Munawar Kazmi

Certified Bounds on Achievable Legibility under a Path Cost Budget

Legible motion is optimised rather than decided, and for good reason: the optimum is intractable. What an optimiser reports is the clarity it found, which does not establish that no clearer trajectory exists, so a question of the form "can any trajectory within this budget be rea...

Certified Bounds on Achievable Legibility under a Path Cost Budget

Legible motion is optimised rather than decided, and for good reason: the optimum is intractable. What an optimiser reports is the clarity it found, which does not establish that no clearer trajectory exists, so a question of the form "can any trajectory within this budget be rea...

plan-failure-bench: A Machine-Checkable Benchmark of How Language Model Planners Fail

Evaluations of language model planners mostly rest on foundations a reader cannot audit: success rates that cannot tell a model refusing every task from one walking into every trap, ground-truth labels that are authored rather than proved, and human or LLM judges somewhere in the...

plan-failure-bench: A Machine-Checkable Benchmark of How Language Model Planners Fail

Evaluations of language model planners mostly rest on foundations a reader cannot audit: success rates that cannot tell a model refusing every task from one walking into every trap, ground-truth labels that are authored rather than proved, and human or LLM judges somewhere in the...