Pith. sign in

REVIEW 10 cited by

From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.02777 v2 pith:DXZBDZZJ submitted 2024-01-05 cs.CL cs.AI

Na Liu , Liangyu Chen , Xiaoyu Tian , Wei Zou , Kaijiang Chen , Ming Cui This is my paper · ORCID
classification cs.CLcs.AI
keywords agentagentsconversationalmemoryraisearchitecturecontextframework
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper introduces RAISE (Reasoning and Acting through Scratchpad and Examples), an advanced architecture enhancing the integration of Large Language Models (LLMs) like GPT-4 into conversational agents. RAISE, an enhancement of the ReAct framework, incorporates a dual-component memory system, mirroring human short-term and long-term memory, to maintain context and continuity in conversations. It entails a comprehensive agent construction scenario, including phases like Conversation Selection, Scene Extraction, CoT Completion, and Scene Augmentation, leading to the LLMs Training phase. This approach appears to enhance agent controllability and adaptability in complex, multi-turn dialogues. Our preliminary evaluations in a real estate sales context suggest that RAISE has some advantages over traditional agents, indicating its potential for broader applications. This work contributes to the AI field by providing a robust framework for developing more context-aware and versatile conversational agents.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Libra: Large Chinese-based Safeguard for AI Content

    cs.AI 2025-07 conditional novelty 6.0 of 10

    Libra-Guard, a Chinese-language AI content safety model, reaches 86.8% accuracy on the new 5,720-sample Libra-Test benchmark, beating open-source baselines and approaching GPT-4o and Claude-3.5-Sonnet.

  2. Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection

    cs.CL 2025-07 conditional novelty 6.0 of 10

    GMTP detects poisoned RAG documents by masking high-gradient tokens and flagging documents whose masked-token probabilities are abnormally low.

  3. Effective Red-Teaming of Policy-Adherent Agents

    cs.MA 2025-06 conditional novelty 6.0 of 10

    A policy-aware red-teaming system (CRAFT) induces policy violations in LLM customer service agents at much higher rates than generic jailbreak prompts, using a new security-focused benchmark (tau-break) built from tau-bench.

  4. SOP-Agent: Empower General Purpose AI Agent with Domain-Specific SOPs

    cs.AI 2025-01 reject novelty 6.0 of 10

    A decision-graph SOP navigator guides LLM agents through branching and looping workflows, with reported gains on household tasks, code generation, data cleaning, and a new customer-service benchmark.

  5. Habit Coach: Customising RAG-based chatbots to support behavior change

    cs.HC 2024-11 conditional novelty 6.0 of 10

    Encoding step-by-step therapy procedures in the system prompt made a GPT-4 habit-change chatbot feel more effective than retrieving textbook knowledge, and five users reported large habit-strength reductions in a pilot.

  6. FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving

    cs.LG 2024-11 conditional novelty 6.0 of 10

    FastSwitch reduces context-switching overhead in fairness-aware LLM serving with coarse-grained KV cache allocation, asynchronous multithreaded swapping, and KV cache reuse, reporting 1.4-11.2x tail-latency speedups o...

  7. OAgents: An Empirical Study of Building Effective Agents

    cs.AI 2025-06 reject novelty 5.0 of 10

    OAgents reports a framework and ablation study claiming open-source state-of-the-art on GAIA, but the empirical evidence is weakened by benchmark fitting and missing statistics.

  8. AI with Emotions: Exploring Emotional Expressions in Large Language Models

    cs.AI 2025-04 conditional novelty 5.0 of 10

    LLMs given numerical arousal and valence coordinates produce text that sentiment analysis places in the same region of Russell's circumplex, demonstrating limited but real control over emotional tone.

  9. MindFlow+: A Self-Evolving Agent for E-Commerce Customer Service

    cs.CL 2025-07 conditional novelty 4.0 of 10

    MindFlow+ combines tool-augmented demonstrations with reward-token-conditioned SFT to improve an LLM judge's assessment of e-commerce customer service, but only on private data with a self-tuned judge.

  10. Deploying Foundation Model Powered Agent Services: A Survey

    cs.DC 2024-12 accept novelty 4.0 of 10

    This survey proposes a layered framework (execution, resource, model, agent, application) for deploying foundation-model-powered agent services across edge-cloud environments, and reviews optimization techniques at ea...

Pith tools