_______ __ _______ | | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----. | || _ || __|| < | -__|| _| | || -__|| | | ||__ --| |___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____| on Gopher (inofficial) URI Visit Hacker News on the Web COMMENT PAGE FOR: URI Search-R1: Training LLMs to Reason and Leverage Search Engines with RL abidhusain wrote 4 hours 14 min ago: Leveraging reinforcement learning (RL) for LLMs is a fascinating evolution in search technology. The potential for improving search engines to reason intelligently and process data in real-time could revolutionize the entire industry. vessenes wrote 5 hours 3 min ago: A couple of comments. Whatâs not that interesting here is that adding search to an LLM increases accuracy â this is known, and largely implemented via RAG or other search pipelines which then stuff information into the context. What might be interesting here is that they are thinking about taxonomic tool use-cases, and exploring training and therefore optimizing the utilization of them. This to me is a proof of concept â an interesting one, but just a proof of concept. You can see from their example search that the model over-relied on search; it didnât need to re-search three times to get the answer. A next step that I think would be useful would be updating the reward function to penalize search; pressing the model to use search when it needs to and not before. This to me is a likely framework going forward where MCP tool costing matters, and would be really useful to have in the next gen of tool calling LLMs. In the case of search weâd hopefully get a really useful signal and outcome for times the model is unsure â it would call a friend, and get good info! And for times itâs sure, weâd have taught it not to waste reward on that. DeathArrow wrote 7 hours 50 min ago: Can someone ELI5 how reinforcement learning works with transformer based architecture? deepsquirrelnet wrote 8 hours 9 min ago: This is pretty cool. I have a similar model thatâs 8 days into training on msmarco. So far I only have the âcold startâ data posted, but Iâm planning on posting a full distillation dataset. URI [1]: https://huggingface.co/datasets/dleemiller/lm25 jacobgorm wrote 2 hours 37 min ago: What kind of hardware setup would be needed to replicate the paperâs results? 0xlogk wrote 8 hours 42 min ago: The paper mentions they used Wikipedia as search corpus. The repo states they plan to expand to Google, Bing APIs. I wonder how they will handle evolving search corpora, ie. if continual RL updates will be needed. sachinaag wrote 12 hours 2 min ago: I wonder if Perplexity uses similar methods under the hood or if it is a completely different approach. mrklol wrote 7 hours 42 min ago: I feel like most of these services simply take your prompt and ask a model for search queries regarding that prompt. Then add the resulting pages into the context. perbu wrote 12 hours 38 min ago: This is the magical thing that happens when AI research happens in the open. Deepseek published their model and their methodology and then the nice people at the University of Illinois are able to build on it. When OpenAI was launched this is what I thought it was going to be like. Something, something for the betterment of man kind. c16 wrote 11 hours 45 min ago: I'm always surprised at how many LLM research papers are published on here, so despite OpenAI, I think it's absolutely happening. NitpickLawyer wrote 5 hours 41 min ago: Unfortunately the "open"AI effect is starting to show in other labs as well. DeepMind recently announced a min 6months delay in publishing their SotA research, to give them a market advantage. I get it, but it's sad that it's happening. The good thing is that there are a lot of companies out there that want to make a name for themselves. Mistral started like that with Apache 2.0 models, now ds w/ MIT models, and so on. And if the past year is a good indicator, it seems that closed SotA to open close-to-SotA is 6-3 months. So that's good. I also find interesting LeCun's take that "there is no closed source moat, or not for long". In a podcast he went into detail on this, saying that "people move companies, and people talk". If someone finds some secret sauce, the ideas will move around and other labs will catch up quickly. So there's some hope. DIR <- back to front page