6arXiv cs.LG (Machine Learning)·
CausalForge: Agentic framework for automated causal inference research grounded in Lean formal proofs
CausalForge is a new agentic research framework that automates theoretical research in causal inference by grounding outputs in the Lean proof assistant rather than relying on LLM reviewers, which the authors note accept fabricated papers at near-chance rates. The system combines Causalean, a 7,035-declaration Lean library for causal inference built with LLM assistance under human oversight, with CausalSmith, a self-improving pipeline that selects topics, proposes results, formalizes statements, and constructs machine-checked proofs. A statement audit step bridges the gap between formal correctness and scientific validity by comparing each theorem against its informal intended claim. The framework represents a notable approach to closing the automated research loop with formal verification rather than LLM judgment.
Related guides (3)
Related events (8)
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.
Goedel-Architect achieves state-of-the-art formal theorem proving with blueprint-based agentic framework
Goedel-Architect is an agentic framework for formal theorem proving in Lean 4 that uses blueprint generation — a dependency graph of definitions and lemmas — rather than recursive decomposition, enabling parallel lemma closure and global refinement. Built on DeepSeek-V4-Flash (284B-A13B), it achieves 99.2% pass@1 on MiniF2F-test and 75.6% on PutnamBench, scaling to 100% on MiniF2F, 88.8% on PutnamBench, and 4/6 on IMO 2025 when seeded with natural-language proofs. The authors claim state-of-the-art performance for an open-source pipeline at up to 500x lower cost than comparable systems.
Paper argues LLMs learn causal structure via difference-making logic, not Pearl/Rubin frameworks
A new arXiv preprint proposes that LLMs learn causal structure through 'variational induction' — a difference-making logic — rather than through the dominant formalisms of Judea Pearl's interventionist approach or the Neyman-Rubin potential outcomes framework. The author analyzes how this logic is realized during training and maps specific architectural features (token embeddings, self-attention) to their roles in this inductive process. The argument draws a parallel between LLM causal learning and the experimental method of systematically varying circumstances. This is a theoretical contribution to understanding how LLMs represent causal and world-model structure.
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.
teLLMe: LLM-powered exploratory causal analysis system for urban driving data
Researchers introduce teLLMe, a system that combines causal structure learning (PC algorithm, DoWhy) with a schema-aware LLM to answer natural-language causal queries over urban driving datasets derived from dashcam annotations. Users pose questions like 'How would rain change traffic density?' and receive a structured 'Causal Card' summarizing effect estimates, adjustment sets, DAG support, and uncertainty. Case studies on BDD-derived traffic events demonstrate plausible causal relationships involving weather and peak hours. The system is framed as a hypothesis-generation tool rather than a definitive causal inference engine.
Forge: Python Framework for Self-Hosted LLM Tool-Calling and Multi-Step Agentic Workflows
Forge is an open-source Python framework designed for self-hosted LLM deployments with tool-calling and multi-step agentic workflow capabilities. It has accumulated 1,396 total stars with a notable single-day spike of +449 stars, suggesting growing community interest. The project targets developers building local or self-hosted agent pipelines without reliance on managed API services.
Causal DAG model for when AI systems should engage Theory of Mind in conflict scenarios
A new arXiv preprint proposes a structural causal model (formalized as a directed acyclic graph) that treats Theory of Mind as a conditionally activated mechanism rather than an always-on capacity in AI systems. The model specifies exogenous situational and agent-level conditions, five endogenous mediators, and three causal pathways (tractability, reasoning-depth, enabling-cause) leading to an epistemic accuracy outcome. The work targets human-machine teaming in conflict contexts, offering a resource-rational decision procedure for when AI should engage social reasoning. Simulation validation and ethical considerations for conflict-optimized mentalizing are discussed.
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.