diff --git a/r/NEWS.md b/r/NEWS.md
index 1955ede5602..3c8cd79717e 100644
--- a/r/NEWS.md
+++ b/r/NEWS.md
@@ -22,6 +22,8 @@
 ## Minor improvements and fixes
 
 - Added bindings for atan, sinh, cosh, tanh, asinh, acosh, and tanh, and expm1 (#44953)
+- Expose an option `check_directory_existence_before_creation` in `S3FileSystem` 
+  to reduce I/O calls on cloud storage (@HaochengLIU, #41998)
 
 # arrow 20.0.0
 
diff --git a/r/R/arrowExports.R b/r/R/arrowExports.R
index 62e2182ffcd..901898e5b29 100644
--- a/r/R/arrowExports.R
+++ b/r/R/arrowExports.R
@@ -1372,8 +1372,8 @@ fs___CopyFiles <- function(source_fs, source_sel, destination_fs, destination_ba
   invisible(.Call(`_arrow_fs___CopyFiles`, source_fs, source_sel, destination_fs, destination_base_dir, chunk_size, use_threads))
 }
 
-fs___S3FileSystem__create <- function(anonymous, access_key, secret_key, session_token, role_arn, session_name, external_id, load_frequency, region, endpoint_override, scheme, proxy_options, background_writes, allow_bucket_creation, allow_bucket_deletion, connect_timeout, request_timeout) {
-  .Call(`_arrow_fs___S3FileSystem__create`, anonymous, access_key, secret_key, session_token, role_arn, session_name, external_id, load_frequency, region, endpoint_override, scheme, proxy_options, background_writes, allow_bucket_creation, allow_bucket_deletion, connect_timeout, request_timeout)
+fs___S3FileSystem__create <- function(anonymous, access_key, secret_key, session_token, role_arn, session_name, external_id, load_frequency, region, endpoint_override, scheme, proxy_options, background_writes, allow_bucket_creation, allow_bucket_deletion, check_directory_existence_before_creation, connect_timeout, request_timeout) {
+  .Call(`_arrow_fs___S3FileSystem__create`, anonymous, access_key, secret_key, session_token, role_arn, session_name, external_id, load_frequency, region, endpoint_override, scheme, proxy_options, background_writes, allow_bucket_creation, allow_bucket_deletion, check_directory_existence_before_creation, connect_timeout, request_timeout)
 }
 
 fs___S3FileSystem__region <- function(fs) {
diff --git a/r/R/dplyr-funcs-datetime.R b/r/R/dplyr-funcs-datetime.R
index b8bc2b60638..77c6c9821e3 100644
--- a/r/R/dplyr-funcs-datetime.R
+++ b/r/R/dplyr-funcs-datetime.R
@@ -856,7 +856,8 @@ register_bindings_hms <- function() {
         Expression$create("multiply_checked", days, 86400)
 
       return(numeric_to_time32(total_secs))
-    }
+    },
+    notes = "subsecond times not supported"
   )
 
   register_binding(
@@ -880,6 +881,7 @@ register_bindings_hms <- function() {
         )
         return(datetime_to_time32(as_date_time))
       }
-    }
+    },
+    notes = "subsecond times not supported"
   )
 }
diff --git a/r/R/dplyr-funcs-doc.R b/r/R/dplyr-funcs-doc.R
index 64e4aab0f2c..7954cd55367 100644
--- a/r/R/dplyr-funcs-doc.R
+++ b/r/R/dplyr-funcs-doc.R
@@ -21,7 +21,7 @@
 #'
 #' The `arrow` package contains methods for 37 `dplyr` table functions, many of
 #' which are "verbs" that do transformations to one or more tables.
-#' The package also has mappings of 221 R functions to the corresponding
+#' The package also has mappings of 222 R functions to the corresponding
 #' functions in the Arrow compute library. These allow you to write code inside
 #' of `dplyr` methods that call R functions, including many in packages like
 #' `stringr` and `lubridate`, and they will get translated to Arrow and run
@@ -83,7 +83,7 @@
 #' Functions can be called either as `pkg::fun()` or just `fun()`, i.e. both
 #' `str_sub()` and `stringr::str_sub()` work.
 #'
-#' In addition to these functions, you can call any of Arrow's 271 compute
+#' In addition to these functions, you can call any of Arrow's 280 compute
 #' functions directly. Arrow has many functions that don't map to an existing R
 #' function. In other cases where there is an R function mapping, you can still
 #' call the Arrow function directly if you don't want the adaptations that the R
@@ -96,7 +96,6 @@
 #'
 #' * [`add_filename()`][arrow::add_filename()]
 #' * [`cast()`][arrow::cast()]
-#' * [`one()`][arrow::one()]
 #'
 #' ## base
 #'
@@ -215,6 +214,11 @@
 #' * [`n()`][dplyr::n()]
 #' * [`n_distinct()`][dplyr::n_distinct()]
 #'
+#' ## hms
+#'
+#' * [`as_hms()`][hms::as_hms()]
+#' * [`hms()`][hms::hms()]
+#'
 #' ## lubridate
 #'
 #' * [`am()`][lubridate::am()]
@@ -297,11 +301,6 @@
 #' * [`ymd_hms()`][lubridate::ymd_hms()]: `locale` argument not supported
 #' * [`yq()`][lubridate::yq()]: `locale` argument not supported
 #'
-#' ## hms
-#'
-#' * [`hms()`][hms::hms()]: subsecond times not supported
-#' * [`hms()`][hms::as_hms()]: subsecond times not supported
-#'
 #' ## methods
 #'
 #' * [`is()`][methods::is()]
diff --git a/r/R/filesystem.R b/r/R/filesystem.R
index 0176cdf846d..378e52bf741 100644
--- a/r/R/filesystem.R
+++ b/r/R/filesystem.R
@@ -156,6 +156,10 @@ FileSelector$create <- function(base_dir, allow_not_found = FALSE, recursive = F
 #'    buckets if `$CreateDir()` is called on the bucket level (default `FALSE`).
 #' - `allow_bucket_deletion`: logical, if TRUE, the filesystem will delete
 #'    buckets if`$DeleteDir()` is called on the bucket level (default `FALSE`).
+#' - `check_directory_existence_before_creation`: logical, check if directory
+#'    already exists or not before creation. Helpful for cloud storage operations
+#'    where object mutation operations are rate limited or existing directories
+#'    are read-only. (default `FALSE`).
 #' - `request_timeout`: Socket read time on Windows and macOS in seconds. If
 #'    negative, the AWS SDK default (typically 3 seconds).
 #' - `connect_timeout`: Socket connection timeout in seconds. If negative, AWS
@@ -411,7 +415,8 @@ S3FileSystem$create <- function(anonymous = FALSE, ...) {
     invalid_args <- intersect(
       c(
         "access_key", "secret_key", "session_token", "role_arn", "session_name",
-        "external_id", "load_frequency", "allow_bucket_creation", "allow_bucket_deletion"
+        "external_id", "load_frequency", "allow_bucket_creation", "allow_bucket_deletion",
+        "check_directory_existence_before_creation"
       ),
       names(args)
     )
@@ -459,6 +464,7 @@ default_s3_options <- list(
   background_writes = TRUE,
   allow_bucket_creation = FALSE,
   allow_bucket_deletion = FALSE,
+  check_directory_existence_before_creation = FALSE,
   connect_timeout = -1,
   request_timeout = -1
 )
diff --git a/r/data-raw/docgen.R b/r/data-raw/docgen.R
index 5f7f21b9029..45773d24659 100644
--- a/r/data-raw/docgen.R
+++ b/r/data-raw/docgen.R
@@ -149,6 +149,10 @@ tidyselect <- grep("^tidyselect::", readLines("R/reexports-tidyselect.R"), value
 # HACK: remove the _random_along UDF we're using (fix in ARROW-17974)
 docs[["_random_along"]] <- NULL
 
+# TODO - update the script to add this back in - will fail CI as tries to link
+# to non-existent function as arrow::one only exists as registered binding
+docs[["arrow::one"]] <- NULL
+
 docs <- c(docs, setNames(rep(list(NULL), length(tidyselect)), tidyselect))
 
 fun_df <- tibble::tibble(
diff --git a/r/man/FileSystem.Rd b/r/man/FileSystem.Rd
index dbf89ef1387..83e7fc65261 100644
--- a/r/man/FileSystem.Rd
+++ b/r/man/FileSystem.Rd
@@ -57,6 +57,10 @@ in the background, without blocking (default \code{TRUE})
 buckets if \verb{$CreateDir()} is called on the bucket level (default \code{FALSE}).
 \item \code{allow_bucket_deletion}: logical, if TRUE, the filesystem will delete
 buckets if\verb{$DeleteDir()} is called on the bucket level (default \code{FALSE}).
+\item \code{check_directory_existence_before_creation}: logical, check if directory
+already exists or not before creation. Helpful for cloud storage operations
+where object mutation operations are rate limited or existing directories
+are read-only. (default \code{FALSE}).
 \item \code{request_timeout}: Socket read time on Windows and macOS in seconds. If
 negative, the AWS SDK default (typically 3 seconds).
 \item \code{connect_timeout}: Socket connection timeout in seconds. If negative, AWS
diff --git a/r/man/acero.Rd b/r/man/acero.Rd
index 345bb099d5a..238a57bdd41 100644
--- a/r/man/acero.Rd
+++ b/r/man/acero.Rd
@@ -9,7 +9,7 @@
 \description{
 The \code{arrow} package contains methods for 37 \code{dplyr} table functions, many of
 which are "verbs" that do transformations to one or more tables.
-The package also has mappings of 212 R functions to the corresponding
+The package also has mappings of 222 R functions to the corresponding
 functions in the Arrow compute library. These allow you to write code inside
 of \code{dplyr} methods that call R functions, including many in packages like
 \code{stringr} and \code{lubridate}, and they will get translated to Arrow and run
@@ -29,7 +29,7 @@ Table into an R \code{tibble}.
 \item \code{\link[dplyr:compute]{collect()}}
 \item \code{\link[dplyr:compute]{compute()}}
 \item \code{\link[dplyr:count]{count()}}
-\item \code{\link[dplyr:distinct]{distinct()}}: \code{.keep_all = TRUE} not supported
+\item \code{\link[dplyr:distinct]{distinct()}}: \code{.keep_all = TRUE} returns a non-missing value if present, only returning missing values if all are missing.
 \item \code{\link[dplyr:explain]{explain()}}
 \item \code{\link[dplyr:filter]{filter()}}
 \item \code{\link[dplyr:mutate-joins]{full_join()}}: the \code{copy} argument is ignored
@@ -71,7 +71,7 @@ can assume that the function works in Acero just as it does in R.
 Functions can be called either as \code{pkg::fun()} or just \code{fun()}, i.e. both
 \code{str_sub()} and \code{stringr::str_sub()} work.
 
-In addition to these functions, you can call any of Arrow's 262 compute
+In addition to these functions, you can call any of Arrow's 280 compute
 functions directly. Arrow has many functions that don't map to an existing R
 function. In other cases where there is an R function mapping, you can still
 call the Arrow function directly if you don't want the adaptations that the R
@@ -108,6 +108,7 @@ as \code{arrow_ascii_is_decimal}.
 \item \code{\link[=^]{^}}
 \item \code{\link[base:MathFun]{abs()}}
 \item \code{\link[base:Trig]{acos()}}
+\item \code{\link[base:Hyperbolic]{acosh()}}
 \item \code{\link[base:all]{all()}}
 \item \code{\link[base:any]{any()}}
 \item \code{\link[base:as.Date]{as.Date()}}: Multiple \code{tryFormats} not supported in Arrow.
@@ -119,14 +120,19 @@ Consider using the lubridate specialised parsing functions \code{ymd()}, \code{y
 \item \code{\link[base:logical]{as.logical()}}
 \item \code{\link[base:numeric]{as.numeric()}}
 \item \code{\link[base:Trig]{asin()}}
+\item \code{\link[base:Hyperbolic]{asinh()}}
+\item \code{\link[base:Trig]{atan()}}
+\item \code{\link[base:Hyperbolic]{atanh()}}
 \item \code{\link[base:Round]{ceiling()}}
 \item \code{\link[base:Trig]{cos()}}
+\item \code{\link[base:Hyperbolic]{cosh()}}
 \item \code{\link[base:data.frame]{data.frame()}}: \code{row.names} and \code{check.rows} arguments not supported;
 \code{stringsAsFactors} must be \code{FALSE}
 \item \code{\link[base:difftime]{difftime()}}: only supports \code{units = "secs"} (the default);
 \code{tz} argument not supported
 \item \code{\link[base:startsWith]{endsWith()}}
 \item \code{\link[base:Log]{exp()}}
+\item \code{\link[base:Log]{expm1()}}
 \item \code{\link[base:Round]{floor()}}
 \item \code{\link[base:format]{format()}}
 \item \code{\link[base:grep]{grepl()}}
@@ -160,6 +166,7 @@ Consider using the lubridate specialised parsing functions \code{ymd()}, \code{y
 \item \code{\link[base:Round]{round()}}
 \item \code{\link[base:sign]{sign()}}
 \item \code{\link[base:Trig]{sin()}}
+\item \code{\link[base:Hyperbolic]{sinh()}}
 \item \code{\link[base:MathFun]{sqrt()}}
 \item \code{\link[base:startsWith]{startsWith()}}
 \item \code{\link[base:strptime]{strftime()}}
@@ -172,6 +179,7 @@ Valid values are "s", "ms" (default), "us", "ns".
 \item \code{\link[base:substr]{substring()}}
 \item \code{\link[base:sum]{sum()}}
 \item \code{\link[base:Trig]{tan()}}
+\item \code{\link[base:Hyperbolic]{tanh()}}
 \item \code{\link[base:chartr]{tolower()}}
 \item \code{\link[base:chartr]{toupper()}}
 \item \code{\link[base:Round]{trunc()}}
@@ -201,6 +209,13 @@ Valid values are "s", "ms" (default), "us", "ns".
 }
 }
 
+\subsection{hms}{
+\itemize{
+\item \code{\link[hms:hms]{as_hms()}}
+\item \code{\link[hms:hms]{hms()}}
+}
+}
+
 \subsection{lubridate}{
 \itemize{
 \item \code{\link[lubridate:am]{am()}}
@@ -285,13 +300,6 @@ On Linux and OS X additionally a, A, b, B, Om, p, r are available.
 }
 }
 
-\subsection{hms}{
-\itemize{
-\item \code{\link[hms:hms]{hms()}}: subsecond times not supported
-\item \code{\link[hms:hms]{hms()}}: subsecond times not supported
-}
-}
-
 \subsection{methods}{
 \itemize{
 \item \code{\link[methods:is]{is()}}
diff --git a/r/src/arrowExports.cpp b/r/src/arrowExports.cpp
index d5aec50219e..e75d38a303f 100644
--- a/r/src/arrowExports.cpp
+++ b/r/src/arrowExports.cpp
@@ -3521,8 +3521,8 @@ END_CPP11
 }
 // filesystem.cpp
 #if defined(ARROW_R_WITH_S3)
-std::shared_ptr<fs::S3FileSystem> fs___S3FileSystem__create(bool anonymous, std::string access_key, std::string secret_key, std::string session_token, std::string role_arn, std::string session_name, std::string external_id, int load_frequency, std::string region, std::string endpoint_override, std::string scheme, std::string proxy_options, bool background_writes, bool allow_bucket_creation, bool allow_bucket_deletion, double connect_timeout, double request_timeout);
-extern "C" SEXP _arrow_fs___S3FileSystem__create(SEXP anonymous_sexp, SEXP access_key_sexp, SEXP secret_key_sexp, SEXP session_token_sexp, SEXP role_arn_sexp, SEXP session_name_sexp, SEXP external_id_sexp, SEXP load_frequency_sexp, SEXP region_sexp, SEXP endpoint_override_sexp, SEXP scheme_sexp, SEXP proxy_options_sexp, SEXP background_writes_sexp, SEXP allow_bucket_creation_sexp, SEXP allow_bucket_deletion_sexp, SEXP connect_timeout_sexp, SEXP request_timeout_sexp){
+std::shared_ptr<fs::S3FileSystem> fs___S3FileSystem__create(bool anonymous, std::string access_key, std::string secret_key, std::string session_token, std::string role_arn, std::string session_name, std::string external_id, int load_frequency, std::string region, std::string endpoint_override, std::string scheme, std::string proxy_options, bool background_writes, bool allow_bucket_creation, bool allow_bucket_deletion, bool check_directory_existence_before_creation, double connect_timeout, double request_timeout);
+extern "C" SEXP _arrow_fs___S3FileSystem__create(SEXP anonymous_sexp, SEXP access_key_sexp, SEXP secret_key_sexp, SEXP session_token_sexp, SEXP role_arn_sexp, SEXP session_name_sexp, SEXP external_id_sexp, SEXP load_frequency_sexp, SEXP region_sexp, SEXP endpoint_override_sexp, SEXP scheme_sexp, SEXP proxy_options_sexp, SEXP background_writes_sexp, SEXP allow_bucket_creation_sexp, SEXP allow_bucket_deletion_sexp, SEXP check_directory_existence_before_creation_sexp, SEXP connect_timeout_sexp, SEXP request_timeout_sexp){
 BEGIN_CPP11
 	arrow::r::Input<bool>::type anonymous(anonymous_sexp);
 	arrow::r::Input<std::string>::type access_key(access_key_sexp);
@@ -3539,13 +3539,14 @@ BEGIN_CPP11
 	arrow::r::Input<bool>::type background_writes(background_writes_sexp);
 	arrow::r::Input<bool>::type allow_bucket_creation(allow_bucket_creation_sexp);
 	arrow::r::Input<bool>::type allow_bucket_deletion(allow_bucket_deletion_sexp);
+	arrow::r::Input<bool>::type check_directory_existence_before_creation(check_directory_existence_before_creation_sexp);
 	arrow::r::Input<double>::type connect_timeout(connect_timeout_sexp);
 	arrow::r::Input<double>::type request_timeout(request_timeout_sexp);
-	return cpp11::as_sexp(fs___S3FileSystem__create(anonymous, access_key, secret_key, session_token, role_arn, session_name, external_id, load_frequency, region, endpoint_override, scheme, proxy_options, background_writes, allow_bucket_creation, allow_bucket_deletion, connect_timeout, request_timeout));
+	return cpp11::as_sexp(fs___S3FileSystem__create(anonymous, access_key, secret_key, session_token, role_arn, session_name, external_id, load_frequency, region, endpoint_override, scheme, proxy_options, background_writes, allow_bucket_creation, allow_bucket_deletion, check_directory_existence_before_creation, connect_timeout, request_timeout));
 END_CPP11
 }
 #else
-extern "C" SEXP _arrow_fs___S3FileSystem__create(SEXP anonymous_sexp, SEXP access_key_sexp, SEXP secret_key_sexp, SEXP session_token_sexp, SEXP role_arn_sexp, SEXP session_name_sexp, SEXP external_id_sexp, SEXP load_frequency_sexp, SEXP region_sexp, SEXP endpoint_override_sexp, SEXP scheme_sexp, SEXP proxy_options_sexp, SEXP background_writes_sexp, SEXP allow_bucket_creation_sexp, SEXP allow_bucket_deletion_sexp, SEXP connect_timeout_sexp, SEXP request_timeout_sexp){
+extern "C" SEXP _arrow_fs___S3FileSystem__create(SEXP anonymous_sexp, SEXP access_key_sexp, SEXP secret_key_sexp, SEXP session_token_sexp, SEXP role_arn_sexp, SEXP session_name_sexp, SEXP external_id_sexp, SEXP load_frequency_sexp, SEXP region_sexp, SEXP endpoint_override_sexp, SEXP scheme_sexp, SEXP proxy_options_sexp, SEXP background_writes_sexp, SEXP allow_bucket_creation_sexp, SEXP allow_bucket_deletion_sexp, SEXP check_directory_existence_before_creation_sexp, SEXP connect_timeout_sexp, SEXP request_timeout_sexp){
 	Rf_error("Cannot call fs___S3FileSystem__create(). See https://arrow.apache.org/docs/r/articles/install.html for help installing Arrow C++ libraries. ");
 }
 #endif
@@ -6013,7 +6014,7 @@ static const R_CallMethodDef CallEntries[] = {
 		{ "_arrow_fs___SubTreeFileSystem__base_path", (DL_FUNC) &_arrow_fs___SubTreeFileSystem__base_path, 1}, 
 		{ "_arrow_fs___FileSystemFromUri", (DL_FUNC) &_arrow_fs___FileSystemFromUri, 1}, 
 		{ "_arrow_fs___CopyFiles", (DL_FUNC) &_arrow_fs___CopyFiles, 6}, 
-		{ "_arrow_fs___S3FileSystem__create", (DL_FUNC) &_arrow_fs___S3FileSystem__create, 17}, 
+		{ "_arrow_fs___S3FileSystem__create", (DL_FUNC) &_arrow_fs___S3FileSystem__create, 18}, 
 		{ "_arrow_fs___S3FileSystem__region", (DL_FUNC) &_arrow_fs___S3FileSystem__region, 1}, 
 		{ "_arrow_FinalizeS3", (DL_FUNC) &_arrow_FinalizeS3, 0}, 
 		{ "_arrow_fs___GcsFileSystem__Make", (DL_FUNC) &_arrow_fs___GcsFileSystem__Make, 2}, 
diff --git a/r/src/filesystem.cpp b/r/src/filesystem.cpp
index f133013d20f..f553bee7e90 100644
--- a/r/src/filesystem.cpp
+++ b/r/src/filesystem.cpp
@@ -289,7 +289,8 @@ std::shared_ptr<fs::S3FileSystem> fs___S3FileSystem__create(
     std::string region = "", std::string endpoint_override = "", std::string scheme = "",
     std::string proxy_options = "", bool background_writes = true,
     bool allow_bucket_creation = false, bool allow_bucket_deletion = false,
-    double connect_timeout = -1, double request_timeout = -1) {
+    bool check_directory_existence_before_creation = false, double connect_timeout = -1,
+    double request_timeout = -1) {
   // We need to ensure that S3 is initialized before we start messing with the
   // options
   StopIfNotOk(fs::EnsureS3Initialized());
@@ -331,6 +332,9 @@ std::shared_ptr<fs::S3FileSystem> fs___S3FileSystem__create(
   s3_opts.allow_bucket_creation = allow_bucket_creation;
   s3_opts.allow_bucket_deletion = allow_bucket_deletion;
 
+  s3_opts.check_directory_existence_before_creation =
+      check_directory_existence_before_creation;
+
   s3_opts.request_timeout = request_timeout;
   s3_opts.connect_timeout = connect_timeout;
 
diff --git a/r/tests/testthat/test-s3-minio.R b/r/tests/testthat/test-s3-minio.R
index 8dfac634716..99219f2a818 100644
--- a/r/tests/testthat/test-s3-minio.R
+++ b/r/tests/testthat/test-s3-minio.R
@@ -46,7 +46,8 @@ fs <- S3FileSystem$create(
   scheme = "http",
   endpoint_override = paste0("localhost:", minio_port),
   allow_bucket_creation = TRUE,
-  allow_bucket_deletion = TRUE
+  allow_bucket_deletion = TRUE,
+  check_directory_existence_before_creation = TRUE
 )
 limited_fs <- S3FileSystem$create(
   access_key = minio_key,
@@ -54,7 +55,8 @@ limited_fs <- S3FileSystem$create(
   scheme = "http",
   endpoint_override = paste0("localhost:", minio_port),
   allow_bucket_creation = FALSE,
-  allow_bucket_deletion = FALSE
+  allow_bucket_deletion = FALSE,
+  check_directory_existence_before_creation = FALSE
 )
 now <- as.character(as.numeric(Sys.time()))
 fs$CreateDir(now)
diff --git a/r/vignettes/fs.Rmd b/r/vignettes/fs.Rmd
index 50278af25bd..07476877c5b 100644
--- a/r/vignettes/fs.Rmd
+++ b/r/vignettes/fs.Rmd
@@ -190,7 +190,7 @@ Also note that parameters in the URI need to be
 
 For S3, only the following options can be included in the URI as query parameters
 are `region`, `scheme`, `endpoint_override`, `access_key`, `secret_key`, `allow_bucket_creation`,
-and `allow_bucket_deletion`. For GCS, the supported parameters are `scheme`, `endpoint_override`,
+`allow_bucket_deletion` and `check_directory_existence_before_creation`. For GCS, the supported parameters are `scheme`, `endpoint_override`,
 and `retry_limit_seconds`.
 
 In GCS, a useful option is `retry_limit_seconds`, which sets the number of seconds