Rhea: Role-aware Heuristic Episodic Attention for Conversational LLMs

• URL: http://arxiv.org/abs/2512.06869v1
• Date: Sun, 07 Dec 2025 14:50:03 GMT
• Title: Rhea: Role-aware Heuristic Episodic Attention for Conversational LLMs
• Authors: Wanyang Hong, Zhaoning Zhang, Yi Chen, Libo Zhang, Baihui Liu, Linbo Qiao, Zhiliang Tian, Dongsheng Li,
• Abstract summary: Large Language Models (LLMs) have achieved remarkable performance on single-turn tasks, yet their effectiveness deteriorates in multi-turn conversations.<n>We propose Rhea, a novel framework that decouples conversation history into two functionally independent memory modules.<n>Experiments show that Rhea mitigates performance decay and improves overall accuracy by 1.04 points on a 10-point scale.
• Score: 36.91809943381492
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have achieved remarkable performance on single-turn tasks, yet their effectiveness deteriorates in multi-turn conversations. We define this phenomenon as cumulative contextual decay - a progressive degradation of contextual integrity caused by attention pollution, dilution, and drift. To address this challenge, we propose Rhea (Role-aware Heuristic Episodic Attention), a novel framework that decouples conversation history into two functionally independent memory modules: (1) an Instructional Memory (IM) that persistently stores high-fidelity global constraints via a structural priority mechanism, and (2) an Episodic Memory (EM) that dynamically manages user-model interactions via asymmetric noise control and heuristic context retrieval. During inference, Rhea constructs a high signal-to-noise context by applying its priority attention: selectively integrating relevant episodic information while always prioritizing global instructions. To validate this approach, experiments on multiple multi-turn conversation benchmarks - including MT-Eval and Long-MT-Bench+ - show that Rhea mitigates performance decay and improves overall accuracy by 1.04 points on a 10-point scale (a 16% relative gain over strong baselines). Moreover, Rhea maintains near-perfect instruction fidelity (IAR > 8.1) across long-horizon interactions. These results demonstrate that Rhea provides a principled and effective framework for building more precise, instruction-consistent conversational LLMs.

Related papers

• Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning [14.368376032599437]
  Amory is a working memory framework that actively constructs structured memory representations during offline time.<n>Amory organizes conversational fragments into episodic narratives, consolidates memories with momentum, and semanticizes peripheral facts into semantic memory.<n>Amory achieves considerable improvements over previous state-of-the-art, with performance comparable to full context reasoning while reducing response time by 50%.
  arXiv  Detail & Related papers  (2026-01-09T19:51:11Z)
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents [80.33280979339123]
  We introduce Memory-T1, a framework that learns a time-aware memory selection policy using reinforcement learning (RL)<n>On the Time-Dialog benchmark, Memory-T1 boosts a 7B model to an overall score of 67.0%, establishing a new state-of-the-art performance for open-source models.
  arXiv  Detail & Related papers  (2025-12-23T06:37:29Z)
• CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models [21.427373172124167]
  Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions.<n>We introduce CogMem, a memory-augmented LLM architecture that supports sustained iterative reasoning through structured, persistent memory.<n> Experiments on TurnBench show that this layered design mitigates reasoning failures, controls context growth, and improves consistency across extended reasoning chains.
  arXiv  Detail & Related papers  (2025-12-16T06:01:08Z)
• Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning [137.33138614095435]
  Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models.<n>Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval.<n>We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions.
  arXiv  Detail & Related papers  (2025-11-12T08:29:39Z)
• KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues [58.305425399644086]
  Multi-Turn Long-Form Question Answering (MT-LFQA) is a key application paradigm of Large Language Models (LLMs) in knowledge-intensive domains.<n>We introduce textbfKnowMT-Bench, the textitfirst-ever benchmark designed to systematically evaluate MT-LFQA for LLMs across knowledge-intensive fields.
  arXiv  Detail & Related papers  (2025-09-26T04:32:29Z)
• Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges [63.741916531380696]
  The CHiME-7 and 8 distant speech recognition (DASR) challenges focus on multi-channel, generalizable, joint automatic speech recognition (ASR) and diarization of conversational speech.<n>This paper outlines the challenges' design, evaluation metrics, datasets, and baseline systems while analyzing key trends from participant submissions.
  arXiv  Detail & Related papers  (2025-07-24T07:56:24Z)
• PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding [20.849307413516183]
  We propose PaceLLM, featuring two innovations: (1) a Persistent Activity (PA) Mechanism that mimics prefrontal cortex (PFC) neurons' persistent firing by introducing an activation-level memory bank to dynamically retrieve, reuse, and update critical FFN states, addressing contextual decay; and (2) Cortical Expert (CE) Clustering that emulates task-adaptive neural specialization to reorganize FFN weights into semantic modules, establishing cross-token dependencies and mitigating fragmentation.
  arXiv  Detail & Related papers  (2025-06-18T09:17:06Z)
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory [0.5584627289325719]
  Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses.<n>But their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues.<n>We introduce Mem0, a scalable memory-centric architecture that addresses this issue by dynamically extracting, consolidating, and retrieving salient information from ongoing conversations.
  arXiv  Detail & Related papers  (2025-04-28T01:46:35Z)
• In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents [70.12342024019044]
  Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information limits their effectiveness.<n>We propose Reflective Memory Management (RMM), a novel mechanism for long-term dialogue agents, integrating forward- and backward-looking reflections.<n>RMM shows more than 10% accuracy improvement over the baseline without memory management on the LongMemEval dataset.
  arXiv  Detail & Related papers  (2025-03-11T04:15:52Z)
• Decoding the Flow: CauseMotion for Emotional Causality Analysis in Long-form Conversations [22.000288488609733]
  CauseMotion is a long-sequence emotional causal reasoning framework grounded in Retrieval-Augmented Generation (RAG) and multimodal fusion.<n>By integrating RAG with a sliding window mechanism, it effectively retrieves and leverages contextually relevant dialogue segments.<n>A GLM-4 integrated with CauseMotion achieves an 8.7% improvement in causal accuracy over the original model and surpasses GPT-4o by 1.2%.<n>On the publicly available DiaASQ dataset, CauseMotion-GLM-4 achieves state-of-the-art results in accuracy, F1 score, and causal reasoning accuracy.
  arXiv  Detail & Related papers  (2025-01-01T09:10:32Z)
• Echotune: A Modular Extractor Leveraging the Variable-Length Nature of Speech in ASR Tasks [4.132793413136553]
  We introduce Echo-MSA, a nimble module equipped with a variable-length attention mechanism. The proposed design captures the variable length feature of speech and addresses the limitations of fixed-length attention.
  arXiv  Detail & Related papers  (2023-09-14T14:51:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.