3 papers
cs.CL2026
Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation
Pratyay Banerjee, Ankit Chadha
Multi-agent LLM systems coordinate through natural-language messages that consume 40--60\% of their token budget. Replacing these with structured graphs reduces cost but fails on t…
cs.CL2026
APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
Pratyay Banerjee, Masud Moshtaghi, Shivashankar Subramanian +2
Large language models still struggle with reliable long-term conversational memory: simply enlarging context windows or applying naive retrieval often introduces noise and destabil…
cs.CL2026
APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay
Pratyay Banerjee, Masud Moshtaghi, Ankit Chadha
LLM agents rerun full reasoning for every task, even one they solved moments earlier. We introduce \textbf{APEX-EM}, a non-parametric experience memory that stores complete procedu…