PhysTool-Bench reveals severe gaps in MLLM physical tool use and embodied planning
Researchers introduce PhysTool-Bench, the first benchmark evaluating multimodal LLMs on physical tool use across 2,510 queries and 2,678 real-world tools spanning manufacturing, electrical work, agriculture, and healthcare. Evaluation of 13 leading MLLMs shows even the best model (Gemini-3.1-Pro) identifies only 58.7% of tools in a scene and completes just 21.0% of queries end-to-end. The results expose a two-level deficit: poor tool perception in realistic scenes and a much larger drop at the planning stage, indicating a lack of functional commonsense for mapping tools to task semantics. This pinpoints a critical bottleneck for embodied AI development.
Related guides (4)
Google: The AI Lab That Builds Everything from DNA Models to Your Phone's Assistant
Related events (8)
PROVE framework trains LLMs for multi-step tool use via stateful MCP environments and programmatic rewards
Researchers introduce PROVE (Programmatic Rewards On Verified Environments), a framework for training LLMs to orchestrate multi-step tool calls using reinforcement learning. The system includes a library of 20 stateful MCP servers with 343 tools, an automated data synthesis pipeline that grounds training queries in live server state, and a multi-component programmatic reward function requiring no judge model. Training four models (Qwen3-4B, Qwen3-8B, Qwen2.5-7B, Granite-4.1-8B) with ~13K examples yields gains of up to +10.2 on BFCL Multi-Turn, +6.8 on tau2-bench, and +6.5 on T-Eval, demonstrating consistent improvements in multi-step tool orchestration.
ESI-Bench: A Benchmark for Embodied Spatial Intelligence Closing the Perception-Action Loop
ESI-Bench is a new benchmark for embodied spatial intelligence spanning 10 task categories and 29 subcategories, built on OmniGibson and grounded in Spelke's core knowledge systems. It evaluates agents that must actively deploy perception, locomotion, and manipulation to accumulate task-relevant evidence, rather than passively processing oracle observations. Experiments on state-of-the-art MLLMs reveal that active exploration outperforms passive baselines, but most failures stem from 'action blindness'—poor action choices leading to cascading errors—and a metacognitive gap where models commit prematurely with high confidence regardless of evidence quality. Human studies show humans seek falsifying viewpoints and revise beliefs under contradiction, a capability current models lack.
GIM: A Grounded Integration Measure Benchmark for Evaluating Multi-Domain Cognitive Coordination in LLMs
The Grounded Integration Measure (GIM) is a new LLM benchmark of 820 original problems designed to resist benchmark saturation by requiring integration of multiple cognitive operations—constraint satisfaction, state tracking, epistemic vigilance, audience calibration—over broadly accessible knowledge. Unlike knowledge-escalation benchmarks (GPQA, HLE) or pure abstraction benchmarks (ARC-AGI), GIM grounds reasoning in realistic tasks without gating on specialized expertise. The authors calibrate a 2-parameter logistic IRT model over 200k+ prompt-response pairs across 28 models and 47 test configurations, producing the most extensive published study of test-time compute vs. model capability tradeoffs on a fixed benchmark. A key finding is that within-family configuration choices (thinking budget, quantization) matter as much as model selection.
MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
OpenAI introduces MLE-bench, a benchmark designed to measure AI agent performance on machine learning engineering tasks. The benchmark draws from Kaggle competitions to evaluate agents on realistic ML engineering workflows. Initial results show that current agents, including those powered by o1-preview, achieve competitive performance on a subset of tasks but fall well short of top human competitors. The benchmark is intended to track progress in agentic ML capabilities over time.
SIMMER benchmark exposes high rates of latent planning failures in frontier LLMs
Researchers introduce SIMMER, a benchmark for evaluating latent failures in LLM-generated executable plans within a kitchen-domain world model comprising 77 actions, 262 objects, and ~46,800 possible interactions. Unlike existing benchmarks that only catch immediate execution failures, SIMMER detects silent hazards and irreversible consequences using a state machine executor. Experiments across six LLMs find that even frontier models produce error-free plans at most 17% of the time, with up to 56% of plans containing latent failures—most leading to irreversible outcomes. The paper also shows that counterfactual foresight simulation can reduce latent failures by up to 72%, pointing toward a mitigation direction.
M³Exam: Benchmark for Multimodal Memory in Realistic User-Agent Interactions
Researchers introduce M³Exam, a query-centric multimodal conversational memory benchmark designed to evaluate language agents on realistic user-agent interactions, including cross-modal grounding and implicit information inference. Existing benchmarks are critiqued for assuming sparse visuals and human-human interaction formats. The paper also proposes M³Proctor, a companion memory method that detects query modality bias and retrieves raw visual sources on demand, achieving 13% accuracy improvement while reducing index-construction time and retrieved tokens by over 70%.
T1-Bench: Multi-scenario agent benchmark across 25 real-world domains
T1-Bench is a new benchmark for evaluating agentic LLM systems in realistic customer-facing, multi-domain environments, covering 25 domains of varying difficulty with interleaved multi-turn scenarios. The authors evaluate 12 proprietary and open-weight models and combine automatic evaluation with human judgments. The benchmark targets gaps in existing agent evals around task complexity, domain diversity, and compositional reasoning across multi-step interactions.
Benchmarking study finds LLMs fail at counterintuitive probability problems despite strong standard performance
A new arXiv paper evaluates 8 state-of-the-art LLMs on discrete probability problems using two datasets: standard exercises (average accuracy 0.96) and counterintuitive exercises designed to trigger heuristic reasoning (average accuracy 0.59). The authors document token bias causing 20%+ performance drops when canonical problem formulations are disguised, and up to 34% degradation when misleading suggestions are embedded in prompts. The findings argue that current LLMs are not genuine probabilistic reasoners despite their success on advanced math benchmarks.