3 papers
cs.AI2026
Self-Evolving Agents with Anytime-Valid Certificates
Biswa Sengupta
Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produced by the policy being update…
cs.LG2026
HARBOR: Automated Harness Optimization
Biswa Sengupta, Jinhua Wang
Long-horizon language-model agents are dominated, in lines of code and in operational complexity, not by their underlying model but by the harness that wraps it: context compaction…
cs.SE2026
From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to Python
Jinhua Wang, Biswa Sengupta
Cross-language migration of large software systems is a persistent engineering challenge, particularly when the source codebase evolves rapidly. We present a methodology for LLM-as…