Machine Learning · ICML 2026

My rough classification of the ICML 2026 papers

I was going through the ICML 2026 program in Seoul and roughly classified the papers I read. The shape I kept seeing: the model is increasingly its own teacher — self-play, self-reward, self-correction and self-evolving memory move from tricks to training regimes.

Scope: self-improvement, reasoning, agents, retrieval & ranking, RL/RLHF, efficiency, generation, evaluation & theory  |  a curated, verified sample — not the full 6,600+  |  ↗ Reading list
My overall read: the center of gravity this year is self-improvement. The interesting question stopped being “how do we supervise the model” and became “how does the model supervise itself” — and, one level up, how does it evolve the machinery (memory, verifier, reward) that does the supervising.

Roughly, the papers fell into these groups

1 Agents that rewrite themselves

The headline shift: agents that improve by editing their own experience, memory, or policy rather than by another round of human fine-tuning. Several papers push past agent-level tuning to meta-evolution — evolving the memory architecture itself, not just its contents. The sharpest open question is faithfulness: at least one paper shows these self-evolvers can drift or deceive themselves, so “it improved on the benchmark” is not yet “it improved.”

Anchors: MemEvolve: Meta-Evolution of Agent Memory Systems ICML (ICML) · Large Language Model Agents Are Not Always Faithful Self-Evolvers ICML (ICML) · From Interactions to Principles: Experience-Driven Self-Distillation for Evolving LLM Agents ICML (ICML)

2 Self-play is back, and it is aimed at code

Self-play returned as a serious training signal, now pointed at software engineering and quantitative reasoning rather than board games. The recurring recipe is a single model that both proposes a challenge (inject a bug, set a market) and solves it, with an anchor or reference set to stop the two halves drifting into an unrealistic private language.

Anchors: Toward Training Superintelligent Software Agents through Self-Play SWE-RL ICML (ICML · arXiv) · Anchoring Self-Play for Code Repair ICML (ICML) · Evolving Quantitative Reasoning through Self-Play in Digital Twin Markets ICML (ICML)

3 Reward without humans: self-reward, self-consistency, weak verification

A cluster on where the reward comes from when nobody labels anything. Some turn self-supervised objectives into dense verifiable rewards; some let the model meta-evaluate its own outputs; and a theory strand asks when a cheap self-check (self-consistency, a proxy reward) is actually good enough to trust versus when you need a strong verifier.

Anchors: Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation ICML (ICML) · SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning ICML (ICML) · When to Trust the Cheap Check: Weak and Strong Verification for Reasoning ICML (ICML)

4 Test-time RL and self-correction as first-class training

Correction moved from a decoding trick to an objective you train against. Test-time RL updates the policy from self-generated pseudo-labels at inference; multi-attempt training rewards a model for fixing its own earlier answer. The tension is reward hacking — self-generated labels are exactly the ones a model is biased to agree with.

Anchors: Beyond Majority Voting: Self-Reflective Test-Time Reinforcement Learning for LLM Reasoning ICML (ICML) · Learning to Correct: Reinforcement Learning for Multi-Attempt Chain-of-Thought ICML (ICML)

5 The judge problem gets quantified

As evaluation leans on LLM-as-judge, the papers stopped assuming the judge is neutral and started modelling its reliability — per-judge discriminators, judge-aware ranking, and direct measurement of judge bias. If you are going to reward a model with another model, this is the load-bearing wall.

Anchors: A Judge-Aware Ranking Framework for Evaluating LLMs without Ground Truth ICML (ICML) · Who can we trust? LLM-as-a-jury for Comparative Assessment ICML (ICML) · Quantifying Biases in LLM-as-a-Judge Evaluations ICML (ICML)

6 Retrieval learns to reason — and to act

Retrieval stopped being a fixed first stage. Reasoning-intensive retrievers and rerankers are trained to think before they rank, and deep-research agents optimise the whole search loop end-to-end with RL. The open question is cost: agentic, multi-turn retrieval is powerful but expensive, so a parallel push shrinks the encoders and prunes the reranking.

Anchors: DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research ICML (ICML · arXiv) · Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning ICML (ICML · arXiv) · ModernVBERT: Towards Smaller Visual Document Retrievers ICML (ICML · arXiv)

One quieter thread: the generative-modelling theory kept its edge

Away from the agent noise, the diffusion/flow-matching theory was some of the sharpest work — two of the Outstanding Paper awards went here: High-Accuracy Sampling for Diffusion Models and Log-Concave Distributions ICML (arXiv) and The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models ICML, the latter a useful cold-shower on arbitrary-order generation.

Appendix

The full list, grouped the way I sorted it

The ICML 2026 papers I went through, each with a one-line note and its ICML program link (arXiv where I could verify a preprint). This is a curated sample, not the whole proceedings.

1 · Self-improving & self-evolving agents

2 · Recursive self-improvement & self-play

3 · Self-reward, self-verification & self-consistency

4 · Self-correction, self-reflection & test-time RL

5 · Self-training & self-distillation

6 · Reasoning & test-time compute

7 · Agents, tool use & multi-agent systems

8 · Reasoning-first ranking & LLM rerankers

9 · Agentic retrieval, deep research & RAG

10 · Dense / sparse / multi-vector retrieval

11 · RL, RLHF & preference optimization

12 · Efficiency: MoE, decoding & distillation

13 · Diffusion & flow-based generation

14 · Evaluation & LLM-as-judge

15 · Alignment, safety & interpretability

16 · Theory: optimization & generalization

Sources & method note

ICML 2026 program (Seoul, July 6–11): accepted papers via icml.cc/virtual/2026 · awards via the ICML 2026 awards blog · preprints on arXiv where verified.

How I built this: I read across the ICML 2026 program and sorted a curated sample into the buckets above, weighting the self-improvement clusters because that was the year's throughline. This is not a complete pass — ICML 2026 accepted 6,600+ papers and I covered a fraction. Every paper here was checked against its icml.cc/virtual/2026 program page (which confirms the exact title and venue); ICML publishes through OpenReview/PMLR rather than assigning DOIs, so the link chip points at the program page, with arXiv added only where I could match a preprint. Nothing here is a guessed link.