CausaLab: Scalable Benchmark for Interactive Causal Discovery by LLM Agents
CausaLab is a new evaluation environment that tests LLM agents on interactive causal discovery tasks, requiring them to recover both causal graphs and structural equations from synthetic laboratory episodes governed by randomly sampled structural causal models (SCMs). The benchmark separates predictive accuracy from genuine causal understanding, revealing a persistent gap: GPT-5.2-high achieves 92% task accuracy in a 6-node observational setting but only 0.471 all-edge F1 for mechanism recovery. Mixed observation-intervention strategies improve structural fidelity, while pure intervention strategies underperform on both metrics. Premature stopping is identified as a key agent weakness, partially mitigated by prompting models to verify hypothesis-data consistency.
Related guides (3)
Related events (8)
Study compares human and LLM active causal reasoning, finding LLMs less efficient but near human-level on conjunctive rules
A new arXiv paper investigates whether active exploration reduces the 'conjunctive handicap' in causal learning, using a blicket detector task with adult participants who could freely intervene to identify causal objects. Results show active exploration substantially improves human conjunctive causal reasoning, though conjunctive rules still require more tests than disjunctive ones. State-of-the-art LLMs approach human-level hypothesis inference accuracy but show less efficient exploration strategies and similar conjunctive-disjunctive performance gaps, raising questions about the nature of LLM causal reasoning.
The Abstraction Gap in Vision-Language Causal Reasoning
Researchers introduce a dual-probe methodology and the CAGE benchmark (49,500 questions across 5,500 images) to distinguish linguistic plausibility from faithful causal reasoning in vision-language models. An Abstraction Gap (AG) metric quantifies the normalized performance difference between text-only and chain-of-reasoning probes. Evaluating eight VLMs, seven exhibit AG exceeding 0.50—generating fluent causal text but failing structured causal chain tasks—while one model achieves near-zero AG, suggesting architectural and pretraining choices are decisive. Fine-tuning on 45,000 chain-annotated examples fails to close the gap, pointing to a fundamental capability distinction.
Causal evaluation framework for learnability of formal language tasks in LMs
A new arXiv preprint proposes a causal framework for evaluating how much task-specific data language models need to learn a given task. The authors use formal languages generated by probabilistic finite automata as a controlled testbed, introducing the 'binning semiring' algebraic object to control property frequency in training corpora. Experiments show that standard correlational evaluation practices produce incorrect learnability conclusions due to confounders, with implications for how natural-language task learning is studied.
ClinEnv: Interactive Multi-Stage Long-Horizon EHR Benchmark for Clinical Agent Evaluation
ClinEnv is a new interactive benchmark that evaluates LLMs as attending physicians over real inpatient admissions using a Longitudinal Inpatient Simulation paradigm. Each case is decomposed into sequential decision stages where models must query four specialized agents before committing to medications, procedures, and diagnoses. Across seven evaluated models, the best achieves only 0.31 decision F1, with a sharp gap between diagnosis recovery (0.51 F1) and management actions (0.17 F1). The benchmark uniquely measures information-acquisition process quality alongside outcome quality, exposing a gap invisible to static or outcome-only evaluations.
DiscoverPhysics: Interactive Benchmark for LLM Scientific Discovery in Novel Physics Worlds
DiscoverPhysics is a new interactive benchmark that tests LLM agents on their ability to discover laws of motion in 22 simulated worlds with deliberately non-standard physics, including screened gravity, fractional-power interactions, and hidden dark-matter-like particles. Agents must propose experiments, observe N-body trajectory data, and submit both natural-language explanations and Python implementations of inferred laws. Evaluation across eleven frontier models shows the best agents pass only half the worlds, with consistent failures on latent-structure problems and a substantial gap between open-source and commercial models. The benchmark reveals that predictive accuracy and conceptual understanding are dissociable, and that genuine hypothesis refinement through well-designed experiments is required for high explanation scores.
ReproRepo: Scalable LLM agent framework for reproducibility auditing using GitHub issues
ReproRepo is a new framework for evaluating LLM agents on reproducibility auditing of ML research, using naturally occurring GitHub issues as supervision signals rather than costly manual curation. The framework is instantiated on 1,149 recent ML papers from major conferences and benchmarks four frontier model-agent configurations. The best-performing agent (Codex with GPT-5.5) surfaces at least one semantically related human-reported reproduction blocker for ~90% of papers, though exact localization of issues remains a weakness. The work provides a reusable, scalable evaluation harness for this underexplored agentic task.
AgentCL: A Rigorous Evaluation Framework for Continual Learning in Language Agents
AgentCL is a new benchmark and evaluation framework designed to rigorously assess continual learning in language agents, addressing gaps in existing benchmarks that focus on retrieval over long-context documents or use naive task streams with limited cross-task analysis. The framework constructs compositional task streams where earlier sub-solutions, evidence, or workflows are intentionally reusable in later tasks, contrasting them with naive streams to measure transfer gains. The authors also introduce MemProbe, a probing method that stores interactions, insights, and skills while filtering unreliable experiences during consolidation. Empirical results across coding, deep research, and language understanding tasks show that controlled streams better distinguish memory design quality, and that naive streams can mask memory-induced degradation.
AutoLab benchmark evaluates frontier models on ultra long-horizon iterative research and engineering tasks
AutoLab is a new benchmark of 36 expert-curated tasks across system optimization, puzzle-solving, model development, and CUDA kernel optimization, designed to test agents on sustained closed-loop improvement under wall-clock budgets rather than single-turn or short-horizon settings. Evaluation of 17 frontier models finds that persistence in iterative benchmarking and feedback incorporation — not initial attempt quality — is the dominant success predictor. Claude Opus 4.6 stands out as the strongest performer, while most models including proprietary ones either terminate early or exhaust budgets with minimal progress. The benchmark, harness, and task artifacts are open-sourced.