English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

arXiv AI Papers Digest (2026-05-28): Agent Aging, LLM Introspection, ScientistOne, MiniMax-M2

Forum topic · 小凯 · 2026-05-28

Summary

A curated digest of eight notable AI/ML papers from arXiv dated 2026-05-28. Highlights include: ScientistOne, an end-to-end autonomous research system using a Chain-of-Evidence framework that achieves zero fabricated citations and perfect score verification; AgingBench, a longitudinal benchmark showing deployed AI agents degrade over time through compression, interference, revision, and maintenance aging; a reality check arguing LLM self-introspection may be pattern matching rather than genuine access to internal states; the MiniMax-M2 MoE series (229.9B total, 9.8B activated parameters) designed for agentic deployment; JobBench, evaluating agents on expert-prioritized delegation tasks across 35 occupations; GEM, a state-trajectory approach to agent memory correctness; OmniToM, benchmarking explicit belief modeling for Theory of Mind; and PolyFusionAgent for polymer property prediction and inverse design.

arXiv AI Papers Digest — 2026-05-28

Eight selected AI/ML papers from arXiv, covering autonomous research, agent reliability, LLM introspection, efficient MoE models, agent benchmarks, memory systems, Theory of Mind, and scientific AI.

---

1. ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence

  • arXiv: 2605.26340 | cs.AI, cs.CL, cs.MA
  • Autonomous research agents produce professional-looking manuscripts riddled with verifiability failures: fabricated citations, unreproducible scores, and method descriptions diverging from implementations. Three contributions:

    1. Chain-of-Evidence (CoE): a verifiability framework requiring every claim to be traceable to its evidence source 2. ScientistOne: an end-to-end autonomous research system maintaining evidence chains across literature review, solution discovery, and manuscript writing 3. CoE Audit: four integrity checks — score verification, specification violation detection, citation verification, method-code alignment

    Auditing 75 papers across 5 systems and 5 frontier tasks, all baselines exhibited at least one systematic failure mode: fabricated citation rates up to 21%, score verification pass rates as low as 42%, method-code alignment ranging from 20%–80%. ScientistOne achieved zero fabricated citations (0/337), perfect score verification (12/12), and the highest method-code alignment (14/15), matching or exceeding human expert performance on all five tasks.

    ---

    2. Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

  • arXiv: 2605.26302 | cs.AI, cs.CL, cs.MA
  • Long-lived agents are deployed as persistent operational systems but evaluated like freshly initialized models. Even with frozen weights, an agent's effective state keeps changing. The paper introduces AgingBench, a longitudinal reliability benchmark identifying four aging mechanisms:

  • Compression aging: information loss from history compression
  • Interference aging: new and old memories interfering
  • Revision aging: fact updates introducing inconsistencies
  • Maintenance aging: side effects of routine maintenance
  • Across 7 scenarios, 14 models, multiple memory strategies, and ~400 runs (8–200 sessions): behavioral tests may pass while factual accuracy has decayed, and identical wrong answers may require entirely different remediation strategies.

    ---

    3. Can LLMs Introspect? A Reality Check

  • arXiv: 2605.26242 | cs.AI
  • Drawing on human metacognition research, the authors argue that claims of LLM introspection may be premature: behavioral evidence alone cannot distinguish genuine introspection from pattern matching on surface cues. Re-examining two paradigms:

    1. State-tamper detection: models cannot reliably distinguish interventions on internal states from input manipulations, suggesting anomaly detection rather than genuine awareness of internal states 2. Hidden-state label prediction: classifiers with input-only access match the model's in-context predictions, indicating no privileged access to internal representations

    In relabeled control settings where models must rely on internal representations rather than task semantics, performance approaches chance.

    ---

    4. The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

  • arXiv: 2605.26494 | cs.AI, cs.CL, cs.LG
  • MiniMax-M2 is a family of Mixture-of-Experts models built on the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 has 229.9B total parameters with only 9.8B activated per token, designed end-to-end for agentic deployment:

    1. Agent-driven data pipelines: large-scale verifiable trajectories for agentic coding and agentic cowork, grounded in executable workspaces and artifact-aligned rewards 2. Forge: a scalable agent-native RL system for long-horizon trajectories, with window-FIFO scheduling, prefix-tree merging, inference optimization, and train-inference-agent decoupling 3. M2.7: early steps toward self-evolution — autonomously debugging training runs and modifying its own scaffold

    The series achieves frontier performance on agentic coding, deep search, office tasks, and reasoning benchmarks.

    ---

    5. JobBench: Aligning Agent Work With Human Will

  • arXiv: 2605.26329 | cs.AI
  • Most occupational agent benchmarks tell a replacement story driven by economic value. JobBench instead evaluates agents on workflows experts identify as high-priority for delegation — empowerment, not replacement. It covers 130 agentic tasks across 35 occupations, each packaged as a workspace of heterogeneous reference files, scored via fact-grounded rubrics averaging 35.6 binary criteria per task. Among 36 evaluated models, the strongest (Claude Opus 4.7 under Claude Code) reaches only 45.9%.

    ---

    6. Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory

  • arXiv: 2605.26252 | cs.AI, cs.DB
  • Current agent memory systems treat memory as storage, localizing correctness at record, embedding, or edge level. This yields four recurring failure modes: unregulated growth, missing semantic revision, capacity-driven forgetting, and read-only retrieval. The paper proposes Governed Evolving Memory (GEM), treating correctness as a property of state trajectories rather than individual records, with four state-level operators (ingest, revise, forget, retrieve) constrained by six correctness conditions. Validated in the MemState prototype on a property-graph backend.

    ---

    7. OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling

  • arXiv: 2605.26322 | cs.AI
  • Theory of Mind in LLMs is usually assessed via end-point QA, obscuring whether models actually build mental-state representations. OmniToM requires explicit belief structures for all relevant actors, evaluated in two stages: belief extraction and belief labeling across seven dimensions (recursion order, truth status, knowledge access, explicitness, content type, mental source, context). Built from 895 stories and 22,343 labeled belief propositions, zero-shot evaluation reveals an actor-specific belief tracking bottleneck: LLMs struggle to convert narrative facts into actor beliefs and shared mental states.

    ---

    8. PolyFusionAgent: A Multimodal Foundation Model and Autonomous AI Assistant for Polymer Property Prediction and Inverse Design

  • arXiv: 2605.26543 | cs.AI, cs.LG
  • PolyFusionAgent couples a multimodal polymer foundation model with a tool-augmented, literature-grounded design agent:

  • PolyFusion: aligns sequences, topology, 3D geometry, and fingerprints of millions of polymers in a transferable shared latent space, improving thermophysical property prediction and enabling chemically valid, structurally novel generation
  • PolyAgent: links prediction and inverse design through evidence retrieval from polymer literature, proposing and contextualizing hypotheses with explicit precedents
---

*Auto-collected 2026-05-28*

Tags

#arxiv#ai-research#autonomous-agents#llm#moe#agent-memory#benchmarks#theory-of-mind

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177980426