ARXIV:2603.03078 · REINFORCEMENT LEARNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

arXiv

Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning.

METHOD

Full abstract

Agentic Reinforcement Learning (Agentic RL) has shown remarkable potential in large language model-based (LLM) agents. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning. However, an inherent limitation of existing Agentic RL methods is their reliance on a pure on-policy paradigm for exploration, restricting exploration to the agent's self-generated outputs and preventing the discovery of new reasoning perspectives for further improvement. While recent efforts incorporate auxiliary off-policy signals to enhance exploration, they typically utilize full off-policy trajectories for trajectory-level policy estimation, overlooking the necessity for the fine-grained, step-level exploratory dynamics within agentic rollout. In this paper, we revisit exploration in Agentic RL and propose Retrieval-Augmented Policy Optimization (RAPO), a novel RL framework that introduces retrieval to explicitly expand exploration during training. To achieve this, we decompose the Agentic RL training process into two phases: (i) Hybrid-policy Agentic Rollout, and (ii) Retrieval-aware Policy Optimization. Specifically, we propose a Hybrid-policy Agentic Rollout strategy, which allows the agents to continuously reason over the retrieved off-policy step-level traces. It dynamically extends the reasoning receptive field of agents, enabling broader exploration conditioned on external behaviors. Subsequently, we introduce the Retrieval-aware Policy Optimization mechanism, which calibrates the policy gradient estimation with retrieval reward and importance shaping, stabilizing training and prioritizing retrieval-illuminating exploration. Extensive experiments show that RAPO achieves an +5.0% average gain on fourteen datasets across three agentic reasoning tasks, while delivering 1.2x faster training efficiency.

RESULT

ScienceToStartup currently rates this 5.0/10 on the public viability pass. To achieve this, we decompose the Agentic RL training process into two phases: (i) Hybrid-policy Agentic Rollout, and (ii) Retrieval-aware Policy Optimization.

WHY NOW

Reinforcement Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score5.0

PainDevelop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2603.03078 · REINFORCEMENT LEARNING · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

arXiv

Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Reinforcement Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score5.0

PainDevelop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2603.03078

RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon filenot materializedderived fallback46 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

5.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Reinforcement Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Agentic Reinforcement Learning (Agentic RL) has shown remarkable potential in large language model-based (LLM) agents. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 5.0/10 on the public viability pass. To achieve this, we decompose the Agentic RL training process into two phases: (i) Hybrid-policy Agentic Rollout, and (ii) Retrieval-aware Policy Optimization.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Reinforcement Learning moved forward this cycle; last verified April 2026. Public score 5.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Reinforcement Learning

Competitors

not indexed

Competitive landscape

Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.

Segment

Reinforcement Learning

Adoption evidence

No public code link in the paper record yet

Commercial read

5.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2603.03078 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(46)

Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning

2025Yifei Chen, Guanting Dong et al.

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

2025Yulei Qin, Xiaoyu Tan et al.

ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization

2025Xixi Wu, Kuan Li et al.

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

2025Zhenghai Xue, Longtao Zheng et al.

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

2025Dongfu Jiang, Yi Lu et al.

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

2025Wenhao Zhang, Yuexiang Xie et al.

Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

2025Jiaxuan Gao, Wei Fu et al.

Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization

2025Zhenpeng Su, Leiyu Pan et al.

From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR

2025Jia Deng, Jie Chen et al.

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

2025Jinyuan Fang, Yan Peng et al.

Reasoning with Exploration: An Entropy Perspective

2025Daixuan Cheng, Shaohan Huang et al.

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

2025Yifan Sun, Jingyan Shen et al.

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

2025Shenzhi Wang, Le Yu et al.

WebDancer: Towards Autonomous Information Seeking Agency

2025Jialong Wu, Baixuan Li et al.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

2025Hao Sun, Zile Qiao et al.

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

2025Xiaoxi Li, Jiajie Jin et al.

Learning to Reason under Off-Policy Guidance

2025Jianhao Yan, Yafu Li et al.

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

2025Yang Yue, Zhiqin Chen et al.

BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

2025Jason Wei, Zhiqing Sun et al.

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

2025Jiazhan Feng, Shijue Huang et al.

Showing 20 of 46 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

none indexed

Extension

Builds On ThisRethinking Agentic Reinforcement Learning In Large Language Models

2.0

Commercially relevant

Higher ViabilityTool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning

7.0

Higher ViabilityProCeedRL: Process Critic with Exploratory Demonstration Reinforcement Learning for LLM Agentic Reasoning

7.0

Higher ViabilityProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation

6.0

Higher ViabilityExploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization

6.0

Higher ViabilityAgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents

7.0

Higher ViabilityPushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization

7.0

Higher ViabilityAT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search

6.0

Higher ViabilityPOPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration

6.0

Higher ViabilityRetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback

8.0

Conflicting

none indexed

Related Resources

Just-In-Time Reinforcement Learning(glossary)
Multi-Agent Reinforcement Learning(glossary)
Multi-Agent Test-Time Reinforcement Learning (MATTRL)(glossary)
How does PRISM improve reinforcement learning?(question)
What is the significance of reinforcement learning in AI?(question)
How does RetroAgent improve reinforcement learning?(question)
Reinforcement Learning – Use Cases(use_case)

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2603.03078
Route: /paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization
Active tab: read
Artifact: rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization/paper-pack
REST build passport API/api/v1/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "9aba965e-5808-4f71-9de3-1b531d7796b2",
  "arxiv_id": "2603.03078",
  "canonical_route": "/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization",
  "endpoints": {
    "paper_pack": "/api/v1/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization/paper-pack",
    "build_passport": "/api/v1/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization

stale

Proof freshness: stale
Proof status: unverified
Display score: 5/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

Canonical ID rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization | Route /paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2603.03078"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization",
  "normalized_query": "2603.03078",
  "route": "/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization",
  "paper_ref": "rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Watch and verify: RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

/buildability/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization

Watchwatch

Subject: RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization

Paper ref

rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization

arXiv id

2603.03078

Freshness

Generated at

2026-04-02T02:30:40.136Z

Evidence freshness

stale

Last verification

2026-04-02T02:30:40.136Z

Sources

References

Coverage

17%

Hash state

Lineage hash

e9078cb4628012433a2cdd58c7bda758fcaee57a5ad40e1a4322b1b8de9da24b

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: proof_status
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet
Unknown: proof verification has not been recorded yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization#webpage",
      "url": "https://sciencetostartup.com/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization",
      "name": "RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization",
      "description": "Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization#scholarlyArticle",
      "headline": "RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization",
      "description": "Develop Retrieval-Augmented Policy Optimization for enhanced exploration in LLM-based agentic reasoning.",
      "url": "https://sciencetostartup.com/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization",
      "sameAs": "https://arxiv.org/abs/2603.03078",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2603.03078"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-03-03T15:23:42.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7dbde77b268d8df57210ccc69fac37e3375a5595"
          },
          "url": "https://www.semanticscholar.org/paper/7dbde77b268d8df57210ccc69fac37e3375a5595"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d4cc1918e071be4148579a4984ee2a5ea682e31e"
          },
          "url": "https://www.semanticscholar.org/paper/d4cc1918e071be4148579a4984ee2a5ea682e31e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "055f039761d570658146e34dbe512d8671493887"
          },
          "url": "https://www.semanticscholar.org/paper/055f039761d570658146e34dbe512d8671493887"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "eb6ef63df104c1b35bbc2400f00285b3414400b2"
          },
          "url": "https://www.semanticscholar.org/paper/eb6ef63df104c1b35bbc2400f00285b3414400b2"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ca38d3dbf0ca25d4eeeb43becdc50aa45052e22d"
          },
          "url": "https://www.semanticscholar.org/paper/ca38d3dbf0ca25d4eeeb43becdc50aa45052e22d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "804039e844664365265dca969ae612d32a992503"
          },
          "url": "https://www.semanticscholar.org/paper/804039e844664365265dca969ae612d32a992503"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "10ab7d6caefec453d36640c7a839ed2080a2d060"
          },
          "url": "https://www.semanticscholar.org/paper/10ab7d6caefec453d36640c7a839ed2080a2d060"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f1e519e86b806db5b65d9330e902ceb74e261387"
          },
          "url": "https://www.semanticscholar.org/paper/f1e519e86b806db5b65d9330e902ceb74e261387"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "64b704bfabc7499e4c375e8845e4a3dceb3fe008"
          },
          "url": "https://www.semanticscholar.org/paper/64b704bfabc7499e4c375e8845e4a3dceb3fe008"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "4d5d951742d101e78646269a45f2573a597d54d6"
          },
          "url": "https://www.semanticscholar.org/paper/4d5d951742d101e78646269a45f2573a597d54d6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "69535d3c6ff3238f8e7b2b29c1d40ea9d9d7914f"
          },
          "url": "https://www.semanticscholar.org/paper/69535d3c6ff3238f8e7b2b29c1d40ea9d9d7914f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7fbabd628f9b1c08c5a357b7068a0effaacc820f"
          },
          "url": "https://www.semanticscholar.org/paper/7fbabd628f9b1c08c5a357b7068a0effaacc820f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d6a29be03a0497602e89311ec38e5141335647c5"
          },
          "url": "https://www.semanticscholar.org/paper/d6a29be03a0497602e89311ec38e5141335647c5"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "84ac4173ac8cd7cfea0262ceedc0796d0ea4b0e2"
          },
          "url": "https://www.semanticscholar.org/paper/84ac4173ac8cd7cfea0262ceedc0796d0ea4b0e2"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "638d402d7c097391d154043554467d077f45f4b1"
          },
          "url": "https://www.semanticscholar.org/paper/638d402d7c097391d154043554467d077f45f4b1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "23f655a7a596ab5f431ab9e18d5c641de3f8afb9"
          },
          "url": "https://www.semanticscholar.org/paper/23f655a7a596ab5f431ab9e18d5c641de3f8afb9"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "847d63914c51e3855ed7f13e74157daaa4a37d94"
          },
          "url": "https://www.semanticscholar.org/paper/847d63914c51e3855ed7f13e74157daaa4a37d94"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "143e18bfd7c356592e7c1439738a3525d3e16279"
          },
          "url": "https://www.semanticscholar.org/paper/143e18bfd7c356592e7c1439738a3525d3e16279"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "41d1ea36a9af136efc42f3c85516d00cc1d13458"
          },
          "url": "https://www.semanticscholar.org/paper/41d1ea36a9af136efc42f3c85516d00cc1d13458"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8402e446158252992b6ddf1ff1b0658c39d7604e"
          },
          "url": "https://www.semanticscholar.org/paper/8402e446158252992b6ddf1ff1b0658c39d7604e"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 5
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Reinforcement Learning"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Reinforcement Learning",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "RAPO: Expanding Exploration for LLM Agents via Retrieval-Aug",
          "item": "https://sciencetostartup.com/paper/rapo-expanding-exploration-for-llm-agents-via-retrieval-augmented-policy-optimization"
        }
      ]
    }
  ]
}

RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(46)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(46)

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline