arXiv subjects

Sahil Bhatnagar

Publications and source records attributed to Sahil Bhatnagar.

5 recordsLinked to original sources

arXiv2026

Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents

Persistent memory is entering production-oriented agent platforms to help long-horizon agents accumulate experience across sessions. Yet a post-task curator agent restricted to completed trajectories can preserve errors, overgeneralize partial evidence, or retain stale knowledge. We introduce environment-probing curation, a deployment-compatible extension that gives an existing asynchronous curator agent least-privilege, read-only world tools to check, scope, and refresh candidate memories. It requires no model retraining and leaves the task agent, retriever, memory representation, and production write authority unchanged. In a production-like GitHub Copilot (GHCP) harness built on its SDK, we compare stateless execution, full in-context learning, GHCP + Mem, and GHCP + Mem (w/ Env Probing) on CLBench database exploration and 90 adapted APEX management-consulting tasks. On CLBench, probing raises pass rate from 39% to 73% and pass-discounted reward from 8.60 to 22.60 while reducing queries from 8.8 to 4.7 per question and task-agent cost from \$3.38 to \$1.68. Across six APEX worlds, all 18 memory-versus-baseline mean reward comparisons are positive and task-agent tool calls fall by 16--75%; probing gives the best task-agent reward gain per dollar in five worlds. Probing also attains higher mean reward than GHCP + Mem on both Sonnet 4.6 and Opus 4.7 without schema drift. Environment probing therefore turns existing agent-memory curation into an environment-informed, auditable process while preserving a compact task-time interface.

cs.AI↗

arXiv2026

Is Bash All You Need? An Empirical Study of Tool Interfaces for Enterprise Digital Worker Agents

In this study, we examine whether a general shell can outperform specialized tools on enterprise tasks. Shell-based agents have shown strong results in coding, but enterprise work also involves moving between applications and services, coordinating with coworkers, and performing professional analysis. We compare five tool interfaces on TheAgentCompany and APEX-Agents using Opus-4.8 and GPT-5.5: typed tools, typed tools plus bash, bash alone, bash with persistent agent-synthesized tools, and programmatic tool calling (PTC), which runs programs whose actions are restricted to a typed tool catalog. Bash alone outperforms typed tools on both benchmarks, improving score by 21.8-24.5 pp on TheAgentCompany and 4.8-7.4 pp on APEX-Agents while using 19-72% fewer total tokens. Adding typed tools or persistent tool synthesis to bash produces no detectable pooled score gain. PTC uses fewer tokens than direct typed calls with broadly similar task performance, but generally underperforms bash alone in both quality and cost efficiency. For enterprise practitioners, these results favor bash alone when arbitrary execution can be isolated and PTC when security or compliance policies require a fixed tool catalog.

cs.SE↗

arXiv2026

AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases

We present AgenticRAG, a practical agentic harness for retrieval and analysis over enterprise knowledge bases. Standard RAG pipelines place significant burden of grounding on the search stack, constraining the language model to a fixed candidate set chosen deep in the retrieval process. Our approach reduces this overdependence by layering a lightweight harness on top of existing enterprise search infrastructure, equipping a reasoning LLM with search, find, open, and summarize tools enabling the model to iteratively retrieve information, navigate within documents, and analyze evidence autonomously. On three open benchmarks we observe substantial gains: $49.6\%$ recall@1 on BRIGHT (+21.8 pp over the best embedding baseline), 0.96 factuality on WixQA ($+13\%$ relative improvement), and $92\%$ answer correctness on FinanceBench--within 2 pp of oracle access to true evidence. Ablation studies show that the most significant factor is the shift from single-shot retrieval to agentic tool use ($5.9\times$ improvement), while multi-query search and in-document navigation contribute to both quality and efficiency. We present various design choices in our agentic harness that were informed by pre-production deployments. Our results demonstrate its suitability for real-world enterprise production environments.

cs.AI↗

arXiv2025

Abstract Operations Research Modeling Using Natural Language Inputs

Operations research (OR) uses mathematical models to enhance decision-making, but developing these models requires expert knowledge and can be time-consuming. Automated mathematical programming (AMP) has emerged to simplify this process, but existing systems have limitations. This paper introduces a novel methodology that uses recent advances in Large Language Model (LLM) to create and edit OR solutions from non-expert user queries expressed using Natural Language. This reduces the need for domain expertise and the time to formulate a problem. The paper presents an end-to-end pipeline, named NL2OR, that generates solutions to OR problems from natural language input, and shares experimental results on several important OR problems.

cs.AI↗

arXiv2022

CASPR: Customer Activity Sequence-based Prediction and Representation

Tasks critical to enterprise profitability, such as customer churn prediction, fraudulent account detection or customer lifetime value estimation, are often tackled by models trained on features engineered from customer data in tabular format. Application-specific feature engineering adds development, operationalization and maintenance costs over time. Recent advances in representation learning present an opportunity to simplify and generalize feature engineering across applications. When applying these advancements to tabular data researchers deal with data heterogeneity, variations in customer engagement history or the sheer volume of enterprise datasets. In this paper, we propose a novel approach to encode tabular data containing customer transactions, purchase history and other interactions into a generic representation of a customer's association with the business. We then evaluate these embeddings as features to train multiple models spanning a variety of applications. CASPR, Customer Activity Sequence-based Prediction and Representation, applies Transformer architecture to encode activity sequences to improve model performance and avoid bespoke feature engineering across applications. Our experiments at scale validate CASPR for both small and large enterprise applications.

cs.LG↗