REVIEW 7 cited by
Long Term Memory: The Foundation of AI Self-Evolution
Not yet reviewed by Pith; the record is open.
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
read the original abstract
Large language models (LLMs) like GPTs, trained on vast datasets, have demonstrated impressive capabilities in language understanding, reasoning, and planning, achieving human-level performance in various tasks. Most studies focus on enhancing these models by training on ever-larger datasets to build more powerful foundation models. While training stronger models is important, enabling models to evolve during inference is equally crucial, a process we refer to as AI self-evolution. Unlike large-scale training, self-evolution may rely on limited data or interactions. Inspired by the columnar organization of the human cerebral cortex, we hypothesize that AI models could develop cognitive abilities and build internal representations through iterative interactions with their environment. To achieve this, models need long-term memory (LTM) to store and manage processed interaction data. LTM supports self-evolution by representing diverse experiences across environments and agents. In this report, we explore AI self-evolution and its potential to enhance models during inference. We examine LTM's role in lifelong learning, allowing models to evolve based on accumulated interactions. We outline the structure of LTM and the systems needed for effective data retention and representation. We also classify approaches for building personalized models with LTM data and show how these models achieve self-evolution through interaction. Using LTM, our multi-agent framework OMNE achieved first place on the GAIA benchmark, demonstrating LTM's potential for AI self-evolution. Finally, we present a roadmap for future research, emphasizing the importance of LTM for advancing AI technology and its practical applications.
Forward citations
Cited by 7 Pith papers
-
On Path to Multimodal Historical Reasoning: HistBench and HistAgent
HistAgent, a history-specialized agent, scores 27.54% pass@1 and 36.47% pass@2 on the new 414-question HistBench benchmark, surpassing generalist agents tested on the same data.
-
AgentBrew: Lifelong Knowledge Brewing from Strong Teachers to Weak LLM Agents
A training-free method where a strong teacher turns a weak agent's failures into environment-validated notes that significantly boost the weak agent's test-time performance.
-
Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
An LLM agent that builds a tool-transition graph with state summaries from past experience improves tool selection and RL exploration by large margins on multi-turn benchmarks.
-
Ella: Embodied Social Agents with Lifelong Memory
Ella, an embodied social agent with a name-centric semantic memory and a spatiotemporal episodic memory, outperformed two re-implemented baselines in social influence and leadership tasks in a 3D simulation.
-
AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
AgentDistill distills agent capabilities without any training by having a teacher generate reusable MCP tool boxes that small-model students invoke at inference time.
-
Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
Alita achieves 75.15% pass@1 on GAIA validation by dynamically generating and reusing MCP-based tools, but the evaluation confounds model choice with the self-evolution mechanism.
-
R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
R1-Searcher++ uses SFT cold-start plus reinforcement learning with group and memorization rewards to teach Qwen-2.5-7B to balance internal knowledge and external retrieval, improving accuracy and reducing retrieval calls.
Discussion (0). Sign in to comment.