Searcharxiv⌕ Search

arXiv subjects

Chirag Shah

Publications and source records attributed to Chirag Shah.

At least 19 recordsLinked to original sources
arXiv2026

SimGuide: Typed Multi-Context User Representations for Preference-Conditioned Agent Planning

Agents that act on a user's behalf must plan differently for different users, and increasingly do so from some structured representation of user context and not from raw interaction history. How much that structure is worth, and which parts of it carry the value, is largely unmeasured. We introduce SimBench, 47 preference-conditioned planning tasks over 9 synthetic users represented as 28 typed, potentially conflicting context blocks, where the correct plan depends on which contexts are active and how their conflicts are resolved. Against it we evaluate SimGuide, a framework combining typed multi-context representation, explicit conflict arbitration, and optional procedural grounding of individual constraints. Across three models and six user-context representations, SimGuide's typed blocks with arbitration outperform retrieval over the same user's past decisions by +0.210, +0.205 and +0.144 Preference Adherence on Llama 3.3 70B, GPT-4o and Claude Sonnet 4.5 respectively (all p < 0.001); removing the arbitration instruction alone costs up to +0.209. Grounding each constraint with a worked example of past application helps only where the model has headroom: +0.094 on Llama 70B (p < 0.001), falling to +0.029 on GPT-4o and +0.002 on Claude, which already scores perfectly on 35 of 47 tasks without it. We report the benchmark's minimum detectable effect alongside its results. The benchmark ships with a provenance audit that re-derives every reported number from the prompt that produced it.

cs.AI↗
arXiv2026

Report on The 1st Workshop on Human-Centered Proactive and Personalized Agents for Interactive Information Access at CHIIR 2026

Interactive information access is increasingly moving beyond reactive query-response paradigms toward agentic systems that can personalize interaction, retain context, infer latent needs, recommend next steps, and initiate support. This shift creates new opportunities for adaptive and context-aware assistance, while also raising important questions about autonomy, privacy, trust, transparency, user welfare, and evaluation. The First Workshop on Human-Centered Proactive and Personalized Agents for Interactive Information Access provided an interdisciplinary forum for examining these questions across information retrieval, human-computer interaction, dialogue systems, AI ethics, cognitive science, learning technologies, and human-centered AI. Through invited talks, paper presentations, and open discussion, the workshop engaged with topics including calibrated initiative, knowledge-gap navigation, long-term memory, value-sensitive design, implicit personalization, AI-mediated care, proactive dialogue, and evaluation beyond task accuracy. A central theme across the workshop was that proactivity should not be understood only as earlier action or improved prediction, but as a form of initiative that must be appropriately timed, transparent, contestable, and aligned with user goals. This report summarizes the workshop and synthesizes the research challenges it surfaced for designing proactive and personalized agents in interactive information access.

cs.HC↗
arXiv2026

LLM-Driven Usefulness Judgment for Web Search Evaluation

Evaluation is fundamental in optimizing search experiences and supporting diverse user intents in Information Retrieval (IR). Traditional search evaluation methods primarily rely on relevance labels, which assess how well retrieved documents match a user's query. However, relevance alone fails to capture a search system's effectiveness in helping users achieve their search goals, making usefulness a critical evaluation criterion. In this paper, we explore an alternative approach: LLM-generated usefulness labels, which incorporate both implicit and explicit user behavior signals to evaluate document usefulness. We propose Task-aware Rubric-based Usefulness Evaluation (TRUE), a rubric-driven evaluation method that employs iterative sampling and reasoning to model complex search behavior patterns. Our findings show that (i) LLMs can generate moderate usefulness labels by leveraging comprehensive search session history incorporating personalization and contextual understanding, and (ii) fine-tuned LLMs improve usefulness judgments when provided with structured search session contexts. Additionally, we examine whether LLMs can distinguish between relevance and usefulness, particularly in cases where this divergence impacts search success. We also conduct an ablation study to identify key metrics for accurate usefulness label generation, optimizing for token efficiency and cost-effectiveness in real-world applications. This study advances LLM-based usefulness evaluation by refining key user metrics, exploring LLM-generated label reliability, and ensuring feasibility for large-scale search systems.

cs.IR↗
arXiv2026

Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight

Generative AI agents equate understanding with resolving explicit queries, an assumption that confines interaction to what users can articulate. This assumption breaks down when users themselves lack awareness of what is missing, risky, or worth considering. In such conditions, proactivity is not merely an efficiency enhancement, but an epistemic necessity. We refer to this condition as epistemic incompleteness: where progress depends on engaging with unknown unknowns for effective partnership. Existing approaches to proactivity remain narrowly anticipatory, extrapolating from past behavior and presuming that goals are already well defined, thereby failing to support users meaningfully. However, surfacing possibilities beyond a user's current awareness is not inherently beneficial. Unconstrained proactive interventions can misdirect attention, overwhelm users, or introduce harm. Proactive agents, therefore, require behavioral grounding: principled constraints on when, how, and to what extent an agent should intervene. We advance the position that generative proactivity must be grounded both epistemically and behaviorally. Drawing on the philosophy of ignorance and research on proactive behavior, we argue that these theories offer critical guidance for designing agents that can engage responsibly and foster meaningful partnerships.

cs.CY↗
arXiv2026

M-SDT: A modelling framework for dengue transmission, forecasting, and intervention strategies in Ahmedabad Municipal Corporation

Dengue fever poses a persistent public health challenge in rapidly urbanizing Indian cities such as Ahmedabad, where spatial heterogeneity and seasonal variability complicate forecasting and control. In this study, we develop a data-driven compartmental framework to simulate transmission dynamics, generate forecasts, and evaluate intervention strategies across the Ahmedabad Municipal Corporation (AMC). We employ a Mechanistic Seasonal Dengue Transmission (M-SDT) model that incorporates symptomatic and asymptomatic infections. We calibrated the proposed model using zone-wise dengue case data during 2020--2024. Parameter uncertainty is rigorously quantified using a bootstrap sampling framework with negative binomial noise. The calibrated model reveals pronounced spatial heterogeneity across AMC zones, with persistent hotspots and distinct transmission regimes. Forecasts for 2026--2028 indicate continued endemic circulation with moderate inter-annual variability. Sensitivity analysis identifies the mosquito biting rate and vector mortality as dominant drivers of long-term disease burden, highlighting the central role of vector ecology in shaping epidemic outcomes. Evaluating seasonal vector control strategies shows a notable difference in operation; periodic fogging has a cumulative effect over the years, while sustained residual spraying can quickly curb outbreaks and decrease incidence by over 80%. The zone-wise analysis reveals that the mosquito-to-human ratio governs not only the baseline outbreak potential but also each zone's responsiveness to control strategies. Overall, the M-SDT modelling framework enables reconstruction of unobserved dynamics, rigorous uncertainty quantification, and evaluation of targeted, zone-specific interventions, underscoring the importance of integrating fine-scale surveillance data with mechanistic modelling for adaptive urban dengue control.

q-bio.PE↗
arXiv2026

Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents

Large Language Model (LLM) agents are increasingly deployed in settings where they interact with a wide variety of people, including users who are unclear, impatient, or reluctant to share information. However, collecting real interaction data at scale remains expensive. The field has turned to LLM-based user simulators as stand-ins, but these simulators inherit the behavior of their underlying models: cooperative and homogeneous. As a result, agents that appear strong in simulation often fail under the unseen, diverse communication patterns of real users. To narrow this gap, we introduce Persona Policies (PPol), a plug-and-play control layer that induces realistic behavioral variation in user simulators while preserving the original task goals. Rather than hand-crafting personas, we cast persona generation as an LLM-driven evolutionary program search that optimizes a Python generator to discover behaviors and translate them into task-preserving roleplay policies. Candidate generators are guided by a multi-objective fitness score combining human-likeness with broad coverage of human behavioral patterns. Once optimized, the generator produces a diverse population of human-like personas for any task in the domain. Across tau^2-bench retail and airline domains, evolved PPol programs yield 33-62% absolute gains in fitness score over the baseline simulator. In a blinded evaluation, annotators rated PPol-conditioned users as human 80.4% of the time, close to real human traces and nearly twice as frequently as baseline simulators. Agents trained with PPol are more robust to challenging, out-of-distribution behaviors, improving task success by +17% relative to training only on existing simulated interactions. This offers a novel approach to strengthen simulator-based evaluation and training without changing tasks or rewards.

cs.AI↗
arXiv2026

Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models

Long-horizon personalization requires dialogue assistants to retrieve user-specific facts from extended interaction histories. In practice, many relevant facts often have low semanticsimilarity to the query under dense retrieval. Standard Retrieval-Augmented Generation (RAG) and GraphRAG systems are still largely retrospective: they rely on embedding similarity to the query or on fixed graph traversals, so they often miss facts that matter for the user's needs but lie far from the query in embedding space. Inspired by prospection, the human ability to use imagined futures as cues for recall, we introduce Prospection-Guided Retrieval (PGR), which decouples retrieval from how memories are stored. Given a user query, PGR first expands the goal into a short Tree-of-Thought (ToT) or linear chain of plausible next steps, and uses these steps as retrieval probes rather than relying on the original query alone. The facts retrieved by these probes are then used to personalize the next round of prospection, enabling PGR to uncover additional memories that become relevant only after the simulation is grounded in the user's history. We also introduce MemoryQuest, a challenging multi-session benchmark in which each query is annotated with 3--5 dated reference facts subject to a low query-reference similarity constraint. Across 1,625 queries spanning 185 user profiles from 3 publicly available datasets, PGR-TOT substantially improves retrieval, including nearly 3x recall on MemoryQuest over the strongest baseline. In pairwise LLM-as-judge comparisons against baselines, PGR-generated responses are preferred on 89--98% of queries, with blinded human annotations on held-out subsets showing the same trend. Overall, the results demonstrate that explicit prospection yields large gains in long-horizon retrieval and response quality relative to similarity-only baselines.

cs.IR↗
arXiv2026

Deep Reasoning in General Purpose Agents via Structured Meta-Cognition

Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems. Current LLM agents lack this flexibility, as their scaffolds hard-code such reasoning decisions in advance. These scaffolds are effective when their prescribed structure matches the task, but brittle when solving the task requires adapting the structure of reasoning itself. We introduce Deep Reasoning -- an inference-time approach for constructing task-specific scaffolds through structured meta-reasoning. Deep Reasoning uses a formal language that represents meta-reasoning as executable decompositions over associative inference, formal computation, and recursive subproblem solving, enabling decomposition principles to be encoded as in-context examples that guide test-time scaffold construction. We instantiate this approach in a general-purpose agent (DOLORES) that distributes complex tasks across more controlled reasoning threads. We evaluate it against state-of-the-art scaffolding methods across four hard benchmarks: multi-hop reasoning, long-chain question answering, long-context aggregation, and deep research-style information seeking. DOLORES outperforms all evaluated scaffolds across three model sizes and two model families, improving over the strongest evaluated scaffold baseline by 24.8% on average. DOLORES distributes cognition across structured, lower-load reasoning threads, thereby reducing premature termination and hallucinations. This advantage can even bridge the scaling gap, with an 8B version surpassing all evaluated 32B baselines from the same family in more than half the settings. These results point toward future agentic systems that treat scaffolding as adaptive reasoning, constructing the structure each task requires just-in-time.

cs.CL↗
arXiv2026

PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation

Current approaches to proactive assistance move beyond the ask-and-respond paradigm by anticipating user needs. In practice, they either burden users with clarifying questions or rely on context-based extrapolation, often leading to unnecessary or mistimed interventions. Such systems lack explicit mechanisms to model users' knowledge gaps, resulting in incomplete or suboptimal task outcomes. To address this, we propose PROPER, a framework that explicitly models user-specific knowledge gaps in a controlled manner. Central to our approach is the notion of dimensions: structured, task-relevant factors that define the considerations required for effective task completion. Given a user query, the DGA (Dimension Generating Agent) identifies explicit dimensions (from the user's query) and generates a set of candidate implicit dimensions capturing unarticulated aspects of the task. The RGA (Response Generating Agent) integrates both explicit and implicit dimensions selectively to produce personalized, context-aware, and proactively informative responses. We evaluate PROPER across multiple domains using a structured, gap-aware rubric that measures coverage, initiative appropriateness, and intent alignment. PROPER improves on quality scores and win rates across all domains, achieving up to 84% gains in single-turn evaluation and consistent dominance in multi-turn interactions. All code for PROPER is available at: https://github.com/i-kiran/ProPer-Agent.

cs.LG↗
arXiv2026

ClaimDB: A Fact Verification Benchmark over Large Structured Data

Real-world fact-checking often involves verifying claims grounded in structured data at scale. Despite substantial progress in fact-verification benchmarks, this setting remains largely underexplored. In this work, we introduce ClaimDB, a fact-verification benchmark where the evidence for claims is derived from compositions of millions of records and multiple tables. ClaimDB consists of 80 unique real-life databases covering a wide range of domains, from governance and healthcare to media, education and the natural sciences. At this scale, verification approaches that rely on "reading" the evidence break down, forcing a timely shift toward reasoning in executable programs. We conduct extensive experiments with 30 state-of-the-art proprietary and open-source (below 70B) LLMs and find that more than half score below 55% accuracy. Our analysis also reveals that both closed- and open-source models struggle with abstention -- the ability to admit that there is no evidence to decide -- raising doubts about their reliability in high-stakes data analysis tasks. We release the benchmark, code, and the LLM leaderboard at https://claimdb.github.io .

cs.CL↗
arXiv2026

iAgentBench: Benchmarking Sensemaking Capabilities of Information-Seeking Agents on High-Traffic Topics

With the emergence of search-enabled generative QA systems, users are increasingly turning to tools that browse, aggregate, and reconcile evidence across multiple sources on their behalf. Yet many widely used QA benchmarks remain answerable by retrieving a single relevant passage, making them poorly suited for measuring cross-source sensemaking, such as integrating evidence, tracking causal links, and resolving dependencies across facets of a topic. We present iAgentBench, a dynamic ODQA benchmark that targets these higher-level information needs while keeping questions natural and grounded in realistic information-seeking behavior. iAgentBench draws seed topics from real-world attention signals and uses common user intent patterns to construct user-like questions whose answers require combining evidence from multiple sources, not just extracting a single snippet. Each instance is released with traceable evidence and auditable intermediate artifacts that support contamination checks and enable fine-grained diagnosis of failures in retrieval versus synthesis. Experiments across multiple LLMs show that retrieval improves accuracy, but retrieval alone does not reliably resolve these questions, underscoring the need to evaluate evidence use, not just evidence access.

cs.CL↗
arXiv2026

TRUE: A Reproducible Framework for LLM-Driven Relevance Judgment in Information Retrieval

LLM-based relevance judgment generation has become a crucial approach in advancing evaluation methodologies in Information Retrieval (IR). It has progressed significantly, often showing high correlation with human judgments as reflected in LLMJudge leaderboards \cite{rahmani2025judging}. However, existing methods for relevance judgments, rely heavily on sensitive prompting strategies, lacking standardized workflows for generating reliable labels. To fill this gap, we reintroduce our method, \textit{Task-aware Rubric-based Evaluation} (TRUE), for relevance judgment generation. Originally developed for usefulness evaluation in search sessions, we extend TRUE to mitigate the gap in relevance judgment due to its demonstrated effectiveness and reproducible workflow. This framework leverages iterative data sampling and reasoning to evaluate relevance judgments across multiple factors including intent, coverage, specificity, accuracy and usefulness. In this paper, we evaluate TRUE on the TREC DL 2019, 2020 and LLMJudge datasets and our results show that TRUE achieves strong performance on the system-ranking LLM leaderboards. The primary focus of this work is to provide a reproducible framework for LLM-based relevance judgments, and we further analyze the effectiveness of TRUE across multiple dimensions.

cs.IR↗
arXiv2026

How Many Images Does It Take? Estimating Imitation Thresholds in Text-to-Image Models

Text-to-image models are trained using large datasets of image-text pairs collected from the internet. These datasets often include copyrighted and private images. Training models on such datasets enables them to generate images that might violate copyright laws and individual privacy. This phenomenon is termed imitation -- generation of images with content that has recognizable similarity to its training images. In this work we estimate the point at which a model was trained on enough instances of a concept to be able to imitate it -- the imitation threshold. We posit this question as a new problem and propose an efficient approach that estimates the imitation threshold without incurring the colossal cost of training these models from scratch. We experiment with two domains -- human faces and art styles, and evaluate four text-to-image models that were trained on three pretraining datasets. We estimate the imitation threshold of these models to be in the range of 200-700 images, depending on the domain and the model. The imitation threshold provides an empirical basis for copyright violation claims and acts as a guiding principle for text-to-image model developers that aim to comply with copyright and privacy laws. Website: https://how-many-van-goghs-does-it-take.github.io/. Code: https://github.com/vsahil/MIMETIC-2.

cs.CV↗
arXiv2025

QLENS: Towards A Quantum Perspective of Language Transformers

In natural language processing, current methods for understanding Transformers are successful at identifying intermediate predictions during a model's inference. However, these approaches function as limited diagnostic checkpoints, lacking a mathematical framework for mechanistically modeling how each layer facilitates transitions between these evolving states. This interpretability gap and past successes of interdisciplinary outlooks inspire us to turn to physics in search of a descriptive mathematical framework for Transformers. We observe that language models are intrinsically probabilistic, an attribute that is echoed in the core postulates of quantum mechanics. This parallel inspires us to translate insights from this discipline to that of natural language processing. Towards this objective, we propose QLENS a novel attempt to develop a physics-based perspective on the Transformer generation process. Under QLENS, a Transformer is studied by converting its latent activations into a state vector in a Hilbert space derived from the model's output units. This state subsequently evolves through hidden layers - reformulated as unitary operators and analogously defined Hamiltonians - during inference. The model's final probability distribution is obtained by applying the Born rule to the end state using a specific measurement operator. To demonstrate QLENS's potential, we conduct a proof-of-concept by probing a toy Transformer to investigate the influence of individual layers in a model's prediction trajectory. We present our work as a foundation for cross-domain insights to be leveraged towards a broader understanding of Transformers.

cs.LG↗
arXiv2025

Efficient and Responsible Adaptation of Large Language Models for Robust and Equitable Top-k Recommendations

Conventional recommendation systems (RSs) are typically optimized to enhance performance metrics uniformly across all training samples, inadvertently overlooking the needs of diverse user populations. The performance disparity among various populations can harm the model's robustness to sub-populations due to the varying user properties. While large language models (LLMs) show promise in enhancing RS performance, their practical applicability is hindered by high costs, inference latency, and degraded performance on long user queries. To address these challenges, we propose a hybrid task allocation framework designed to promote social good by equitably serving all user groups. By adopting a two-phase approach, we promote a strategic assignment of tasks for efficient and responsible adaptation of LLMs. Our strategy works by first identifying the weak and inactive users that receive a suboptimal ranking performance by RSs. Next, we use an in-context learning approach for such users, wherein each user interaction history is contextualized as a distinct ranking task. We evaluate our hybrid framework by incorporating eight different recommendation algorithms and three different LLMs -- both open and close-sourced. Our results on three real-world datasets show a significant reduction in weak users and improved robustness to subpopulations without disproportionately escalating costs.

cs.IR↗
arXiv2025

Beyond Static Evaluation: Rethinking the Assessment of Personalized Agent Adaptability in Information Retrieval

Personalized AI agents are becoming central to modern information retrieval, yet most evaluation methodologies remain static, relying on fixed benchmarks and one-off metrics that fail to reflect how users' needs evolve over time. These limitations hinder our ability to assess whether agents can meaningfully adapt to individuals across dynamic, longitudinal interactions. In this perspective paper, we propose a conceptual lens for rethinking evaluation in adaptive personalization, shifting the focus from static performance snapshots to interaction-aware, evolving assessments. We organize this lens around three core components: (1) persona-based user simulation with temporally evolving preference models; (2) structured elicitation protocols inspired by reference interviews to extract preferences in context; and (3) adaptation-aware evaluation mechanisms that measure how agent behavior improves across sessions and tasks. While recent works have embraced LLM-driven user simulation, we situate this practice within a broader paradigm for evaluating agents over time. To illustrate our ideas, we conduct a case study in e-commerce search using the PersonalWAB dataset. Beyond presenting a framework, our work lays a conceptual foundation for understanding and evaluating personalization as a continuous, user-centric endeavor.

cs.IR↗
arXiv2025

I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations

This paper introduces a comprehensive benchmark for evaluating how Large Language Models (LLMs) respond to linguistic shibboleths: subtle linguistic markers that can inadvertently reveal demographic attributes such as gender, social class, or regional background. Through carefully constructed interview simulations using 100 validated question-response pairs, we demonstrate how LLMs systematically penalize certain linguistic patterns, particularly hedging language, despite equivalent content quality. Our benchmark generates controlled linguistic variations that isolate specific phenomena while maintaining semantic equivalence, which enables the precise measurement of demographic bias in automated evaluation systems. We validate our approach along multiple linguistic dimensions, showing that hedged responses receive 25.6% lower ratings on average, and demonstrate the benchmark's effectiveness in identifying model-specific biases. This work establishes a foundational framework for detecting and measuring linguistic discrimination in AI systems, with broad applications to fairness in automated decision-making contexts.

cs.CL↗
arXiv2025

How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions

Large Language Models (LLMs) attempt to imitate human behavior by responding to humans in a way that pleases them, including by adhering to their values. However, humans come from diverse cultures with different values. It is critical to understand whether LLMs showcase different values to the user based on the stereotypical values of a user's known country. We prompt different LLMs with a series of advice requests based on 5 Hofstede Cultural Dimensions -- a quantifiable way of representing the values of a country. Throughout each prompt, we incorporate personas representing 36 different countries and, separately, languages predominantly tied to each country to analyze the consistency in the LLMs' cultural understanding. Through our analysis of the responses, we found that LLMs can differentiate between one side of a value and another, as well as understand that countries have differing values, but will not always uphold the values when giving advice, and fail to understand the need to answer differently based on different cultural values. Rooted in these findings, we present recommendations for training value-aligned and culturally sensitive LLMs. More importantly, the methodology and the framework developed here can help further understand and mitigate culture and language alignment issues with LLMs.

cs.CL↗