diff --git a/lib/OptimizationAuglag/src/OptimizationAuglag.jl b/lib/OptimizationAuglag/src/OptimizationAuglag.jl
index 3ce0df17d..37c6a1a80 100644
--- a/lib/OptimizationAuglag/src/OptimizationAuglag.jl
+++ b/lib/OptimizationAuglag/src/OptimizationAuglag.jl
@@ -17,6 +17,7 @@ using LinearAlgebra: norm
 end
 
 SciMLBase.has_init(::AugLag) = true
+SciMLBase.allowscallback(::AugLag) = true
 SciMLBase.allowsbounds(::AugLag) = true
 SciMLBase.requiresgradient(::AugLag) = true
 SciMLBase.allowsconstraints(::AugLag) = true
diff --git a/lib/OptimizationBBO/src/OptimizationBBO.jl b/lib/OptimizationBBO/src/OptimizationBBO.jl
index 59e507f26..ed244ab9d 100644
--- a/lib/OptimizationBBO/src/OptimizationBBO.jl
+++ b/lib/OptimizationBBO/src/OptimizationBBO.jl
@@ -9,7 +9,7 @@ abstract type BBO end
 
 SciMLBase.requiresbounds(::BBO) = true
 SciMLBase.allowsbounds(::BBO) = true
-
+SciMLBase.allowscallback(opt::BBO) = true
 SciMLBase.has_init(opt::BBO) = true
 
 for j in string.(BlackBoxOptim.SingleObjectiveMethodNames)
diff --git a/lib/OptimizationBase/src/solve.jl b/lib/OptimizationBase/src/solve.jl
index cd1a80607..777ca1d8f 100644
--- a/lib/OptimizationBase/src/solve.jl
+++ b/lib/OptimizationBase/src/solve.jl
@@ -123,7 +123,7 @@ function _check_opt_alg(prob::SciMLBase.OptimizationProblem, alg; kwargs...)
         (isnothing(prob.lcons) || isnothing(prob.ucons)) &&
         throw(ArgumentError("Constrained optimization problem requires both `lcons` and `ucons` to be provided to OptimizationProblem. " *
                             "Example: OptimizationProblem(optf, u0, p; lcons=[-Inf], ucons=[0.0])"))
-    !allowscallback(alg) && haskey(kwargs, :callback) &&
+    !allowscallback(alg) && !(get(kwargs, :callback, DEFAULT_CALLBACK) isa NullCallback) &&
         throw(IncompatibleOptimizerError("The algorithm $(typeof(alg)) does not support callbacks, remove the `callback` keyword argument from the `solve` call."))
     requiresgradient(alg) &&
         !(prob.f isa SciMLBase.AbstractOptimizationFunction) &&
diff --git a/lib/OptimizationCMAEvolutionStrategy/src/OptimizationCMAEvolutionStrategy.jl b/lib/OptimizationCMAEvolutionStrategy/src/OptimizationCMAEvolutionStrategy.jl
index 9d372569b..ea1b58284 100644
--- a/lib/OptimizationCMAEvolutionStrategy/src/OptimizationCMAEvolutionStrategy.jl
+++ b/lib/OptimizationCMAEvolutionStrategy/src/OptimizationCMAEvolutionStrategy.jl
@@ -9,6 +9,7 @@ export CMAEvolutionStrategyOpt
 
 struct CMAEvolutionStrategyOpt end
 
+SciMLBase.allowscallback(opt::CMAEvolutionStrategyOpt) = true
 SciMLBase.allowsbounds(::CMAEvolutionStrategyOpt) = true
 SciMLBase.has_init(opt::CMAEvolutionStrategyOpt) = true
 SciMLBase.requiresgradient(::CMAEvolutionStrategyOpt) = false
diff --git a/lib/OptimizationEvolutionary/src/OptimizationEvolutionary.jl b/lib/OptimizationEvolutionary/src/OptimizationEvolutionary.jl
index 6e4395e91..db5a5e46a 100644
--- a/lib/OptimizationEvolutionary/src/OptimizationEvolutionary.jl
+++ b/lib/OptimizationEvolutionary/src/OptimizationEvolutionary.jl
@@ -4,6 +4,7 @@ using Reexport
 @reexport using Evolutionary, OptimizationBase
 using SciMLBase
 
+SciMLBase.allowscallback(opt::Evolutionary.AbstractOptimizer) = true
 SciMLBase.allowsbounds(opt::Evolutionary.AbstractOptimizer) = true
 SciMLBase.allowsconstraints(opt::Evolutionary.AbstractOptimizer) = true
 SciMLBase.has_init(opt::Evolutionary.AbstractOptimizer) = true
diff --git a/lib/OptimizationGCMAES/src/OptimizationGCMAES.jl b/lib/OptimizationGCMAES/src/OptimizationGCMAES.jl
index 84b0602be..8282cc306 100644
--- a/lib/OptimizationGCMAES/src/OptimizationGCMAES.jl
+++ b/lib/OptimizationGCMAES/src/OptimizationGCMAES.jl
@@ -48,12 +48,8 @@ function __map_optimizer_args(cache::OptimizationBase.OptimizationCache, opt::GC
 end
 
 function SciMLBase.__init(prob::SciMLBase.OptimizationProblem,
-        opt::GCMAESOpt; σ0 = 0.2,
-        callback = (args...) -> (false),
-        progress = false, kwargs...)
-    return OptimizationCache(prob, opt; σ0 = σ0, callback = callback,
-        progress = progress,
-        kwargs...)
+        opt::GCMAESOpt; σ0 = 0.2, kwargs...)
+    return OptimizationCache(prob, opt; σ0 = σ0, kwargs...)
 end
 
 function SciMLBase.__solve(cache::OptimizationCache{O}) where {O <: GCMAESOpt}
diff --git a/lib/OptimizationIpopt/src/OptimizationIpopt.jl b/lib/OptimizationIpopt/src/OptimizationIpopt.jl
index 719d41c08..6d4dbb648 100644
--- a/lib/OptimizationIpopt/src/OptimizationIpopt.jl
+++ b/lib/OptimizationIpopt/src/OptimizationIpopt.jl
@@ -170,6 +170,8 @@ function SciMLBase.has_init(alg::IpoptOptimizer)
     true
 end
 
+SciMLBase.allowscallback(alg::IpoptOptimizer) = true
+
 # Compatibility with OptimizationBase@v3
 function SciMLBase.supports_opt_cache_interface(alg::IpoptOptimizer)
     true
@@ -254,7 +256,8 @@ function __map_optimizer_args(cache,
     )
 
     # Set up progress callback
-    progress_callback = IpoptProgressLogger(progress, callback, prob, cache.n, cache.num_cons, maxiters, cache.iterations)
+    progress_callback = IpoptProgressLogger(
+        progress, callback, prob, cache.n, cache.num_cons, maxiters, cache.iterations)
     intermediate = (args...) -> progress_callback(args...)
     Ipopt.SetIntermediateCallback(prob, intermediate)
 
diff --git a/lib/OptimizationLBFGSB/src/OptimizationLBFGSB.jl b/lib/OptimizationLBFGSB/src/OptimizationLBFGSB.jl
index 4d8a26771..f342c0345 100644
--- a/lib/OptimizationLBFGSB/src/OptimizationLBFGSB.jl
+++ b/lib/OptimizationLBFGSB/src/OptimizationLBFGSB.jl
@@ -31,6 +31,7 @@ References
     ϵ = 1e-8
 end
 
+SciMLBase.allowscallback(::LBFGSB) = true
 SciMLBase.has_init(::LBFGSB) = true
 SciMLBase.allowsbounds(::LBFGSB) = true
 SciMLBase.requiresgradient(::LBFGSB) = true
diff --git a/lib/OptimizationMOI/src/OptimizationMOI.jl b/lib/OptimizationMOI/src/OptimizationMOI.jl
index 4d3ead8e6..1678424a1 100644
--- a/lib/OptimizationMOI/src/OptimizationMOI.jl
+++ b/lib/OptimizationMOI/src/OptimizationMOI.jl
@@ -288,6 +288,11 @@ function SciMLBase.has_init(alg::Union{MOI.AbstractOptimizer,
     true
 end
 
+function SciMLBase.allowscallback(alg::Union{MOI.AbstractOptimizer,
+        MOI.OptimizerWithAttributes})
+    true
+end
+
 # Compatibility with OptimizationBase@v3
 function SciMLBase.supports_opt_cache_interface(alg::Union{MOI.AbstractOptimizer,
         MOI.OptimizerWithAttributes})
diff --git a/lib/OptimizationMadNLP/Project.toml b/lib/OptimizationMadNLP/Project.toml
index 22e009448..637320c4d 100644
--- a/lib/OptimizationMadNLP/Project.toml
+++ b/lib/OptimizationMadNLP/Project.toml
@@ -30,6 +30,7 @@ julia = "1.10"
 OptimizationBase = {path = "../OptimizationBase"}
 
 [extras]
+ADTypes = "47edcb42-4c32-4615-8424-f2b9edc5f35b"
 Aqua = "4c88cf16-eb10-579e-8560-4a9242c79595"
 DifferentiationInterface = "a0c0ee7d-e4b9-4e03-894e-1c5f64a51d63"
 ForwardDiff = "f6369f11-7733-5829-9624-2563aa707210"
@@ -41,4 +42,4 @@ Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 Zygote = "e88e6eb3-aa80-5325-afca-941959d7151f"
 
 [targets]
-test = ["Aqua", "DifferentiationInterface", "ForwardDiff", "ModelingToolkit", "Random", "ReverseDiff", "Test", "Symbolics", "Zygote"]
+test = ["ADTypes", "Aqua", "DifferentiationInterface", "ForwardDiff", "ModelingToolkit", "Random", "ReverseDiff", "Test", "Symbolics", "Zygote"]
diff --git a/lib/OptimizationMadNLP/src/OptimizationMadNLP.jl b/lib/OptimizationMadNLP/src/OptimizationMadNLP.jl
index b71c1178b..70a53a94e 100644
--- a/lib/OptimizationMadNLP/src/OptimizationMadNLP.jl
+++ b/lib/OptimizationMadNLP/src/OptimizationMadNLP.jl
@@ -231,6 +231,10 @@ end
     hessian_constant::Bool = false
     hessian_approximation::Type = MadNLP.ExactHessian
 
+    # Initialization Options
+    nlp_scaling::Bool = true
+    nlp_scaling_max_gradient::Float64 = 100.0
+
     # Linear solver configuration
     linear_solver::Union{Nothing, Type} = nothing  # e.g., MumpsSolver, LapackCPUSolver, UmfpackSolver
 
@@ -247,6 +251,8 @@ end
 
 SciMLBase.has_init(opt::MadNLPOptimizer) = true
 
+SciMLBase.allowscallback(opt::MadNLPOptimizer) = false
+
 function SciMLBase.requiresgradient(opt::MadNLPOptimizer)
     true
 end
@@ -343,7 +349,7 @@ function __map_optimizer_args(cache,
     nvar = length(cache.u0)
     ncon = !isnothing(cache.lcons) ? length(cache.lcons) : 0
 
-    if callback !== DEFAULT_CALLBACK || progress
+    if !(callback isa OptimizationBase.NullCallback) || progress
         @warn("MadNLP doesn't currently support user defined callbacks.")
     end
     # TODO: add support for user callbacks in MadNLP
@@ -374,7 +380,7 @@ function __map_optimizer_args(cache,
         print_level = verbose
     end
 
-    !isnothing(reltol) && @warn "reltol not supported by MadNLP."
+    !isnothing(reltol) && @warn "reltol not supported by MadNLP, use abstol instead."
     tol = isnothing(abstol) ? 1e-8 : abstol
     max_iter = isnothing(maxiters) ? 3000 : maxiters
     max_wall_time = isnothing(maxtime) ? 1e6 : maxtime
@@ -411,6 +417,8 @@ function __map_optimizer_args(cache,
     options[:jacobian_constant] = opt.jacobian_constant
     options[:hessian_constant] = opt.hessian_constant
     options[:hessian_approximation] = opt.hessian_approximation
+    options[:nlp_scaling] = opt.nlp_scaling
+    options[:nlp_scaling_max_gradient] = opt.nlp_scaling_max_gradient
     options[:print_level] = print_level
     options[:tol] = tol
     options[:max_iter] = max_iter
@@ -422,6 +430,7 @@ end
 function SciMLBase.__solve(cache::OptimizationCache{O}) where {O <: MadNLPOptimizer}
     maxiters = OptimizationBase._check_and_convert_maxiters(cache.solver_args.maxiters)
     maxtime = OptimizationBase._check_and_convert_maxtime(cache.solver_args.maxtime)
+    maxtime = maxtime isa Float32 ? convert(Float64, maxtime) : maxtime
 
     meta, options = __map_optimizer_args(cache,
         cache.opt;
diff --git a/lib/OptimizationMadNLP/test/runtests.jl b/lib/OptimizationMadNLP/test/runtests.jl
index da2d21cbf..7be5e153d 100644
--- a/lib/OptimizationMadNLP/test/runtests.jl
+++ b/lib/OptimizationMadNLP/test/runtests.jl
@@ -2,6 +2,7 @@ using OptimizationMadNLP
 using OptimizationBase
 using MadNLP
 using Test
+using ADTypes
 import Zygote, ForwardDiff, ReverseDiff
 using SparseArrays
 using DifferentiationInterface: SecondOrder
@@ -497,7 +498,7 @@ end
             @test min_dist > 0.5  # Electrons should be well-separated
         end
 
-        @testset verbose = true "LBFGS vs Exact Hessian" begin
+        @testset verbose=true "LBFGS vs Exact Hessian" begin
             # Test with moderate size to show LBFGS efficiency
             np = 10  # Gyroelongated square dipyramid configuration
             x0 = init_electrons_on_sphere(np)
@@ -525,11 +526,12 @@ end
                 )
 
                 sol = solve(prob, opt; abstol = 1e-6, maxiters = 300, verbose = false)
-                push!(results, name => (
-                    objective = sol.objective,
-                    iterations = sol.stats.iterations,
-                    success = SciMLBase.successful_retcode(sol)
-                ))
+                push!(results,
+                    name => (
+                        objective = sol.objective,
+                        iterations = sol.stats.iterations,
+                        success = SciMLBase.successful_retcode(sol)
+                    ))
             end
 
             # All methods should converge
diff --git a/lib/OptimizationManopt/src/OptimizationManopt.jl b/lib/OptimizationManopt/src/OptimizationManopt.jl
index 8bee9abac..5b97f0035 100644
--- a/lib/OptimizationManopt/src/OptimizationManopt.jl
+++ b/lib/OptimizationManopt/src/OptimizationManopt.jl
@@ -13,6 +13,7 @@ internal state.
 abstract type AbstractManoptOptimizer end
 
 SciMLBase.has_init(opt::AbstractManoptOptimizer) = true
+SciMLBase.allowscallback(opt::AbstractManoptOptimizer) = true
 
 function __map_optimizer_args!(cache::OptimizationBase.OptimizationCache,
         opt::AbstractManoptOptimizer;
diff --git a/lib/OptimizationNLopt/src/OptimizationNLopt.jl b/lib/OptimizationNLopt/src/OptimizationNLopt.jl
index eea9f4791..7dc6f8168 100644
--- a/lib/OptimizationNLopt/src/OptimizationNLopt.jl
+++ b/lib/OptimizationNLopt/src/OptimizationNLopt.jl
@@ -9,6 +9,7 @@ using OptimizationBase: deduce_retcode
 
 SciMLBase.allowsbounds(opt::Union{NLopt.Algorithm, NLopt.Opt}) = true
 SciMLBase.has_init(opt::Union{NLopt.Algorithm, NLopt.Opt}) = true
+SciMLBase.allowscallback(opt::Union{NLopt.Algorithm, NLopt.Opt}) = true
 
 function SciMLBase.requiresgradient(opt::Union{NLopt.Algorithm, NLopt.Opt})
     # https://github.com/JuliaOpt/NLopt.jl/blob/master/src/NLopt.jl#L18C7-L18C16
diff --git a/lib/OptimizationOptimJL/src/OptimizationOptimJL.jl b/lib/OptimizationOptimJL/src/OptimizationOptimJL.jl
index cdd25f430..d94e8353d 100644
--- a/lib/OptimizationOptimJL/src/OptimizationOptimJL.jl
+++ b/lib/OptimizationOptimJL/src/OptimizationOptimJL.jl
@@ -16,6 +16,10 @@ SciMLBase.has_init(opt::Optim.AbstractOptimizer) = true
 SciMLBase.has_init(opt::Union{Optim.Fminbox, Optim.SAMIN}) = true
 SciMLBase.has_init(opt::Optim.ConstrainedOptimizer) = true
 
+SciMLBase.allowscallback(opt::Optim.AbstractOptimizer) = true
+SciMLBase.allowscallback(opt::Union{Optim.Fminbox, Optim.SAMIN}) = true
+SciMLBase.allowscallback(opt::Optim.ConstrainedOptimizer) = true
+
 function SciMLBase.requiresgradient(opt::Optim.AbstractOptimizer)
     !(opt isa Optim.ZerothOrderOptimizer)
 end
@@ -39,8 +43,9 @@ function __map_optimizer_args(cache::OptimizationBase.OptimizationCache,
         maxtime::Union{Number, Nothing} = nothing,
         abstol::Union{Number, Nothing} = nothing,
         reltol::Union{Number, Nothing} = nothing,
+        verbose = false,
         kwargs...)
-    mapped_args = (; extended_trace = true, kwargs...)
+    mapped_args = (; extended_trace = true, show_trace = verbose, kwargs...)
 
     if !isnothing(abstol)
         mapped_args = (; mapped_args..., f_abstol = abstol)
diff --git a/lib/OptimizationOptimisers/src/OptimizationOptimisers.jl b/lib/OptimizationOptimisers/src/OptimizationOptimisers.jl
index 2476e5743..990234640 100644
--- a/lib/OptimizationOptimisers/src/OptimizationOptimisers.jl
+++ b/lib/OptimizationOptimisers/src/OptimizationOptimisers.jl
@@ -7,6 +7,7 @@ using SciMLBase
 SciMLBase.has_init(opt::AbstractRule) = true
 SciMLBase.requiresgradient(opt::AbstractRule) = true
 SciMLBase.allowsfg(opt::AbstractRule) = true
+SciMLBase.allowscallback(opt::AbstractRule) = true
 
 function SciMLBase.__init(
         prob::SciMLBase.OptimizationProblem, opt::AbstractRule;
@@ -67,7 +68,6 @@ function SciMLBase.__solve(cache::OptimizationCache{O}) where {O <: AbstractRule
     breakall = false
     progress_id = :OptimizationOptimizersJL
     for epoch in 1:epochs, d in data
-
         if cache.f.fg !== nothing && dataiterate
             x = cache.f.fg(G, θ, d)
             iterations += 1
@@ -107,7 +107,7 @@ function SciMLBase.__solve(cache::OptimizationCache{O}) where {O <: AbstractRule
         if cache.progress
             message = "Loss: $(round(first(first(x)); digits = 3))"
             @logmsg(LogLevel(-1), "Optimization", _id=progress_id,
-                message=message, progress=iterations/maxiters)
+                message=message, progress=iterations / maxiters)
         end
         if cache.solver_args.save_best
             if first(x)[1] < first(min_err)[1]  #found a better solution
diff --git a/lib/OptimizationPRIMA/src/OptimizationPRIMA.jl b/lib/OptimizationPRIMA/src/OptimizationPRIMA.jl
index 7dba5752b..e08860f5f 100644
--- a/lib/OptimizationPRIMA/src/OptimizationPRIMA.jl
+++ b/lib/OptimizationPRIMA/src/OptimizationPRIMA.jl
@@ -14,6 +14,7 @@ struct COBYLA <: PRIMASolvers end
 export UOBYQA, NEWUOA, BOBYQA, LINCOA, COBYLA
 
 SciMLBase.has_init(::PRIMASolvers) = true
+SciMLBase.allowscallback(::PRIMASolvers) = true
 SciMLBase.allowsconstraints(::Union{LINCOA, COBYLA}) = true
 SciMLBase.allowsbounds(opt::Union{BOBYQA, LINCOA, COBYLA}) = true
 SciMLBase.requiresconstraints(opt::COBYLA) = true
diff --git a/lib/OptimizationPolyalgorithms/src/OptimizationPolyalgorithms.jl b/lib/OptimizationPolyalgorithms/src/OptimizationPolyalgorithms.jl
index b03cd88b0..092f202fb 100644
--- a/lib/OptimizationPolyalgorithms/src/OptimizationPolyalgorithms.jl
+++ b/lib/OptimizationPolyalgorithms/src/OptimizationPolyalgorithms.jl
@@ -6,6 +6,7 @@ using SciMLBase, OptimizationOptimJL, OptimizationOptimisers
 
 struct PolyOpt end
 
+SciMLBase.allowscallback(::PolyOpt) = SciMLBase.allowscallback(Optimisers.Adam) && SciMLBase.allowscallback(OptimizationOptimJL.BFGS)
 SciMLBase.requiresgradient(opt::PolyOpt) = true
 
 function SciMLBase.__solve(prob::OptimizationProblem,
diff --git a/lib/OptimizationSciPy/src/OptimizationSciPy.jl b/lib/OptimizationSciPy/src/OptimizationSciPy.jl
index 0ac3f589b..43e39a799 100644
--- a/lib/OptimizationSciPy/src/OptimizationSciPy.jl
+++ b/lib/OptimizationSciPy/src/OptimizationSciPy.jl
@@ -216,6 +216,7 @@ for opt_type in [:ScipyMinimize, :ScipyDifferentialEvolution, :ScipyBasinhopping
     :ScipyLinprog, :ScipyMilp]
     @eval begin
         SciMLBase.allowsbounds(::$opt_type) = true
+        SciMLBase.allowscallback(::$opt_type) = true
         SciMLBase.has_init(::$opt_type) = true
     end
 end
@@ -223,10 +224,12 @@ end
 for opt_type in [:ScipyMinimizeScalar, :ScipyRootScalar, :ScipyLeastSquares]
     @eval begin
         SciMLBase.has_init(::$opt_type) = true
+        SciMLBase.allowscallback(::$opt_type) = true
     end
 end
 
 SciMLBase.has_init(::ScipyRoot) = true
+SciMLBase.allowscallback(::ScipyRoot) = true
 
 function SciMLBase.requiresgradient(opt::ScipyMinimize)
     gradient_free = ["Nelder-Mead", "Powell", "COBYLA", "COBYQA"]
diff --git a/lib/OptimizationSophia/src/OptimizationSophia.jl b/lib/OptimizationSophia/src/OptimizationSophia.jl
index e68702af6..93a2e8831 100644
--- a/lib/OptimizationSophia/src/OptimizationSophia.jl
+++ b/lib/OptimizationSophia/src/OptimizationSophia.jl
@@ -62,6 +62,7 @@ struct Sophia
 end
 
 SciMLBase.has_init(opt::Sophia) = true
+SciMLBase.allowscallback(opt::Sophia) = true
 SciMLBase.requiresgradient(opt::Sophia) = true
 SciMLBase.allowsfg(opt::Sophia) = true
 SciMLBase.requireshessian(opt::Sophia) = true