pith. sign in

arxiv: 2402.17574 · v3 · pith:PTNQXGGLnew · submitted 2024-02-27 · 💻 cs.AI · cs.CL

Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization

classification 💻 cs.AI cs.CL
keywords agent-propolicyreflectiondynamicllm-basedoptimizationtaskagents
0
0 comments X
read the original abstract

Large Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks. However, most LLM-based agents are designed as specific task solvers with sophisticated prompt engineering, rather than agents capable of learning and evolving through interactions. These task solvers necessitate manually crafted prompts to inform task rules and regulate LLM behaviors, inherently incapacitating to address complex dynamic scenarios e.g., large interactive games. In light of this, we propose Agent-Pro: an LLM-based Agent with Policy-level Reflection and Optimization that can learn a wealth of expertise from interactive experiences and progressively elevate its behavioral policy. Specifically, it involves a dynamic belief generation and reflection process for policy evolution. Rather than action-level reflection, Agent-Pro iteratively reflects on past trajectories and beliefs, fine-tuning its irrational beliefs for a better policy. Moreover, a depth-first search is employed for policy optimization, ensuring continual enhancement in policy payoffs. Agent-Pro is evaluated across two games: Blackjack and Texas Hold'em, outperforming vanilla LLM and specialized models. Our results show Agent-Pro can learn and evolve in complex and dynamic scenes, which also benefits numerous LLM-based applications.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

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

  1. PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts

    cs.CR 2026-05 unverdicted novelty 7.0

    PragLocker protects agent prompts as IP by building non-portable obfuscated versions that function only on the intended LLM through code-symbol semantic anchoring followed by target-model feedback noise injection.

  2. SAGE: A Service Agent Graph-guided Evaluation Benchmark

    cs.AI 2026-04 unverdicted novelty 7.0

    SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 m...

  3. C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving

    cs.AI 2026-03 unverdicted novelty 7.0

    C-TRAIL combines LLM commonsense with a dual-trust mechanism and Dirichlet-weighted Monte Carlo Tree Search to improve trajectory planning accuracy and safety in autonomous driving.

  4. Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning

    cs.CL 2026-06 unverdicted novelty 6.0

    EDV decouples execution, distillation by a third-party agent, and consensus verification to filter erroneous trajectories in LLM agent experience learning, outperforming baselines on tau2-bench, Mind2Web, and MMTB.

  5. PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts

    cs.CR 2026-05 unverdicted novelty 6.0

    PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.

  6. Reflection of Episodes: Learning to Play Game from Expert and Self Experiences

    cs.AI 2025-02 unverdicted novelty 5.0

    ROE framework lets LLM defeat Very Hard bot in TextStarCraft II via keyframe selection, expert/self-experience decisions, and post-game reflection for new self-experience.

  7. Agent System Operations: Categorization, Challenges, and Future Directions

    cs.MA 2026-06 unverdicted novelty 3.0

    This survey categorizes anomalies in agent systems into intra-agent and inter-agent types and introduces the AgentOps framework with four operational stages.

  8. Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

    cs.AI 2025-01 unverdicted novelty 3.0

    The paper surveys reinforced reasoning techniques for LLMs, covering automated data construction, learning-to-reason methods, and test-time scaling as steps toward Large Reasoning Models.