No one outside of CA can say for sure what how good the BAI in Napoleon will be but there are some obvious clues that were offered in developer Mike Simpson's 1/10 blog post http://blogs.sega.com/totalwar/2009/11/10/battle-ai-by-mike-simpson/. Simpson wrote:"Progress is frustratingly slow...battle AI is not rocket science - its way, way harder than that."
I think he's trying to tell us not to expect much BAI improvement in Napoleon."In the updates so far we’ve got rid of some of the worst behaviours that are close to the surface, and have started to tackle deeper issues like unstable decision loops that cause the AI to mill around rather than hold its line and fire. We’re also starting to add new behaviours, for example taking better advantage of hilly terrain. These improvements take the code further than we’ve been able before and will be there for Napoleon."
This suggests very limited improvements, such as NTW's BAI may seek high ground. However, other things he talks about, i.e. the milling around bit was mostly solved by Darth in his Empire mod IMO. "Our overall aim with the improvements is first to get rid of any erratic behaviour, second to improve general performance to the point where the obvious handicaps can be removed, and then to add a greater variety of ’smart’ behaviours...it’s a process of continual improvement, and each game will get AI better than the last one. Including Napoleon."
To paraphrase, the goal for NTW is removing obvious bugs, not something dramatically better."If you’re a genius C++ programmer, you understand exactly how difficult this problem is, but still think it’s the most interesting code problem in the world, apply for a job. We’ll find space for you."
This definitely surprised me, i.e. how he transformed BAI discussion into a plea for programmers to apply for jobs at CA! I may be reading too much desperation into this however.