state-aware

This paper presents TRACE, a query processing framework that models conversational data as temporal evidence graphs to enable state-aware reasoning over evolving user states, improving temporal and multi-hop reasoning for long-conversation QA.

Introduces Mixture-of-Control (MoC), a lightweight fine-tuning framework that integrates local and global control signals via sparse mixture-of-experts for efficient cross-block communication, achieving better performance than prior state-based methods.

The paper proposes SVoT, a reinforcement learning framework that generates interleaved, verifiable intermediate states and visualizations for multi-hop spatial reasoning in MLLMs, achieving significant accuracy gains on new benchmarks involving multi-object interactions and numerical reasoning.

Introduces AgentRevive, a Markov state-aware framework for resilient multi-agent collaboration that uses soft state transitions (Active, Standby, Terminated) to prevent premature pruning of agents that may recover, reducing token consumption while improving performance on reasoning and domain tasks.

This paper identifies a critical failure mode in LLM agents where they fail to update personalized memories when new evidence conflicts with prior beliefs. It introduces the STALE benchmark and a three-dimensional probing framework, revealing that even the best models achieve only 55.2% accuracy, and proposes CUPMem as a prototype for robust memory revision.