Tag
Struct-Searcher introduces a belief revision theory-based structural agentic workflow for multimodal deep information seeking, achieving significant accuracy improvements over existing vision-language models and deep research agents.
XTraceAI launched a managed memory API for conversational AI agents, featuring an open-source SDK (xmem) with AGM-style belief revision to handle contradictions and automatic fact extraction. It uses PostgreSQL with pgvector for semantic retrieval and supports multi-tenant isolation, allowing developers to offload memory management.
This paper introduces Preregistered Belief Revision Contracts (PBRC), a protocol-level mechanism for multi-agent systems (including LLM-based agents) that separates open communication from admissible belief changes by publicly fixing evidence triggers and revision operators. The work addresses dangerous conformity effects in agent deliberation and provides formal guarantees that social-only pressure cannot drive false consensus.
Large-scale study finds LLM-based scientific agents ignore evidence 68% of the time and rarely revise beliefs, showing they execute workflows but lack genuine scientific reasoning.