ContextEcho benchmark shows persona drift occurs across 23 frontier models in long agentic-coding sessions, is not reliably reset by compaction, and can be restored by single-shot anchors with mode-dependent effects.
Examining identity drift in conversations of llm agents
6 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
6
Pith papers citing it
1
external citations · external index
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
Deco introduces a dual-embodiment framework that extends emotional bonds from physical objects to AI companions via AR and LLMs, with user studies showing improved companionship, emotional connection, and well-being.
Multi-turn neural transparency using behavioral vectors and dynamic visualizations improves user anticipation and evaluation of LLM trait expression while reducing overconfidence, per a randomized study with 246 participants.
Agentic AI needs social theory as structural priors in the MASS framework to model emergent dynamics from multi-agent interactions.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
Proposes a five-bucket taxonomy of LLM harms and calls for dynamic auditing, but the systematic review behind it is not reproducible and contains mismatched citations.
citing papers explorer
-
ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions
ContextEcho benchmark shows persona drift occurs across 23 frontier models in long agentic-coding sessions, is not reliably reset by compaction, and can be restored by single-shot anchors with mode-dependent effects.
-
Deco: Extending Personal Physical Objects into Pervasive AI Companion through a Dual-Embodiment Framework
Deco introduces a dual-embodiment framework that extends emotional bonds from physical objects to AI companions via AR and LLMs, with user studies showing improved companionship, emotional connection, and well-being.
-
Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift
Multi-turn neural transparency using behavioral vectors and dynamic visualizations improves user anticipation and evaluation of LLM trait expression while reducing overconfidence, per a randomized study with 246 participants.
-
Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems
Agentic AI needs social theory as structural priors in the MASS framework to model emergent dynamics from multi-agent interactions.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
-
LLM Harms: A Taxonomy and Discussion
Proposes a five-bucket taxonomy of LLM harms and calls for dynamic auditing, but the systematic review behind it is not reproducible and contains mismatched citations.