Tag: LLM agents
Browse our exclusive articles!
Preventing Capability Loss in Self-Evolving LLM Agents
Explore how Capability-Preserving Evolution (CPE) helps self-evolving LLM agents maintain skills and prevent capability degradation during lifelong adaptat...
Agentic MIP Research: Fast Constraint Handler Creation
Discover how agentic MIP research uses LLM agents to accelerate constraint handler generation and improve mixed-integer programming solver efficiency.
Token Economics for LLM Agents: Computing & Economics Insights
Explore token economics in LLM agents with a dual perspective from computing and economics, addressing efficiency, collaboration, and security challenges.
OPT-BENCH: Benchmarking Self-Optimization in LLM Agents
Discover OPT-BENCH, a new benchmark evaluating how Large Language Models self-optimize in large-scale search spaces through iterative learning.
EnvTrustBench: Benchmarking Evidence-Grounding Defects in LLMs
Discover EnvTrustBench, a framework to benchmark and reduce evidence-grounding defects in LLM agents caused by overtrusting environmental evidence.