3 papers
cs.CL2026
Mind the Cap: Output-Budget Regimes Change the Measured Multilingual Reasoning Gap
Ankit Goyal, Jaideep Ray
Multilingual evaluations report accuracy at a single output-token cap, but languages need different numbers of tokens to express the same content, so the cap is a hidden experiment…
cs.CL2026
From Agent Failures to Text Policies: What Works and What Breaks
Jaideep Ray, Ankit Goyal
TextGrad improves language-model systems by revising text from feedback. Its core thesis is that natural-language feedback can act as a gradient for optimizing text components with…
cs.SE2026
Structured Feedback Improves Repair in an LLM Agent Loop
Jaideep Ray, Ankit Goyal
LLM agents often retry after external validation rejects a candidate, but the interface between validation and the next model call remains underspecified. We introduce VeriHarness,…