browsecomp 无context folding 分数

#50
by qwertsdcv - opened

请问有大佬测过browsecomp 无context folding 分数么?我这边测出来才30多,感觉是不是太低了,还是本来就这么低呢?工具用的是web_search和web_extractor。工具返回格式用的xml格式

整了一下,我测出55,还可以

整了一下,我测出55,还可以

请问大佬方便指导一下吗?还是无context folding 测出来的吗

整了一下,我测出55,还可以

请问大佬方便指导一下吗?还是无context folding 测出来的吗

对,无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507,system是

Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.

如果无tool call输出就认为是answer,好像在system要求在<answer>里输出会掉点

This comment has been hidden (marked as Abuse)

整了一下,我测出55,还可以

请问大佬方便指导一下吗?还是无context folding 测出来的吗

对,无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507,system是

Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.

如果无tool call输出就认为是answer,好像在system要求在<answer>里输出会掉点

qwertsdcv changed discussion status to closed
qwertsdcv changed discussion status to open
This comment has been hidden (marked as Abuse)
qwertsdcv changed discussion status to closed
qwertsdcv changed discussion status to open

整了一下,我测出55,还可以

请问大佬方便指导一下吗?还是无context folding 测出来的吗

对,无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507,system是

Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.

如果无tool call输出就认为是answer,好像在system要求在<answer>里输出会掉点

谢谢大佬!!!另外请问search 和visit工具是那种普通的网页访问的么还是基于GUI啥的呀?以及web_search的默认结果返回条数每个query是10么? web_extractor的输出结构大概是什么样的呀??? 感谢感谢🙏

qwertsdcv changed discussion status to closed

整了一下,我测出55,还可以

请问大佬方便指导一下吗?还是无context folding 测出来的吗

对,无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507,system是

Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.

如果无tool call输出就认为是answer,好像在system要求在<answer>里输出会掉点

谢谢大佬!!!另外请问search 和visit工具是那种普通的网页访问的么还是基于GUI啥的呀?以及web_search的默认结果返回条数每个query是10么? web_extractor的输出结构大概是什么样的呀??? 感谢感谢🙏
web_search的默认结果返回条数每个query是10,调的serpapi;web_extractor的输出我是按照TongyiDeepResearch的设置给的

整了一下,我测出55,还可以

请问大佬方便指导一下吗?还是无context folding 测出来的吗

对,无context folding, max length 128k, max turns 不设, web_extractor summary model 是Qwen3-30B-A3B-Instruct-2507,system是

Search intensity is set to high. Please conduct thorough, multi-source research and provide comprehensive, well-cited results.

如果无tool call输出就认为是answer,好像在system要求在<answer>里输出会掉点

谢谢大佬!!!另外请问search 和visit工具是那种普通的网页访问的么还是基于GUI啥的呀?以及web_search的默认结果返回条数每个query是10么? web_extractor的输出结构大概是什么样的呀??? 感谢感谢🙏
web_search的默认结果返回条数每个query是10,调的serpapi;web_extractor的输出我是按照TongyiDeepResearch的设置给的

感谢大佬!救狗命了🥹

Sign up or log in to comment