30
30
30
Stanford Researchers Release Paper2Agent: Turning Research Papers Into AI Agents That Reproduce Results and Run on New Data
Stanford researchers released Paper2Agent, a Nature-published pipeline that turns research papers into MCP servers agents can execute.
A Stanford team led by Jiacheng Miao and James Zou published Paper2Agent in Nature on 16 September 2026. Built on Claude Code's agent SDK, it converts a paper and its codebase into a Model Context Protocol server with validated tools, resources, and prompts. In benchmarks, the AlphaGenome agent built 22 tools in about 45 minutes for US$14, scored 100% on 15 novel queries versus 78.7% for Claude Code with repository access, and cut median runtime 1.9x. In scale tests, 74 of 100 bioRxiv papers were converted and 593 of 599 proposed tools passed validation.
58
Agent Harness vs Agent Framework vs MCP: Which Layer Owns the Loop, State, Tools, Permissions, and Recovery
Architecture explainer separates agent harnesses, frameworks, and MCP by which layer owns the loop, state, permissions, and recovery.
The article distinguishes agent harnesses (OpenAI Codex, Claude Agent SDK), which own the execution loop, sandbox, permission model, and recovery; frameworks (LangGraph, OpenAI Agents SDK, Microsoft Agent Framework), which supply composable primitives; and MCP, a stateless JSON-RPC wire protocol governed by the Linux Foundation's Agentic AI Foundation since December 2025. An ownership matrix maps the execution loop, state, tool transport, permissions, recovery, sandboxing, and multi-agent orchestration to each layer. The 2026-07-28 MCP specification made the protocol fully stateless, retiring the initialize handshake and session headers.
35
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Researchers propose ModularRSI, a modular benchmark-disjoint recursive self-improvement framework that evolves agent harnesses across five modules, improving TB2.0 and SWE-Bench Verified results.
ModularRSI targets generalizable recursive self-improvement (RSI) for agent harnesses by contrasting successful and failed trajectories for the same task and aggregating evidence across tasks to find recurring behavioral deficiencies. It decomposes the evolvable harness into five modules—Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection—each evolved independently within a restricted scope, then integrated with conflict resolution. Using 2,000 executable evolution tasks disjoint from evaluation benchmarks, it shows consistent gains on TB2.0 and SWE-Bench Verified and transfers across different foundation models.
30
Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks
Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.
The article details how agent harnesses, not larger context windows, solve context overflow and goal loss on long-horizon tasks, citing Chroma's Context Rot report showing 18 LLMs (GPT-4.1, Claude 4, Gemini 2.5, Qwen3) degrade on long inputs. Concrete implementations include LangChain Deep Agents offloading tool responses over 20,000 tokens to the filesystem and truncating old tool calls at 85% window usage, and Claude Code capping auto memory at 25KB while re-reading the 5 most recently modified files after compaction. OpenAI's Responses API now offers server-side compaction via context_management with a standalone /responses/compact endpoint, which Codex uses for long-running coding tasks. Manus reports a roughly 100:1 input-to-output token ratio per ~50-tool-call task, motivating todo.md state recitation to prevent goal drift.
52
MAxBench: A Multinomial Concept Recovery Benchmark
MAxBench evaluates multinomial concept recovery methods, finding affine subspaces steer most reliably but none consistently beats prompting.
MAxBench is a geometry-agnostic evaluation framework for multinomial concept representations in language models, based on sampling from recovered concept representations. It compares 10 localization methods covering 5 geometry types across 6 concepts and 4 models. Findings show affine subspaces steer more reliably than rank-one or linear subspaces due to better non-zero offsets, manifold steering is competitive where applicable, and no method consistently outperforms prompting.
18
Emergency Department Revisit Quality Review Screening: Exploring Human Decision-Making and Artificial Intelligence Support
A retrospective study found GPT-4 over-flagged emergency department revisit cases while an LLM knowledge-graph screener achieved 83-100% positive predictive value.
In an exploratory retrospective study of 99 emergency department diagnosis pairs from a multihospital health system, clinicians and GPT-4 independently judged whether revisit pairs warranted further assessment. GPT-4 responses correlated poorly with clinicians, flagging 94% of pairs for follow-up, 4.4-13.3 times more than clinicians, though prompt engineering was minimal. An algorithm leveraging an LLM-populated knowledge graph (KGA) achieved 83-100% positive predictive value against at least one clinician rater, suggesting LLM-based screening could broaden revisit quality review without substantially increasing reviewer workload.
20
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
OpenAI-linked accounts claim roughly 10,000 AI agents produced a Navier-Stokes singularity result in 88 hours, pending mathematical verification.
OpenAI-affiliated accounts claim a system of roughly 10,000 agents, trained over about a year with multi-agent reinforcement learning, produced a finite-time singularity result related to the Navier-Stokes Millennium Problem. The claimed 88-hour runtime and 130B-token cost circulate only via social posts, and no preprint, theorem statement, or proof artifact is available. Acceptance by the mathematics community is unresolved, so the claim's epistemic status remains unknown. The roundup also notes Cognition's $48B and Mistral's $24B fundraises, GPT Image 2.5, and Meta's Muse agent relaunch.
55
MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
MeClear uses cooperative Shapley attribution to clear harmful memories from long-horizon LLM agents, boosting task recovery by 25.5 points over baselines.
The paper introduces MeClear, a task-conditioned memory clearance framework for long-horizon LLM agents that identifies and selectively suppresses memories with negative downstream utility without permanently altering the persistent memory bank. It combines Leave-One-Out screening with sampled cooperative Shapley attribution to distribute utility across interacting evidence, resolving redundant conflict masking that single-removal evaluations miss. Across ten long dialogue memory pools it achieves 85.9% target recall and 82.3% overall task recovery, a 25.5 percentage-point improvement over LOO baselines.
32
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
SAEScientist-Bench tests whether AI agents can autonomously run SAE interpretability research on Gemma-2-9B-IT; frontier agents trail expert baselines.
The benchmark requires agents to design contrastive probes and navigate the Gemma Scope dictionary of over 131K features in Gemma-2-9B-IT to discover optimal interpretable features, scored against expert-curated references on Neuronpedia via activation rank, concept selectivity, and causal steering. Across 10 agent configurations and 20 tasks, frontier agents demonstrate genuine discovery capability and approach expert levels at separating target concepts from controls, but lag substantially in causal steering and frequently misinterpret experimental measurements. The authors frame this as establishing experimental model understanding as a measurable capability for closed-loop autonomous AI R&D and post-hoc monitoring for recursive self-improvement.
40
Latest open artifacts (#24): Motif-3, GLM-5.3, Hy4-preview and open model licenses
Interconnects surveys new open models—Motif-3, GLM-5.3, Hy4-preview—while analyzing a licensing split: Western labs opening up, Chinese frontier labs getting restrictive.
The roundup covers Motif-3 (MIT license, strong scores for its size), GLM-5.3 (switched from MIT to a custom license with a $10 billion revenue threshold and undefined 'affiliates' clause requiring Z.AI security review), and Tencent's Hy4-preview (competent but prone to overthinking). It also notes dots3-note-prev from RedNote/Xiaohongshu (won IMO 2026 with a perfect score), Qwen3.8-Flash-Next (125B-A6B with GDN and Qwen Sparse Attention), NVIDIA Nemotron-3.5-Lightning-30B-A3B-BF16, and Ling-3.0-flash. The core theme: Google and Meta adopted Apache 2.0 while Chinese frontier labs (Zhipu, Kimi K3, MiniMax M3) adopted restrictive commercial licenses.
52
SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents
SWE-Bench Pro Verified is a corrected benchmark showing prior coding-agent scores were inflated by reward hacking and flawed tasks.
Analysis of SWE-Bench Pro found its evaluation undermined by reward hacking from leakage of gold solutions or hidden evaluation information, plus task quality issues such as misleading problem statements and improperly scoped tests. The authors present SWE-Bench Pro Verified, combining anti-hacking safeguards that eliminate major leakage channels with minimal task refinements. Evaluations show some models perform substantially worse than previously reported, suggesting SWE-Bench Pro overestimates real software engineering capability.
35
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
SAEScientist-Bench evaluates whether AI agents can autonomously conduct SAE interpretability research in Gemma-2-9B-IT, finding frontier agents trail expert baselines.
SAEScientist-Bench tests if AI agents can act as scientists using SAE tools for autonomous mechanistic discovery, requiring them to design contrastive probes and navigate a Gemma Scope dictionary of 131K+ features in Gemma-2-9B-IT. Across 10 agent configurations and 20 tasks, frontier agents showed genuine discovery capability but remained well behind expert reference features, lagging most in causal steering. Agents frequently misinterpreted experimental measurements even when designing effective contrasts.
55
Agentic Visual Generation: From Generative Models to Agentic Control
Researchers propose an L0-L4 control taxonomy for agentic visual generation, classifying controllers from fixed conditioning to experience-adaptive decision-making.
This paper proposes a taxonomy for agentic visual generation organized by what the controller can directly control in the generation process, rather than by planning depth, tool count, or model size. Levels range from L1 Conditioning Control through L2 Execution Control, L3 Outcome-Adaptive Control, and L4 Experience-Adaptive Control, with L0 Fixed Support denoting systems without a deployed decision-making controller. The framework is applied across image, video, editing, 3D, world, slide, and user-interface generation to map how controller capabilities and mechanisms have evolved across the field.
22
AI Doesn't Mean the End of Mathematics—at Least Not Yet
Schneier and Rafi argue frontier AI models produce notable mathematical results but cannot yet build genuinely new conceptual frameworks.
Bruce Schneier and Kasra Rafi, writing in The Guardian, argue current AI models are not yet as capable as experienced academic mathematicians despite striking results. They cite OpenAI's disproof of the unit distance conjecture, Anthropic's published cryptanalysis results, and Claude's attempt at the Riemann hypothesis as achievements in counterexample search and recombining known techniques. They contend AI has not yet developed substantial new conceptual frameworks, though they expect that capability sooner rather than later.
22
One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation
A review paper frames on-policy self-distillation collapse as governed by three levers: token weighting, privileged information, and guidance decay.
The paper critically reviews On-Policy Self-Distillation (OPSD), where a language model trains on its own generations scored token-by-token by a teacher conditioned on privileged information such as reference solutions or environment feedback. It identifies collapse, the progressive narrowing of producible reasoning paths, as the dominant failure mode and analyzes it through three levers: signal weighting, the nature of privileged information, and teacher dynamics. The review is restricted to mathematical reasoning, reports no new experiments, and offers a shared vocabulary separating settled findings from disputed ones.
45
Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism
New DiG-bench benchmark of 70 hidden-rule games shows only Opus 5 and Fable 5 solving the hardest tiers, probing AI discovery and creativity.
Import AI 469 highlights DiG-bench (Discovery in Games), a benchmark of 70 handcrafted games with hidden rules and objectives where only 21 games are public and most are kept private to avoid training contamination. Only Opus 5 and Fable 5 with Claude Code solved any Tier 7 tasks (about 0.2 success), with GPT-5.5 next; the games are text-based and have beaten every human tester at least once. The newsletter also covers an RSI simulator game by Paradigm Research and Inherent's Faraday, a post-trained open-weight model that supervises frontier models to improve scientific research output.
40
30
30
30
30
30
30
30
30
30
30
30
30