4 papers · 1 filter
Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets
Olga Manakina, Igor Bogdanov, Chung-Horng Lung
Large language models (LLMs) are increasingly deployed as multi-turn agents that must sustain goals, use tools, and adapt to other agents over extended interactions. However, exist…
Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy
Igor Bogdanov, Olga Manakina, Chung-Horng Lung
Large language model (LLM) agents may perform well on isolated tasks yet drift into inconsistency over extended interaction. We evaluate temporal consistency in a controlled 20-ste…
FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast
Igor Bogdanov, Chung-Horng Lung, Thomas Kunz +3
Can LLM agents improve decision-making through self-generated memory without gradient updates? We propose FORGE (Failure-Optimized Reflective Graduation and Evolution), a staged, p…
Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
Igor Bogdanov, Chung-Horng Lung, Thomas Kunz +3
Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reason…