Author

Atul Anand

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilation

A training-free remedy: an instruction compiler that rewrites the stacked prompt in a single LLM call and is reused across queries is evaluated, recovering up to +11 points of follow rate for weaker models, while leaving stronger models, which already internalise the same structure, essentially unchanged.

Atul Anand, S. Chattaraj · 0 citations

Preprint Aug 2026

Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools

Canary tools are introduced: diagnostic probe tools planted in an agent's Model Context Protocol (MCP) tool set, each engineered to probe one specific tool-selection weakness, evidence that the probes measure reasoning, not phrase-spotting.

Atul Anand, S. Chattaraj · 1 citation