ARAnup Roy

Anup Roy

*This is an algorithmically generated author record based on publicly available information.

Anup Roy has a total of 5 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PyRAMIND: Auditable Deterministic Pyramid Memory for Long-Running LLM Agents

    by Anup Roy, Rishabh Gyanendra Upadhyay, Aidan Philip Millar, Larry Murray, Robin Mills

    Long-running LLM agents are increasingly considered for regulated, high-consequence domains such as finance, compliance, and audit, where memory must be accurate, traceable, replayable, and inspectable after a decision. Existing agent-memory systems often invoke an LLM during maintenance operations such as fact extraction, consolidation, updating, summarization, and forgetting. Although effective, this design makes it harder to reconstruct why a memory existed, changed, or was removed at a particular point in time. We present PyRAMIND (Pyramidal Retention with Arithmetic Memory for Inference-time Determinism), an auditable memory architecture in which write consolidation, reinforcement, forgetting, tier promotion, and retrieval scoring are closed-form arithmetic over cached embeddings. Only optional entity tagging at ingest and answer generation at query time call an external LLM. Given fixed embeddings, cached boundary-model outputs, parameters, and software, each maintenance transition is replayable from ordered inputs. PyRAMIND stores memories in a four-tier Pyramid (raw →facts →themes→worldview) and ranks them with a max-ensemble retention score modulated by local semantic density. Under a matched harness, PyRAMIND achieves competitive accuracy on long-horizon memory tasks (0.93 on LongMemEval-S) despite eliminating LLM calls from the memory-maintenance path, while reducing memory-lifecycle token expenditure to 1.4k LLM tokens per turn versus 3.1k for reproduced Mem0 OSS and 4.2k for Zep v3. Performance is weaker on temporal and multi-hop reasoning tasks (0.62 on LoCoMo), highlighting the continued value of richer relational memory structures for compositional reasoning. These results suggest that strong long-term memory performance is possible without LLM-mediated maintenance, and motivate future replayable memory systems that add temporal and relational structure while preserving auditable deterministic maintenance.

  • Open Access

    BANANA: Bounded Adaptive Navigation Architecture for Nested Archives

    by Anup Roy, Rishabh Gyanendra Upadhyay, Animesh Rameshbhai Panara, Aidan Philip Millar, Larry Murray, Robin Mills