Nachiket Lele

Faithful, Query-Aware Compression of LLM Agent Tool Output

Tool outputs—web pages, JSON API responses, logs, CSV exports—are the largest andmost-ignored token sink in LLM agent loops. A single verbose tool result can dwarf the agent’sinstructions, and the standard mitigation, blind truncation, silently discards the fact the agentneeds. W...

Faithful, Query-Aware Compression of LLM Agent Tool Output

Tool outputs—web pages, JSON API responses, logs, CSV exports—are the largest andmost-ignored token sink in LLM agent loops. A single verbose tool result can dwarf the agent’sinstructions, and the standard mitigation, blind truncation, silently discards the fact the agentneeds. W...

Precision- and Error-Aware SQL Equivalence: Deciding Rewrites Under IEEE-754 Rounding and Runtime Errors

Every published SQL equivalence checker — Cosette/HoTTSQL, EQUITAS, SPES, WeTune, and the current frontier QED, VeriEQL, and Polygon — decides whether two queries are equivalent by modeling numeric columns as exact mathematical integers or reals under total, error-free arithmetic...

Precision- and Error-Aware SQL Equivalence: Deciding Rewrites Under IEEE-754 Rounding and Runtime Errors

Every published SQL equivalence checker — Cosette/HoTTSQL, EQUITAS, SPES, WeTune, and the current frontier QED, VeriEQL, and Polygon — decides whether two queries are equivalent by modeling numeric columns as exact mathematical integers or reals under total, error-free arithmetic...

provensql: Sound, Catalog-Aware Detection of Behavior-Changing SQL Edits — and Why LLMs Can't Be Trusted To Do It

provensql decides whether an edit to a SQL query changes its result. It returns EQUIVALENT only with a proof (canonical-form or SMT), DIFFERENT only with a concrete, executable counterexample database instance, and otherwise abstains (UNKNOWN) rather than guess — soundness (never...

provensql: Sound, Catalog-Aware Detection of Behavior-Changing SQL Edits — and Why LLMs Can't Be Trusted To Do It

provensql decides whether an edit to a SQL query changes its result. It returns EQUIVALENT only with a proof (canonical-form or SMT), DIFFERENT only with a concrete, executable counterexample database instance, and otherwise abstains (UNKNOWN) rather than guess — soundness (never...