures, or stop prematurely. We…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

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

    StateM is a runtime system that improves long-horizon agent execution through durable states, recoverable runbooks, and enforceable procedural controls without altering model weights.

RELATED ENTITIES

RELATED TOPICS