Skip to content
Papers.

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents research paper by IBM, 2026

IBM · Jun 18, 2026 · Agents and evaluation · 1 citations · 42 upvotes · unverified

Read on arXiv

What it shows

Aggregate-score leaderboards in agent benchmarks fail to capture deployment-relevant dimensions and show rank instability, necessitating new evaluation frameworks based on predictive validity and out-of-distribution criteria.

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

More from IBM

All 3
PaperCitations
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM AgentsLLM-based systems use executable workflows that interleave various computational components, with recent approaches organized by workflow structure determination timing and optimization dimensions.Agents and evaluation · Mar 2026 · Unverified26
TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP EnvironmentsToucan, a large publicly available tool-agentic dataset, enhances the performance of LLM agents by providing diverse, realistic, and complex multi-tool and multi-turn interactions.Agents and evaluation · Oct 2025 · Unverified54

Other agents and evaluation papers

Topic
PaperCitations
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic CapabilitiesGemini 2.X model family, including Gemini 2.5 Pro and Flash, offers superior coding, reasoning, and multimodal understanding capabilities across a range of computational efficiencies.Google · Jul 2025 · Unverified4,134
DeepSeek-V3.2: Pushing the Frontier of Open Large Language ModelsDeepSeek-V3.2 introduces DeepSeek Sparse Attention and a scalable reinforcement learning framework, achieving superior reasoning and performance compared to GPT-5 and Gemini-3.0-Pro in complex reasoning tasks.DeepSeek · Dec 2025 · Unverified761
WebWatcher: Breaking New Frontier of Vision-Language Deep Research AgentWebWatcher, a multimodal agent with enhanced visual-language reasoning, outperforms existing agents in complex visual and textual information retrieval tasks using synthetic trajectories and reinforcement learning.Alibaba (Qwen) · Aug 2025 · Unverified117
SkillOpt: Executive Strategy for Self-Evolving Agent SkillsSkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.Microsoft · May 2026 · Unverified85
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic ReasoningWe present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model.NVIDIA · Dec 2025 · Unverified81
AgentFold: Long-Horizon Web Agents with Proactive Context ManagementAgentFold, a novel proactive context management paradigm, enhances long-horizon task performance through dynamic context folding, achieving superior results on benchmarks compared to larger models and proprietary agents.Alibaba (Qwen) · Oct 2025 · Unverified77
About this paper
Authors
Dhaval C. Patel, Kaoutar El Maghraoui, Shuxin Lin and 58 more
arXiv
2606.19704 · PDF
Venue
arXiv.org
Citations
1, 0 influential · Semantic Scholar
Upvotes
42 · Hugging Face
Lab
IBM · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf

Changes

What changed
Influential citationsfirst count: 0Sep 25, 2026
Citationsfirst count: 1Sep 25, 2026
New paperFound by the weekly scan, unverifiedSep 25, 2026

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

New papers by email

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

Double opt-in. Unsubscribe any time.