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.
Online recommendation has traditionally taken place after a user enters a platform, which determines the candidate pool and the ranking shown to the user. LLM-based user agents enable a different recommendation process: a user specifies a need before choosing a platform, leaving platforms to compete for the user's attention, which we refer to as an agentic recommendation market. In our controlled LLM-based experiments across three product domains, we find this new setting of recommendation creates a tension between access and attention. Compared with traditional platform-centric recommendation, user-centric recommendation greatly expands the opportunity for relevant items to enter comparison; yet broader participation does not translate directly into effective exposure. Competition directly triggers platforms' strategic play: selectively positive explanations occupy 73--78% of first-ranked positions. When the user agent relates platforms' actions to subsequent user feedback, this share falls to 36--41%, while the chance of a user purchasing the relevant item increases. A user agent is therefore more than a ranker over a larger pool of candidates: its querying, ranking, and feedback mechanism governing who can compete, how scarce attention is allocated, and how earlier outcomes shape the evaluation of platforms directly affect user utility. Designing agentic recommendation therefore requires treating access, attention, and accountability as a joint mechanism design problem.
Modern recommendation is shifting from platform-centric personalization toward user-governed personalization, where a personal LLM agent can act on the user's behalf across services. We formalize this emerging paradigm as Personal-Agent Mediated Recommendation: a platform recommender ranks a candidate set using platform-local information, and a personal agent uses user-authorized cross-platform history to mediate the resulting ranking and produce the final top-K slate. Such mediation is nontrivial: the platform ranking can encode strong population evidence that the personal agent cannot observe, so effective mediation must therefore balance beneficial rescues against harmful overrides. To study this trade-off, we introduce MediateRec, a benchmark that includes scalable proxy cross-platform environments and a real cross-platform test under a controlled platform-agent information boundary. To train the agent to use cross-platform history effectively, we further propose Personal Attribution Mediation Optimization (PAMO), which counterfactually masks that history to estimate personal mediation support and reallocates rank-aware advantage mass under a platform-relative value floor. We theoretically prove that PAMO preserves cutoff-level advantage mass and is locally optimal among first-order reallocations that preserve this mass without lowering average platform-relative value. Experiments on MediateRec show that personal-agent mediation enables meaningful platform corrections, yet even strong proprietary LLMs introduce non-negligible harmful overrides. PAMO consistently improves over matched outcome-only RL across seen and unseen target platforms and on the real cross-platform test, while achieving a better rescue-harm balance.
Yu Xia, Jiangfan Zhang, Jun Xiao +2
University of California San Diego · Meta · Meta AI
Agents typically assume an expert user -- one with well-formed preferences about what they want -- and default to clarifying questions whenever the task is underspecified. We argue this assumption is unrealistic. Users often lack the domain knowledge to have completely specified preferences; if asked about their preference on some feature, the user may be unable to answer without the agent helping the user to learn some domain knowledge needed to form a preference for that feature, e.g., via examples or explanations. To formalize these principles, we draw on the Search-Experience-Credence framework from Information Economics to introduce CoPref, a model of how users construct preferences based on agent dialog actions. We then study these ideas concretely in agentic recommender systems, proposing CoShop, an interactive benchmark. In CoShop, an agent converses with and makes recommendations for a CoPref user. The agent's performance depends on whether it can help the user gain the knowledge needed to specify the task well. Evaluating five frontier models, we find that no agent exceeds 56% accuracy on CoShop despite five turns of interaction. Failures stem not from agents' ability to find items, but from how little the interaction expands what users know about what they want.