Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Jagmohan, Ashish"'
As our world digitizes, web agents that can automate complex and monotonous tasks are becoming essential in streamlining workflows. This paper introduces an approach to improving web agent performance through multi-modal validation and self-refinemen
Externí odkaz:
http://arxiv.org/abs/2410.00689
Large language models (LLMs) have limitations in handling tasks that require real-time access to external APIs. While several benchmarks like ToolBench and APIGen have been developed to assess LLMs' API-use capabilities, they often suffer from issues
Externí odkaz:
http://arxiv.org/abs/2409.15523
Autor:
Niknazar, Mohammad, Haley, Paul V, Ramanan, Latha, Truong, Sang T., Shrinivasan, Yedendra, Bhowmick, Ayan Kumar, Dey, Prasenjit, Jagmohan, Ashish, Maheshwari, Hema, Ponoth, Shom, Smith, Robert, Vempaty, Aditya, Haber, Nick, Koyejo, Sanmi, Sundararajan, Sharad
Generative AI holds the promise of enabling a range of sought-after capabilities and revolutionizing workflows in various consumer and enterprise verticals. However, putting a model in production involves much more than just generating an output. It
Externí odkaz:
http://arxiv.org/abs/2408.01452
Autor:
Bulusu, Arya, Man, Brandon, Jagmohan, Ashish, Vempaty, Aditya, Mari-Wyka, Jennifer, Akkil, Deepak
There has been significant recent interest in harnessing LLMs to control software systems through multi-step reasoning, planning and tool-usage. While some promising results have been obtained, application to specific domains raises several general i
Externí odkaz:
http://arxiv.org/abs/2407.17544
Autor:
Abuelsaad, Tamer, Akkil, Deepak, Dey, Prasenjit, Jagmohan, Ashish, Vempaty, Aditya, Kokku, Ravi
AI Agents are changing the way work gets done, both in consumer and enterprise domains. However, the design patterns and architectures to build highly capable agents or multi-agent systems are still developing, and the understanding of the implicatio
Externí odkaz:
http://arxiv.org/abs/2407.13032
Autor:
Bhowmick, Ayan Kumar, Jagmohan, Ashish, Vempaty, Aditya, Dey, Prasenjit, Hall, Leigh, Hartman, Jeremy, Kokku, Ravi, Maheshwari, Hema
The use of question-based activities (QBAs) is wide-spread in education, traditionally forming an integral part of the learning and assessment process. In this paper, we design and evaluate an automated question generation tool for formative and summ
Externí odkaz:
http://arxiv.org/abs/2309.15004
We present a Reinforcement Learning (RL) based framework for optimizing long-term discounted reward problems with large combinatorial action space and state dependent constraints. These characteristics are common to many operations management problem
Externí odkaz:
http://arxiv.org/abs/2112.02215
We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve over time but their total vari
Externí odkaz:
http://arxiv.org/abs/2010.04244
Autor:
Sarpatwar, Kanthi, Shanmugam, Karthikeyan, Ganapavarapu, Venkata Sitaramagiridharganesh, Jagmohan, Ashish, Vaculin, Roman
We envision AI marketplaces to be platforms where consumers, with very less data for a target task, can obtain a relevant model by accessing many private data sources with vast number of data samples. One of the key challenges is to construct a train
Externí odkaz:
http://arxiv.org/abs/1910.12832
The reliability function of variable-rate Slepian-Wolf coding is linked to the reliability function of channel coding with constant composition codes, through which computable lower and upper bounds are derived. The bounds coincide at rates close to
Externí odkaz:
http://arxiv.org/abs/1505.01137