DACS achieves 90-98% steering accuracy in multi-agent LLM systems by agent-triggered asymmetric context scoping, versus 21-60% for flat-context baselines across 200 trials.
Adaptive Focus Memory for Language Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ATLAS-RTC raises first-attempt success on structured LLM generation and tool calling by 20-37.8 points through closed-loop token-level interventions.
citing papers explorer
-
Dynamic Attentional Context Scoping: Agent-Triggered Focus Sessions for Isolated Per-Agent Steering in Multi-Agent LLM Orchestration
DACS achieves 90-98% steering accuracy in multi-agent LLM systems by agent-triggered asymmetric context scoping, versus 21-60% for flat-context baselines across 200 trials.
-
ATLAS-RTC: Closing the Loop on LLM Agent Output with Token-Level Runtime Control
ATLAS-RTC raises first-attempt success on structured LLM generation and tool calling by 20-37.8 points through closed-loop token-level interventions.