Skip to content
Papers.

StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments research paper by ServiceNow, 2026

ServiceNow · Aug 25, 2026 · Retrieval and data · 41 upvotes · unverified 4 weeks ago

Read on arXiv

What it shows

StarHarness evolves fixed-weight agent harnesses via stratified task pools and hidden selection to improve enterprise tool-use performance and cross-model transfer.

UnverifiedHugging Face's summary; not yet checked by hand.

More from ServiceNow

All 20
PaperCitations
AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-CallingAgentJudgeBench reveals that LLM judges face structural reliability limits on dependency-driven agentic tool-calling workflows, with alignment degrading by difficulty and ground-truth exposure yielding mixed effects.Agents and evaluation · Aug 2026 · Unverified4 weeks ago-
SynthDocBench: Controlled Benchmark for Long-Context Visual Document UnderstandingSynthDocBench is a synthetic long-context visual document benchmark that isolates failure modes in vision-language models, revealing sharp length degradation, positional sensitivity, and chart comprehension breakdowns.Agents and evaluation · Jul 2026 · Unverified2 months ago-
EVA-Bench: A New End-to-end Framework for Evaluating Voice AgentsEVA-Bench presents a comprehensive evaluation framework for voice agents that simulates realistic conversations and measures performance across multiple voice-specific failure modes using novel accuracy and experience metrics.Agents and evaluation · May 2026 · Unverified4 months ago-
Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer DynamicsEnterprise discovery agents that read system configuration at runtime outperform traditional world models in configurable environments where dynamics change over time.Agents and evaluation · May 2026 · Unverified4 months ago-
Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient ReasoningApriel-Reasoner is a 15B-parameter language model trained with reproducible multi-domain reinforcement learning to improve reasoning efficiency and accuracy across diverse tasks while reducing inference costs.Reasoning · Apr 20265 months ago-
Therefore I am. I ThinkReasoning models appear to encode action choices before beginning textual deliberation, as evidenced by early decision detection and activation steering effects.Reasoning · Apr 2026 · Unverified5 months ago-
Terminal Agents Suffice for Enterprise AutomationSimple terminal-based coding agents using programmatic interfaces and foundation models can effectively perform enterprise tasks comparable to or better than complex tool-augmented agents.Agents and evaluation · Mar 2026 · Unverified5 months ago-
CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use AgentsCUA-Suite introduces a large-scale ecosystem of expert video demonstrations and annotations for computer-use agents, providing continuous screen recordings and detailed reasoning annotations to advance desktop automation capabilities.Agents and evaluation · Mar 20266 months ago-

Other retrieval and data papers

Topic
PaperCitations
From Local to Global: A Graph RAG Approach to Query-Focused SummarizationGraphRAG builds a knowledge graph of a document set so a model can answer questions about the whole collection.Microsoft · Apr 20242 years ago2,198
DINOv3DINOv3, a self-supervised learning model, achieves superior performance across various vision tasks by scaling datasets and models, addressing dense feature degradation, and enhancing flexibility with post-hoc strategies.Meta · Aug 2025 · Unverified1 year ago1,498
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic DataGenerating extensive Lean 4 proof data from mathematical competition problems improved DeepSeekMath 7B's theorem-proving capabilities over GPT-4 and other methods.DeepSeek · May 2024 · Unverified2 years ago260
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and RankingThe Qwen3-VL-Embedding and Qwen3-VL-Reranker models form an end-to-end multimodal search pipeline, leveraging multi-stage training and cross-attention mechanisms to achieve high-precision retrieval across diverse modalities.Alibaba (Qwen) · Jan 2026 · Unverified8 months ago231
DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree SearchDeepSeek-Prover-V1.5 improves theorem proving by optimizing training and inference, utilizing reinforcement learning, and proposing RMaxTS for diverse proof paths, achieving state-of-the-art results on miniF2F and ProofNet benchmarks.DeepSeek · Aug 2024 · Unverified2 years ago207
Learning to Discover at Test TimeTest-time training enables AI systems to discover optimal solutions for specific scientific problems through continual learning focused on individual challenges rather than generalization.Stanford University · Jan 2026 · Unverified8 months ago82
About this paper
Authors
Esakkivel Esakkiraja, Denis Akhiyarov, Vikas Yadav and 4 more
arXiv
2608.24804 · PDF
Citations
Not counted yet · Semantic Scholar
Upvotes
41 · Hugging Face
Lab
ServiceNow · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf

Changes

What changed
New paperFound by the weekly scan, unverifiedSep 26, 2026today

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.