Contract compliance verification requires reasoning about cross-clause dependencies where obligations, exceptions, and conditions interact across multiple provisions, yet existing legal NLP benchmarks like ContractNLI and CUAD focus exclusively on isolated single-clause tasks. We introduce COMPACT (COMpliance PAralegals via Clause graph reasoning over conTracts), a framework that models cross-clause dependencies through structured clause graphs. Our approach extracts deontic-temporal entities from clauses and constructs typed relationship graphs capturing definitional dependencies, exception hierarchies, and temporal sequences. From these graphs, we introduce ACE (Assessing Compliance in Enterprise)- a benchmark containing 4,700 carefully constructed compliance scenarios derived from 633 real-world contracts covering 26 types of agreements. Each scenario requires multi-hop reasoning across multiple clauses, and undergoes independent LLM-based validation to ensure quality. Evaluation reveals that multi-clause reasoning poses a fundamental challenge for state-of-the-art models (34-57% base accuracy), while training on ACE yields substantial improvements on compliance tasks (+22–43 % points) and also enhances general legal reasoning performance on other benchmarks (PrivaCI-Bench, ContractNLI).

Compound AI (CAI) systems, also referred to as LLM Agents, combine LLMs with retrievers and tools to enable information-seeking applications in the real-world. Thus, ensuring these systems perform reliably is critical. However, traditional evaluation using benchmark datasets and aggregate metrics often fails to capture their true operational performance. This is because understanding the operational efficacy of these information-seeking systems requires the ability to probe their behavior across a spectrum of simulated scenarios to identify potential failure modes. Thus, we present a behavior-driven evaluation framework that generates test specifications - explicit descriptions of expected system behaviors in specific scenarios - aligned with real usage contexts. These test specifications serve as formal declarations of system requirements that are then automatically transformed into concrete test cases. Specifically, our framework operates in two phases: (1) generating diverse test specifications via submodular optimization over semantic diversity and document coverage of the tests, and (2) implementing these specifications through graph-based pipelines supporting both tabular and textual sources. Evaluations on QuAC & HybriDialogue datasets, across SoTA LLMs, reveal that our framework identifies failure modes missed by traditional metrics, demonstrating failure rates twice as high as human-curated datasets.