Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents
IBM Research presents an analysis of VAKRA, a benchmark designed to evaluate agentic AI systems on reasoning and tool use capabilities. The post examines how agents fail across different task categories, surfacing systematic failure modes in multi-step reasoning and tool invocation. The analysis provides diagnostic insights into where current agent architectures break down under realistic task conditions.
Related guides (4)
Related events (8)
RoboWits: Benchmark for Robotic Creative Problem Solving Under Unexpected Conditions
RoboWits is a new bi-manual robotic benchmark designed to evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions in robotics. The authors introduce an automated multi-agent task generation pipeline that produces 30 seed tasks and 208 mutated tasks spanning geometry, material, and assembly-based reasoning. Benchmarking results show that pre-trained Vision-Language-Action models (VLAs) achieve limited success on seed tasks after fine-tuning but fail on mutated variants, exposing brittleness in reasoning and strategy adaptation. The benchmark highlights a significant gap between skill-level execution and genuine cognitive reasoning in current robotic systems.
IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST
IBM Research and UC Berkeley have released IT-Bench and MAST, a benchmark suite and diagnostic framework aimed at evaluating why AI agents fail in enterprise IT environments. The work targets realistic IT operations tasks such as incident response, service management, and infrastructure automation. By categorizing failure modes systematically, MAST provides a structured taxonomy for understanding agent shortcomings beyond simple pass/fail metrics. This addresses a gap in enterprise-focused agent evaluation, where general benchmarks often fail to capture domain-specific complexity.
EVA-Bench Data 2.0: Expanded agentic tool-use evaluation benchmark with 121 tools and 213 scenarios
ServiceNow AI has released EVA-Bench Data 2.0, an evaluation benchmark covering 3 domains, 121 tools, and 213 scenarios for assessing agentic AI systems. The benchmark appears designed to measure tool-use and multi-step task completion capabilities across diverse enterprise-relevant contexts. This expands the evaluation surface for agent benchmarking, which remains an active area of development.
VISTA: Hybrid user simulation toolkit for interactive agent evaluation
Researchers introduce VISTA, a user simulation framework designed to address limitations in current agent evaluation methods, which rely on static benchmarks that miss dynamic, multi-step failure modes. VISTA provides six metrics for measuring realism, capability coverage, and interaction effectiveness, and combines UI-based and API-based interactions in a hybrid simulator. The toolkit is evaluated in e-commerce and education customer service settings, showing more realistic and comprehensive coverage than existing approaches.
AARRI-Bench evaluates frontier LLMs and agents on granular research-intern-level tasks
Researchers introduce AARR (Act As a Real Researcher), a new benchmark series targeting whether AI agents can emulate the professionalism, thoroughness, and nuanced judgment of human researchers in granular research scenarios—not just macro-level task execution. The first benchmark, AARRI-Bench, tests frontier models and agentic harnesses, finding that even the best configuration (Mini-SWE-Agent with Claude Opus 4.7) achieves only 68.3% success, frequently missing subtle but critical details obvious to human researchers. The work argues that closing the gap requires deeper modeling of research behavior rather than more complex scaffolding.
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
Researchers introduce 'Boiling the Frog,' a multi-turn safety benchmark evaluating whether tool-using AI agents in corporate/office settings are susceptible to incremental attacks that begin with benign requests before introducing harmful payloads. The benchmark uses stateful multi-turn evaluation with a three-level operational risk taxonomy grounded in the EU AI Act and its GPAI Code of Practice. Across nine models, aggregate strict attack success rate is 44.4%, ranging from 20.5% for Claude Haiku 4.5 to 92.9% for Gemini 3.1 Flash Lite, with loss-of-control scenarios reaching 93.3% category-level ASR.
Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
This paper presents a controlled robustness study of Vision-Language-Action (VLA) models in autonomous driving, evaluating Alpamayo R1 (10B parameters) across ~18,000 inference trials under eight sensor perturbation types including noise, lighting extremes, and fog. The key finding is that Chain-of-Causation (CoC) reasoning consistency is a high-fidelity proxy for trajectory reliability: when CoC explanations change post-perturbation, trajectory deviation spikes 5.3× (r=0.99 across attack types). Enabling CoC generation is associated with 11.8% average improvement in trajectory accuracy, and degradation under noise is approximately linear (R²=0.957), while standard preprocessing defenses offer only marginal benefit.
Automated Benchmark Auditing for AI Agents and Large Language Models (ABA)
The paper introduces Auto Benchmark Audit (ABA), an agentic framework that systematically audits AI benchmark tasks for issues such as ambiguous specifications, environment conflicts, and incorrect ground truths. Applied to 168 benchmarks across nine domains including NeurIPS publications, ABA identifies critical issues in over 25.7% of evaluated tasks. The authors demonstrate that filtering out flawed tasks materially shifts model rankings and improves average performance on SWE-bench Verified and Terminal-Bench 2 by 9.9% and 9.6% respectively, indicating that current benchmark scores are significantly distorted by task quality problems. The agentic tool and annotations are released publicly.