Large language models (LLMs) have demonstrated strong reasoning capabilities. Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks. Retrieval-augmented reasoning represents a promising approach. However, significant challenges still persist, including inaccurate and insufficient retrieval for complex questions, as well as difficulty in integrating multi-source knowledge. To address this, we propose Beam Aggregation Reasoning, BeamAggR, a reasoning framework for knowledge-intensive multi-hop QA. BeamAggR explores and prioritizes promising answers at each hop of question. Concretely, we parse the complex questions into trees, which include atom and composite questions, followed by bottom-up reasoning. For atomic questions, the LLM conducts reasoning on multi-source knowledge to get answer candidates. For composite questions, the LLM combines beam candidates, explores multiple reasoning paths through probabilistic aggregation, and prioritizes the most promising trajectory. Extensive experiments on four open-domain multi-hop reasoning datasets show that our method significantly outperforms SOTA methods by 8.5%. Furthermore, our analysis reveals that BeamAggR elicits better knowledge collaboration and answer aggregation.

PARACHINAR, Pakistan (Reuters) - A suspected U.S. drone attack along the Pakistani-Afghan border killed an Islamist militant commander and one of his associates on Tuesday, a Pakistani official in the remote area said.

PARACHINAR/PESHAWAR, Pakistan (Reuters) - A suspected U.S. drone strike killed five people on the mountainous Pakistan-Afghanistan border, government and militant sources said on Tuesday, days after a Canadian-American couple held hostage by the Taliban were freed from the same area.

PARACHINAR/PESHAWAR, Pakistan (Reuters) - A suspected U.S. drone strike killed three people in the tribal area of Pakistan near the Afghanistan border on Friday, a senior regional official said, in what Afghan Taliban sources say was an attack targeting a Haqqani network militant.

Billionaires in the world's tech capital Silicon Valley are reportedly preparing for the apocalypse by buying underground bunkers, guns, ammo and motorcycles. Fearful that artificial intelligence will displace so many jobs that there will be a revolt against those responsible for the technology, the are entrepreneurs readying themselves for doomsday like scenarios. Reid Hoffman, the co-founder of the professional social network, LinkedIn, told The New Yorker that he believes more than 50 per cent of billionaires in the Californian tech hub are preparing for the worst. "I own a couple of motorcycles. I have a bunch of guns and ammo. I figure that, with that, I can hole up in my house for some amount of time," he said.