Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most existing ARL methods train a single set of parameters to support both reasoning and tool-use behaviors, implicitly assuming that joint training leads to improved overall agent performance. Despite its widespread adoption, this assumption has rarely been examined empirically. In this paper, we systematically examine this assumption by introducing Capability Effect Attribution (CEA), which provides quantitative evidence of interference between reasoning and tool-use behaviors. Through an in-depth analysis, we show that these two capabilities often induce misaligned gradient directions, leading to training interference that undermines the effectiveness of joint optimization and challenges the prevailing ARL paradigm. To address this issue, we propose Disentangled Action–Reasoning Tuning (DART), a simple and efficient framework that explicitly decouples parameter updates for reasoning and tool use via separate low-rank adaptation modules. With this simple change alone, DART outperforms all joint-optimization baselines and approaches the 2-Agent upper bound across thirteen benchmarks on retrieval-augmented QA and NL2SQL, further supporting our finding of capability interference under shared optimization.

Fact verification has attracted a lot of attention recently, e.g., in journalism, marketing, and policymaking, as misinformation and dis- information can sway one’s opinion and affect one’s actions. While fact-checking is a hard task in general, in many cases, false statements can be easily debunked based on analytics over tables with reliable information. Hence, table- based fact verification has recently emerged as an important and growing research area. Yet, progress has been limited due to the lack of datasets that can be used to pre-train language models (LMs) to be aware of common table operations, such as aggregating a column or comparing tuples. To bridge this gap, this paper introduces PASTA for table-based fact verification via pre-training with synthesized sentence–table cloze questions. In particular, we design six types of common sentence–table cloze tasks, including Filter, Aggregation, Superlative, Comparative, Ordinal, and Unique, based on which we synthesize a large corpus consisting of 1.2 million sentence–table pairs from WikiTables. PASTA uses a recent pre-trained LM, DeBERTaV3, and further pre- trains it on our corpus. Our experimental results show that PASTA achieves new state-of-the-art (SOTA) performance on two table-based fact verification datasets TabFact and SEM-TAB- FACTS. In particular, on the complex set of TabFact, which contains multiple operations, PASTA largely outperforms previous SOTA by 4.7% (85.6% vs. 80.9%), and the gap between PASTA and human performance on the small test set is narrowed to just 1.5% (90.6% vs. 92.1%).