Conventional recommender systems operate within platform-specific catalogs, limiting access to potentially valuable resources across platforms. We propose user-centered agentic recommendation, a paradigm in which user agents compare recommendations from competing platform agents, and formalize their interaction as a repeated game. Platforms strategically modify descriptions without changing intrinsic item value, while each user agent assesses platform credibility using feedback from consumed items only. Our analysis shows that expanded resource access need not improve user welfare: strategic misrepresentation and limited verification can offset the benefits of platform competition. We quantify when platform credibility assessment allows users to benefit from broader access despite strategic exaggeration. Our analysis identifies resource and reporting conditions that guarantee higher average welfare than the original platform with an interaction budget linear in platform count. Experiments on synthetic and Amazon-grounded markets show that credibility assessment can improve finite-horizon utility, while its benefits depend on market size and mechanism parameters.
Figures & tables
Figure 1: Interaction for user j in round t . The UA compares recommendations from multiple PAs; after consumption, only its credibility record for the selected platform is updated.
Figure 2: Synthetic markets under learning PAs: gains across market widths at T=4096 (left) and cumulative average net utility at n=16 (right).
Figure 3: Amazon semantic markets under learning PAs: gains across market widths at T=4096 (left) and cumulative average net utility at n=16 (right).
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
Table 4
Market
ν
Calibrated gain
Actual net gain
95% CI
Distortion
Synthetic
0.03
165.2
99.8
[89.8,109.8]
65.4
0.10
92.5
48.3
[39.0,57.6]
44.2
0.30
4.4
−11.9
[−20.3,−3.6]
16.3
Amazon
0.03
12.8
6.1
[−1.9,14.1]
6.7
0.10
−6.6
−7.8
[−16.0,0.4]
1.2
0.30
−12.9
−13.3
[−21.8,−4.9]
0.4
Appendix
Table 3: Choice-temperature sensitivity with Exp3 PAs and credibility assessment, at n=16 , T=4096 and η=0.2 . Value columns are in units of 10−3 . Means and pointwise 95% intervals for actual net gain use 12 seeds.
Setting
Calibrated gain
Observed net gain
Certified lower bound
Certified rounds
Base
0.493
0.466
0.094
1,465
n=4
0.496
0.491
0.137
357
n=32
0.489
0.433
0.036
3,034
h=0.60
0.140
0.120
−0.305
—
h=0.75
0.327
0.301
−0.084
—
a=0
0.493
0.465
0.316
582
Appendix
Table 4: Observed net utility and theoretical guarantees in the controlled synthetic market at T=4096 . The base is (n,h,a)=(16,0.9,0.05) ; other rows change one parameter. Lower bounds are rounded down. All observed-net-gain interval half-widths are below 0.0001 over 12 seeds. A dash means no finite positive-gain budget is certified.