Skip to content

Agentic AI / LLM Agents — 2025

🗓️ 2025 in Review

🕒 Timeline

  • 2022-10: ReAct establishes the interleaved reason–act–observe loop that becomes the default agent template (referenced throughout, e.g. MoRAgent, INFORM-CT).
  • 2023: AutoGPT / Reflexion / RLHF popularize autonomous loops, verbal self-reflection, and preference-based alignment as the agent baseline.
  • 2024: Scaffolding frameworks (MetaGPT, AutoGen, CrewAI) and tool benchmarks (ToolBench, 16k+ APIs) standardize hand-designed multi-agent pipelines.
  • 2025-H1: Verifiable-reward RL (GRPO/PPO) shifts agent training from SFT toward RL post-training (foundation for AgentMath, AutoTool, The Conductor, ClinTutor-R1).
  • 2025-12
    • Learned orchestration replaces fixed topologies — The Conductor and rSIM train small planners to design coordination/strategy on the fly.
    • Teacher-free / self-play agent training matures — Self-Play SWE-RL and GTR-Turbo remove dependence on human labels and external teacher APIs.
    • Memory becomes a first-class, closed-loop module — ReMe, EchoTrail-GUI, and VideoARM add distillation, retrieval, and pruning.
    • Realistic vertical benchmarks expose large gaps — Finch (38%), LocalSearchBench (36%), TravelBench (~75), SoMe (<70) show real work remains unsolved.
    • Agent safety/control/governance consolidates — Factor(U,T), TRAP, the ARC framework, BAID, and the akrasia/scheming line emerge.
    • First hard real-world deployments — AMS-IO-Agent reaches a 28nm silicon tape-out; MASFIN runs an 8-week live trading evaluation.

📈 Trend

Where the field stands

Agentic AI in 2025 has moved decisively from hand-scaffolded prompting pipelines toward learned agency: systems where orchestration, tool selection, memory, and self-correction are trained objectives rather than fixed templates. The digests in this window cluster around four pressures — making agents trainable end-to-end (agentic RL), giving them persistent and adaptive memory, deploying them in messy real-world verticals (finance, EDA, clinical, local services), and governing their failure modes (prompt injection, scheming, PII leakage, sycophancy). A recurring empirical signal is that structure beats scale: small models wired into the right multi-agent or tool-augmented harness repeatedly match or beat frontier models (HPO's 8B beating GPT-4o, OPT-350M beating ChatGPT on ToolBench, rSIM's 0.5B matching 14B, The Conductor's 7B surpassing GPT-5). Simultaneously, a wave of realistic benchmarks (Finch, LocalSearchBench, TravelBench, SoMe, SpatialBench, ARC-AGI-3) shows that despite this progress, frontier agents still fail the majority of authentic long-horizon, tool-using tasks.

➡️ Read the full trend analysis

📄 Papers (400)

➡️ Paper list — 400 papers, grouped by month. · ⭐ 13 key papers (see Key papers in the left nav).