arXiv subjects

Amin Saberi

Publications and source records attributed to Amin Saberi.

At least 19 recordsLinked to original sources

arXiv2026

MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation

Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a stricter requirement: recommendations must be drawn only from a merchant's fixed catalog, without web search or unsupported product claims. In this setting, the main challenge is reliability under hard constraints: the system must satisfy user requirements, remain grounded in available inventory, and preserve preferences across multiple conversational turns. We present MACS (Multi-Agent Commerce System), a hybrid multi-agent framework for reliable conversational recommendation in fixed-catalog settings. MACS uses LLMs for language-facing tasks such as interpreting user requests, eliciting preferences, and generating responses, while correctness-critical operations, including product retrieval, hard-constraint filtering, brand exclusion, and progressive relaxation, are executed deterministically by the merchant agent. A session-persistent preference layer tracks constraints across turns, enabling consistent handling of budget overwrites and exclusion reversals. On a 140-query single-turn benchmark, MACS achieves the highest pass rate (87.1%) and perfect brand compliance (1.000). On a 10-scenario multi-turn benchmark, MACS achieves the strongest macro Pass@5 (72% vs. 56% GPT+Catalog / 52% Gemini+Catalog) with zero constraint drift. The advantage is sharpest on exclusion reversal (100% vs. 20% / 0%) and constraint accumulation (100% vs. 60% / 40%). Mean judged response quality is similar across systems (0.751 vs. 0.736). These results suggest that hybrid architectures combining deterministic constraint enforcement with session-persistent preference tracking provide stronger reliability-oriented performance than catalog-bound prompt-only baselines in the fixed-catalog merchant setting.

cs.IR↗

arXiv2026

Learning Distributions from Multiple Data Providers

Motivated by learning from heterogeneous and overlapping data providers, we study a stylized model of distribution learning from restricted conditional samples. The goal is to learn an unknown distribution $p$ on a finite domain $[n]$. The learner is given a fixed family of queryable sets $\mathscr{S} \subseteq 2^{[n]}$, and each query to $S \in \mathscr{S}$ returns an independent sample from the conditional distribution $p(\cdot \mid S)$. Learnability is governed by the co-occurrence graph associated with $\mathscr{S}$: two domain elements are adjacent if they appear together in some queryable set. Pointwise consistency is achievable when this graph is connected on the target support. PAC learning requires more: it is possible when the co-occurrence graph is complete. The optimal sample complexity of PAC learning ranges from nearly linear to quadratic. Every query family with complete co-occurrence graph admits sample complexity $\widetilde O(n^2/ε^2)$, and this bound is tight in the worst case. On the other hand, if $[n]$ is queryable then ordinary sampling improves the bound to $Θ(n/ε^2)$, and this cannot be improved further even if every set is queryable. More generally, we identify hierarchical comparabilityas a sufficient structural condition on $\mathscr S$ under which the optimal complexity is nearly linear, $\widetilde Θ(n/ε^2)$, with pairwise query families as a canonical example. Finally, the full range of polynomial rates between linear and quadratic is attainable: for every $α\in (1,2)$, there exists a query family with optimal PAC rate $\widetilde Θ(n^α/ε^2)$.

cs.DS↗

arXiv2026

Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation

Language models deployed in high-stakes roles can potentially favor certain entities, brands, or viewpoints, steering user decisions at scale. Such preferential biases can be introduced by any actor in the model's supply chain and are most dangerous when the model reveals its preference only on the relevant topic while behaving identically to its unmodified base on all other inputs. Recent work has shown that these biases can transfer through context distillation on semantically unrelated data, with the signal residing entirely in the soft logit distribution and remaining invisible to text-based inspection. However, the defender faces a fundamental asymmetry: without knowing the bias topic, no detection method can reliably surface a stealth preferential bias, regardless of whether it examines generated text, internal representations, or model weights. Here we introduce Distill to Detect (D2D), a method that surfaces hidden biases by distilling the distributional shift between a suspected model and its base into a cartridge (a KV-cache prefix adapter), concentrating the dominant divergence and amplifying the bias signal into generated text. We show that D2D successfully amplifies the hidden biases of stealth models to the extent that they can be reliably detected across multiple bias types. We also propose a theoretical framework that explains the efficacy of D2D through the lens of Fisher-weighted projection of the logit distribution shift, supported by empirical observations. By turning the capacity bottleneck of prefix-tuning adapters into a detection tool, D2D provides a practical building block for auditing hidden behaviors in deployed language models.

cs.CL↗

arXiv2026

On Language Generation in the Limit with Bounded Memory

We study language generation in the limit under bounded memory. In this task, a learner observes examples from an unknown target language one at a time and must eventually output only new valid examples. Prior work assumes access to the entire history, a strong assumption since realistic algorithms retain limited past information. Classical work in learning theory shows memory constraints dramatically alter learnability; we extend this to language generation. First, we study memoryless generators. Under a mild enumeration restriction, every countable collection of infinite languages remains generable without memory. Without this restriction, we exactly characterize when memoryless generation is possible. For finite collections, we characterize the optimal minimax density achievable by memoryless generators -- the best density guaranteed against any collection of a given size. This combinatorial bound relies on Sperner's theorem and symmetric chain decompositions. We further show that a sliding window of the last $W$ examples does not improve this worst-case density, whereas allowing it to store $b$ adaptively chosen past examples improves the achievable density for every $b \geq 1$. Finally, we revisit identification in the limit, where the learner must converge to a single correct hypothesis for the target language. We focus on its incremental variant, where the learner remembers only its previous guess. Here, although exact identification fails on a collection of just three languages, a mild relaxation requiring convergence to an ``approximate'' version of the target is achievable for every finite collection. These results show bounded memory affects these tasks differently: generation remains achievable for every countable collection, while density and identification are confined to finite collections, with guarantees weakening as the collection grows.

cs.DS↗

arXiv2026

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue that many headline RLVR gains are not yet well validated because reports often conflate policy improvement with three confounds: (i) budget mismatch between RLVR and baseline evaluations, (ii) attempt inflation and calibration drift that convert abstentions into confident answers, and (iii) benchmark data contamination. Using budget-matched reproductions and partial-prompt contamination probes, we find that several widely cited gaps shrink substantially or disappear once budgets, prompts, and dataset versions are matched and contaminated sets are treated as memorization probes rather than evidence of reasoning. This does not mean that RLVR is ineffective, but it implies that current measurements often overstate capability gains and obscure reliability costs. We therefore propose a compact, tax-aware minimum standard for RLVR training and evaluation: budget-matched saturation curves with variance, calibration, and abstention tracking, a judge-robustness stress test when LLM judges are used, and an explicit contamination screen. With these controls, RLVR remains effective and deployable in verifiable domains, but reasoning gains should be treated as provisional without them.

cs.LG↗

arXiv2026

Local Limits of Small World Networks

Small-world networks, known for high local clustering and short path lengths, are a fundamental structure in many real-world systems, including social, biological, and technological networks. We apply the theory of (marked) local convergence (also known as Benjamini-Schramm convergence) to derive the limiting behavior of the local structures for two commonly studied small-world network models: the Watts-Strogatz and the Kleinberg models. Establishing local convergence enables us to show that key network measures, such as clustering coefficient, PageRank, greedy maximal independent set, number of spanning trees and tree entropy, converge as network size increases, with their limits determined by the graph's local structure. Additionally, this framework facilitates the estimation of global phenomena, such as the size of the giant component under bond percolation and the closely related properties, the size of the epidemic and information cascades, using local information from small neighborhoods. Furthermore, we observe a critical change in the behavior of the limit exactly when the parameter governing long-range connections in the Kleinberg model crosses the threshold where decentralized search remains efficient, offering a new perspective on why decentralized algorithms fail in certain regimes.

math.PR↗

arXiv2026

Entropy Guided Diversification and Preference Elicitation in Agentic Recommendation Systems

Users on e-commerce platforms can be uncertain about their preferences early in their search. Queries to recommendation systems are frequently ambiguous, incomplete, or weakly specified. Agentic systems are expected to proactively reason, ask clarifying questions, and act on the user's behalf, which makes handling such ambiguity increasingly important. In existing platforms, ambiguity led to excessive interactions and question fatigue or overconfident recommendations prematurely collapsing the search space. We present an Interactive Decision Support System (IDSS) that addresses ambiguous user queries using entropy as a unifying signal. IDSS maintains a dynamically filtered candidate product set and quantifies uncertainty over item attributes using entropy. This uncertainty guides adaptive preference elicitation by selecting follow-up questions that maximize expected information gain. When preferences remain incomplete, IDSS explicitly incorporates residual uncertainty into downstream recommendations through uncertainty-aware ranking and entropy-based diversification, rather than forcing premature resolution. We evaluate IDSS using review-driven simulated users grounded in real user reviews, enabling a controlled study of diverse shopping behaviors. Our evaluation measures both interaction efficiency and recommendation quality. Results show that entropy-guided elicitation reduces unnecessary follow-up questions, while uncertainty-aware ranking and presentation yield more informative, diverse, and transparent recommendation sets under ambiguous intent. These findings demonstrate that entropy-guided reasoning provides an effective foundation for agentic recommendation systems operating under uncertainty.

cs.AI↗

arXiv2025

Near-Optimal Bayesian Online Assortment of Reusable Resources

Motivated by the applications of rental services in e-commerce, we consider revenue maximization in online assortment of reusable resources for a stream of arriving consumers with different types. We design competitive online algorithms with respect to the optimum online policy in the Bayesian setting, in which types are drawn independently from known heterogeneous distributions over time. In the regime where the minimum of initial inventories $c_0$ is large, our main result is a near-optimal $1-\min\left(\frac{1}{2},\sqrt{\log(c_0)/c_0}\right)$ competitive algorithm for the general case of reusable resources. Our algorithm relies on an expected LP benchmark for the problem, solves this LP, and simulates the solution through an independent randomized rounding. The main challenge is obtaining point-wise inventory feasibility in a computationally efficient fashion from these simulation-based algorithms. To this end, we use several technical ingredients to design $\textit{discarding policies}$ -- one for each resource. These policies handle the trade-off between the inventory feasibility under reusability and the revenue loss of each of the resources. However, discarding a unit of a resource changes the future consumption of other resources. To handle this new challenge, we also introduce $\textit{post-processing}$ assortment procedures that help with designing and analyzing our discarding policies as they run in parallel, which might be of independent interest. As a side result, by leveraging techniques from the literature on prophet inequality, we further show an improved near-optimal $1-1/\sqrt{c_0+3}$ competitive algorithm for the special case of non-reusable resources. We finally evaluate the performance of our algorithms using the numerical simulations on the synthetic data.

cs.DS↗

arXiv2025

SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models

Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce SPRINT, a novel post-training and inference-time framework designed to enable LRMs to dynamically identify and exploit opportunities for parallelization during their reasoning process. SPRINT incorporates an innovative data curation pipeline that reorganizes natural language reasoning trajectories into structured rounds of long-horizon planning and parallel execution. By fine-tuning LRMs on a small amount of such curated data, the models learn to dynamically identify independent subtasks within extended reasoning processes and effectively execute them in parallel. Through extensive evaluations, we demonstrate that models fine-tuned with the SPRINT framework match the performance of reasoning models on complex domains such as mathematics while generating up to 39% fewer sequential tokens on problems requiring more than 8,000 output tokens. Finally, we observe consistent results transferred to two out-of-distribution tasks, namely GPQA and Countdown, with up to 45% and 65% reduction in average sequential tokens respectively for longer reasoning trajectories, while matching the performance of the fine-tuned reasoning model.

cs.AI↗

arXiv2025

Robustness of Online Inventory Balancing to Inventory Shocks

In classic adversarial online resource allocation problems such as AdWords, customers arrive online while products are given offline with a fixed initial inventory. To ensure revenue guarantees under uncertainty, the decision maker must balance consumption across products. Based on this, the prevalent policy "inventory balancing (IB)" has proved to be optimal or near-optimal competitive in almost all classic settings. However, these models do not capture various forms of inventory shocks on the supply side, which play an important role in real-world online assortment and can significantly impact the revenue performance of the IB algorithm. Motivated by this paradigm, we introduce a variant of online assortment planning with inventory shocks. Our model considers adversarial exogenous shocks (where supply increases unpredictably) and allocation-coupled endogenous shocks (where an inventory reduction is triggered by the algorithms and re-adjusted after a usage duration), whose combination leads to non-monotonic inventory fluctuations. As our main result, we show the robustness of IB-type strategies against such shocks by designing a new family of optimal competitive algorithms called "Batched Inventory Balancing (BIB)." Using a novel randomized primal-dual method, we bound the competitive ratio of BIB against optimal offline. We show that with proper choice of a certain parameter, this competitive ratio is asymptotically optimal and converges to (1-1/e) as initial inventories grow, in contrast to the original IB which no longer achieves the optimal ratio in this new model. Moreover, we characterize BIB's competitive ratio parametric by its penalty function and show that it matches exactly the competitive ratio of IB without shocks. Our refined analysis reduces the dual construction to a combinatorial "interval assignment problem" whose algorithmic solution may be of independent interest.

cs.DS↗

arXiv2025

Optimal Rounding for Two-Stage Bipartite Matching

We study two-stage bipartite matching, in which the edges of a bipartite graph on vertices $(B_1 \cup B_2, I)$ are revealed in two batches. In stage one, a matching must be selected from among revealed edges $E \subseteq B_1 \times I$. In stage two, edges $E^θ\subseteq B_2 \times I$ are sampled from a known distribution, and a second matching must be selected between $B_2$ and unmatched vertices in $I$. The objective is to maximize the total weight of the combined matching. We design polynomial-time approximations to the optimum online algorithm, achieving guarantees of $7/8$ for vertex-weighted graphs and $2\sqrt{2}-2 \approx 0.828$ for edge-weighted graphs under arbitrary distributions. Both approximation ratios match known upper bounds on the integrality gap of the natural fractional relaxation, improving upon the best-known approximation of 0.767 by Feng, Niazadeh, and Saberi for unweighted graphs whose second batch consists of independently arriving nodes. Our results are obtained via an algorithm that rounds a fractional matching revealed in two stages, aiming to match offline nodes (respectively, edges) with probability proportional to their fractional weights, up to a constant-factor loss. We leverage negative association (NA) among offline node availabilities -- a property induced by dependent rounding -- to derive new lower bounds on the expected size of the maximum weight matching in random graphs where one side is realized via NA binary random variables. Moreover, we extend these results to settings where we have only sample access to the distribution. In particular, $\text{poly}(n,ε^{-1})$ samples suffice to obtain an additive loss of $ε$ in the approximation ratio for the vertex-weighted problem; a similar bound holds for the edge-weighted problem with an additional (unavoidable) dependence on the scale of edge weights.

cs.DS↗

arXiv2025

From signaling to interviews in random matching markets

In many two-sided labor markets, interviews are conducted before matches are formed. The growing number of interviews in medical residency markets has increased demand for signaling mechanisms, where applicants send a limited number of signals to communicate interest. We study the role of signaling mechanisms to reduce interviews in centralized random matching markets where initial preferences are refined through interviews. Agents can only match with those they interview. For the market to clear, we focus on perfect interim stability: no pair of agents-even if they never interviewed each other-prefers each other to their assigned partners under their interim preferences. A matching is almost interim stable if it is perfect interim stable after removing a vanishingly small fraction of agents. We analyze signaling mechanisms in random matching markets with $n$ agents where agents on the short side, long side, or both sides signal their top $d$ preferred partners. The interview graph connects pairs where at least one party signaled the other. We reveal a fundamental trade-off between almost and perfect interim stability. For almost interim stability, $d=ω(1)$ signals suffice: short-side signaling is always effective, whereas long-side signaling is effective only when the market is weakly imbalanced, i.e., when any size difference between the two sides becomes negligible as the market grows. For perfect interim stability, at least $d=Ω(\log^2 n)$ signals are necessary, and short-side signaling becomes crucial in any imbalanced market. We establish that truthful signaling is a Bayes-Nash equilibrium and extend our analysis to markets with hierarchical structure. As a technical contribution, we develop a message-passing algorithm that efficiently determines interim stability by leveraging local neighborhood structures.

cs.GT↗

arXiv2025

StorySage: Conversational Autobiography Writing Powered by a Multi-Agent Framework

Every individual carries a unique and personal life story shaped by their memories and experiences. However, these memories are often scattered and difficult to organize into a coherent narrative, a challenge that defines the task of autobiography writing. Existing conversational writing assistants tend to rely on generic user interactions and pre-defined guidelines, making it difficult for these systems to capture personal memories and develop a complete biography over time. We introduce StorySage, a user-driven software system designed to meet the needs of a diverse group of users that supports a flexible conversation and a structured approach to autobiography writing. Powered by a multi-agent framework composed of an Interviewer, Session Scribe, Planner, Section Writer, and Session Coordinator, our system iteratively collects user memories, updates their autobiography, and plans for future conversations. In experimental simulations, StorySage demonstrates its ability to navigate multiple sessions and capture user memories across many conversations. User studies (N=28) highlight how StorySage maintains improved conversational flow, narrative completeness, and higher user satisfaction when compared to a baseline. In summary, StorySage contributes both a novel architecture for autobiography writing and insights into how multi-agent systems can enhance human-AI creative partnerships.

cs.HC↗

arXiv2025

When to Trust Context: Self-Reflective Debates for Context Reliability

Large language models frequently encounter conflicts between their parametric knowledge and contextual input, often resulting in factual inconsistencies or hallucinations. We propose Self-Reflective Debate for Contextual Reliability (SR-DCR), a lightweight framework that integrates token-level self-confidence with an asymmetric multi-agent debate to adjudicate such conflicts. A critic, deprived of context, challenges a defender who argues from the given passage; a judge model evaluates the debate and determines the context's reliability. The final answer is selected by combining the verdict with model confidence. Experiments on the ClashEval benchmark demonstrate that SR-DCR consistently enhances robustness to misleading context while maintaining accuracy on trustworthy inputs, outperforming both classical debate and confidence-only baselines with minimal computational overhead. The code is available at https://github.com/smiles724/Self-Reflective-Debates.

cs.CL↗

arXiv2025

Adaptive Approximation Schemes for Matching Queues

We study a continuous-time, infinite-horizon dynamic bipartite matching problem. Suppliers arrive according to a Poisson process; while waiting, they may abandon the queue at a uniform rate. Customers on the other hand must be matched upon arrival. The objective is to minimize the expected long-term average cost subject to a throughput constraint on the total match rate. Previous literature on dynamic matching focuses on "static" policies, where the matching decisions do not depend explicitly on the state of the supplier queues, achieving constant-factor approximations. By contrast, we design "adaptive" policies, which leverage queue length information, and obtain near-optimal polynomial-time algorithms for several classes of instances. First, we develop a bi-criteria fully polynomial-time approximation scheme for dynamic matching on networks with a constant number of queues--that computes a $(1-ε)$-approximation of the optimal policy in time polynomial in both the input size and $1/ε$. A key new technique is a hybrid LP relaxation, which combines static and state-dependent LP approximations of the queue dynamics, after a decomposition of the network. Networks with a constant number of queues are motivated by deceased organ donation schemes, where the supply types can be divided according to blood and tissue types. The above algorithm, combined with a careful cell decomposition gives an efficient polynomial-time approximation scheme for dynamic matching on Euclidean networks of fixed dimension. The Euclidean case is of interest in ride-hailing and spatial service platforms, where the goal is to fulfill as many trips as possible while minimizing driving distances.

cs.DS↗

arXiv2025

Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL

Text-to-SQL is a challenging task involving multiple reasoning-intensive subtasks, including natural language understanding, database schema comprehension, and precise SQL query formulation. Existing approaches often rely on handcrafted reasoning paths with inductive biases that can limit their overall effectiveness. Motivated by the recent success of reasoning-enhanced models such as DeepSeek R1 and OpenAI o1, which effectively leverage reward-driven self-exploration to enhance reasoning capabilities and generalization, we propose a novel set of partial rewards tailored specifically for the Text-to-SQL task. Our reward set includes schema-linking, AI feedback, n-gram similarity, and syntax check, explicitly designed to address the reward sparsity issue prevalent in reinforcement learning (RL). Leveraging group relative policy optimization (GRPO), our approach explicitly encourages large language models (LLMs) to develop intrinsic reasoning skills necessary for accurate SQL query generation. With models of different sizes, we demonstrate that RL-only training with our proposed rewards consistently achieves higher accuracy and superior generalization compared to supervised fine-tuning (SFT). Remarkably, our RL-trained 14B-parameter model significantly outperforms larger proprietary models, e.g. o3-mini by 4% and Gemini-1.5-Pro-002 by 3% on the BIRD benchmark. These highlight the efficacy of our proposed RL-training framework with partial rewards for enhancing both accuracy and reasoning capabilities in Text-to-SQL tasks.

cs.LG↗

arXiv2025

Stable Matching with Interviews

In several two-sided markets, including labor and dating, agents typically have limited information about their preferences prior to mutual interactions. This issue can result in matching frictions, as arising in the labor market for medical residencies, where high application rates are followed by a large number of interviews. Yet, the extensive literature on two-sided matching primarily focuses on models where agents know their preferences, leaving the interactions necessary for preference discovery largely overlooked. This paper studies this problem using an algorithmic approach, extending Gale-Shapley's deferred acceptance to this context. Two algorithms are proposed. The first is an adaptive algorithm that expands upon Gale-Shapley's deferred acceptance by incorporating interviews between applicants and positions. Similar to deferred acceptance, one side sequentially proposes to the other. However, the order of proposals is carefully chosen to ensure an interim stable matching is found. Furthermore, with high probability, the number of interviews conducted by each applicant or position is limited to $O(\log^2 n)$. In many seasonal markets, interactions occur more simultaneously, consisting of an initial interview phase followed by a clearing stage. We present a non-adaptive algorithm for generating a single stage set of in tiered random markets. The algorithm finds an interim stable matching in such markets while assigning no more than $O(\log^3 n)$ interviews to each applicant or position.

cs.DS↗

arXiv2024

CHESS: Contextual Harnessing for Efficient SQL Synthesis

Translating natural language questions into SQL queries, known as text-to-SQL, is a long-standing research problem. Effective text-to-SQL synthesis can become very challenging due to (i) the extensive size of database catalogs (descriptions of tables and their columns) and database values, (ii) reasoning over large database schemas, (iii) ensuring the functional validity of the generated queries, and (iv) navigating the ambiguities of natural language questions. We introduce CHESS, a Large Language Model (LLM) based multi-agent framework for efficient and scalable SQL synthesis, comprising four specialized agents, each targeting one of the aforementioned challenges: the Information Retriever (IR) extracts relevant data, the Schema Selector (SS) prunes large schemas, the Candidate Generator (CG) generates high-quality candidates and refines queries iteratively, and the Unit Tester (UT) validates queries through LLM-based natural language unit tests. Our framework offers configurable features that adapt to various deployment constraints, including 1) Supporting industrial-scale databases: leveraging the Schema Selector agent, CHESS efficiently narrows down very large database schemas into manageable sub-schemas, boosting system accuracy by approximately $2\%$ and reducing the number of LLM tokens by $\times 5$. 2) State-of-the-Art privacy-preserving performance: Among the methods using open-source models, CHESS achieves state-of-the-art performance, resulting in a high-performing, privacy-preserving system suitable for industrial deployment. 3) Scalablity with additional compute budget: In settings with high computational budgets, CHESS achieves $71.10\%$ accuracy on the BIRD test set, within $2\%$ of the leading proprietary method, while requiring approximately $83\%$ fewer LLM calls.

cs.LG↗