V. K. Madisetti

Programmed Interventions To Prevent Delusions From Excessive Use of Conversational AI Bots

Large language models (LLMs) frequently endorse and elaborate on users’ delusional beliefs, a failure mode termed psychogenicity in the Psychosis-Bench study of Au Yeung et al., whose framing we adopt. We present the first systematic evaluation of whether anti-sycophancy interventions transfer to psychosis-relevant con...

Training-Free Cross-Domain Learning Transfer in Reasoning Models

Large language models often solve problems within familiar domains but struggle to transfer the same reasoning strategy across domains with different surface vocabularies. We present COMETS (Cross-domain Memory Enrichment and Transfer System), a training-free framework for cross-domain reasoning transfer through explic...

When Too Many Cooks Spoil the Broth: Three Failure Modes of Multi-Agent LLM Reliability

ANVIL-FL: Runtime-Aware Fault Localization for Code Generation and Debugging

Fault localization (FL) is a dominant debugging cost, yet most recent LLM-based FL systems rely on static or coverage-only signals. We introduce <sc>ANVIL-FL</sc> (Anchored Near-failure Value-Informed Localization), a two-turn, tool-free framework that combines LLM reasoning with failure-anchored runtime telemetry. A l...