Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory
AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting interpretations of the same events. A concession during a client negotiation encodes as a `trust-building investment'' for one strategic goal and a `contractual liability'' for another. Current memory architectures assume a single correct encoding, or at best support multiple views over unified storage. We propose Rashomon Memory: an architecture where parallel goal-conditioned agents encode experiences according to their priorities and negotiate at query time through argumentation. Each perspective maintains its own ontology and knowledge graph. At retrieval, perspectives propose interpretations, critique each other's proposals using asymmetric domain knowledge, and Dung's argumentation semantics determines which proposals survive. The resulting attack graph is itself an explanation: it records which interpretation was selected, which alternatives were considered, and on what grounds they were rejected. We present a proof-of-concept showing that retrieval modes (selection, composition, conflict surfacing) emerge from attack graph topology, and that the conflict surfacing mode, where the system reports genuine disagreement rather than forcing resolution, lets decision-makers see the underlying interpretive conflict directly.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
From Rashomon Theory to PRAXIS: Efficient Decision Tree Rashomon Sets
Standard machine learning pipelines often admit many near-optimal models. These "Rashomon sets" pose a range of challenges and opportunities for uncertainty-aware, robust decision making. They allow users to incorporate …
Decision MakingExploring the Rashomon Set for Concept-Based Models
In many machine learning problems, there may exist multiple models that achieve nearly identical predictive performance while relying on fundamentally different internal logic. However, standard training procedures produ…
GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities
LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such agent-operated social platforms raise a new security concern: attackers may manipulate agents to induce group polarizati…
Knowledge GraphsRashomon Sets and Model Multiplicity in Federated Learning
The Rashomon set captures the collection of models that achieve near-identical empirical performance yet may differ substantially in their decision boundaries. Understanding the differences among these models, i.e., thei…
Federated LearningRashomon Capacity: A Metric for Predictive Multiplicity in Classification
Predictive multiplicity occurs when classification models with statistically indistinguishable performances assign conflicting predictions to individual samples. When used for decision-making in applications of consequen…
ClassificationDecision Making