Skip to content

Instantly share code, notes, and snippets.

@donbr
Last active November 1, 2025 17:13
Show Gist options
  • Save donbr/5eede2fb3e79d51f90d3095865b42534 to your computer and use it in GitHub Desktop.
Save donbr/5eede2fb3e79d51f90d3095865b42534 to your computer and use it in GitHub Desktop.
agentic-papers-2025.md

2025 agentic papers

  1. Agentic Retrieval-Augmented Generation: A SurveyarXiv, Jan 2025 Why it matters: formalizes “agentic RAG” patterns (reflection, planning, tool use, multi-agent) and maps implementation choices you already teach. Great for framing why orchestration beats “just a better model.” (summarizepaper.com)

  2. Reasoning↔RAG Synergy (Survey): Toward Deeper RAG-Reasoning SystemsarXiv, Jul 2025 Why it matters: unifies “reasoning-enhanced RAG” and “RAG-enhanced reasoning,” then spotlights agentic interleaving (search ↔ think loops). Solid taxonomy + dataset links you can fold into eval curricula. (summarizepaper.com)

  3. LLM-based Agents in Medicine (Survey)ACL Findings 2025 Why it matters: a rigorous vertical survey (healthcare) with evaluation tables, safety constraints, and workflow patterns (routing, oversight, audit). Use it as a model for domain-specific agent governance sections in your posts. (ACL Anthology)

  4. TreeRL / ToTRL & contemporaries (LLM-RL roundups, 2025)multiple arXiv 2025 entries aggregated Why it matters: captures the 2025 turn toward on-policy tree search and cheap post-training (e.g., critique fine-tuning) to elicit reasoning—directly relevant to agent planning quality vs. cost. Use as supportive citations when you discuss “don’t just swap models; improve the loop.” (lxl-sword.github.io)

  5. Multi-Agent Safety & Oversight (2025)assorted 2025 arXiv preprints in agent lists Why it matters: emerging patterns (tiered oversight, debate vulnerabilities, equilibrium-style coordination). Handy for a short “risks & mitigations” sidebar in your posts about multi-agent orchestration. (lxl-sword.github.io)


How these compare (and why they’re relevant)

  • Versus “Fundamentals of Building Autonomous LLM Agents” (architecture pillars): #1 and #2 extend that base into deployable agent loops—where reasoning and retrieval co-evolve, and tools get scheduled intelligently. They’re closer to the problems you coach (planner quality, retrieval hygiene, evals).

  • Evaluation lens you can quote: While not 2025, OSWorld remains the most cited “computer-use” anchor (human ~72% vs SOTA much lower); pair it as context any time you temper claims about autonomy. It’s acceptable to include as a baseline and note it’s 2024. (arXiv)


Drop-in sentences for your article

  • “For a 2025 view on agentic RAG patterns and how reflection/planning/tool-use actually change retrieval quality, see Agentic RAG: A Survey.” (summarizepaper.com)
  • “If you want a single map of reasoning↔retrieval co-design in 2025 (including interleaved agent loops), the July ‘RAG-Reasoning’ survey is the best organizing reference.” (summarizepaper.com)
  • “In regulated domains, the ACL 2025 survey on LLM agents in medicine shows how agent workflows, routing, and audit interact with safety and evaluation.” (ACL Anthology)
  • “Recent 2025 LLM-RL works (TreeRL/ToTRL; critique fine-tuning) show you can improve planning/efficiency without swapping to a bigger model—ideal for agent loops under budget.” (lxl-sword.github.io)

Want me to compile PDFs + BibTeX for these and generate a one-page “What to cite in 2025 for agentic systems” handout?

Key Agentic AI Papers to Cite in 2025

✅ Core Surveys

  • Agentic RAG: A Survey (arXiv 2025)
    eprint: 2501.09136

    • Covers reflective retrieval, tool routing, multi-agent retrieval
  • RAG↔Reasoning Synergy: Toward Deeper RAG-Reasoning Systems (arXiv 2025)
    eprint: 2507.21504

    • Frameworks for interleaving planning + retrieval

✅ Domain Benchmark Survey

  • LLM-based Agents in Medicine (ACL 2025 Findings)
    • Patterns for safety, audit loops, human oversight

✅ Reasoning / RL for Agents

  • Tree-of-Thoughts Reinforcement Learning (arXiv 2025)
    eprint: 2505.12717
    • Policy learning for reasoning strategies

✅ Multi-Agent Governance

  • Multi-Agent Safety & Oversight in Autonomous LLM Systems (2025)
    • Coordination failures, debate risks, tiered oversight

📎 Usage Note

Use these citations when discussing:

  • Agentic retrieval orchestration
  • Interaction of reasoning + search + memory
  • Multi-agent workflows and tool routing
  • Safety, oversight, and evaluation in large agent systems

Perfect for bootcamp slides, RAG notes, LangGraph/MCP demos, and research blog posts.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment