?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Large+Language+Models+Are+Neurosymbolic+Reasoners&rft.creator=Fang%2C+M&rft.creator=Deng%2C+S&rft.creator=Zhang%2C+Y&rft.creator=Shi%2C+Z&rft.creator=Chen%2C+L&rft.creator=Pechenizkiy%2C+M&rft.creator=Wang%2C+J&rft.description=A+wide+range+of+real-world+applications+is+characterized+by+their+symbolic+nature%2C+necessitating+a+strong+capability+for+symbolic+reasoning.+This+paper+investigates+the+potential+application+of+Large+Language+Models+(LLMs)+as+symbolic+reasoners.+We+focus+on+text-based+games%2C+significant+benchmarks+for+agents+with+natural+language+capabilities%2C+particularly+in+symbolic+tasks+like+math%2C+map+reading%2C+sorting%2C+and+applying+common+sense+in+text-based+worlds.+To+facilitate+these+agents%2C+we+propose+an+LLM+agent+designed+to+tackle+symbolic+challenges+and+achieve+in-game+objectives.+We+begin+by+initializing+the+LLM+agent+and+informing+it+of+its+role.+The+agent+then+receives+observations+and+a+set+of+valid+actions+from+the+text-based+games%2C+along+with+a+specific+symbolic+module.+With+these+inputs%2C+the+LLM+agent+chooses+an+action+and+interacts+with+the+game+environments.+Our+experimental+results+demonstrate+that+our+method+significantly+enhances+the+capability+of+LLMs+as+automated+agents+for+symbolic+reasoning%2C+and+our+LLM+agent+is+effective+in+text-based+games+involving+symbolic+tasks%2C+achieving+an+average+performance+of+88%25+across+all+tasks.&rft.publisher=Association+for+the+Advancement+of+Artificial+Intelligence+(AAAI)&rft.date=2024-03-25&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A++Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence.++(pp.+pp.+17985-17993).++Association+for+the+Advancement+of+Artificial+Intelligence+(AAAI)+(2024)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10194858%2F1%2F2401.09334v1.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10194858%2F&rft.rights=open