ZeroSlop — October 26, 2026
Today: Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic…; Phronix: The Capability-Centric Learning Paradigm for…; Do AI-for-Science Agents Preserve Model Safety?
12 stories worth knowing about today — AI breakthroughs, launches, and innovations making a difference.
1. Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model
MarkTechPost
Nanbeige LLM Lab released Nanbeige4.3-33B, a 33B dense Apache 2.0 model with 512K context. It reports 80.9 on Terminal-Bench 2.1 and will teach the upcoming Nanbeige4.3-3B. The post Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model appeared first on MarkTechPost ….
2. Phronix: The Capability-Centric Learning Paradigm for Agents
arXiv CS.AI
arXiv:2610.31789v1 Announce Type: new Abstract: Scientific computing increasingly relies on large language model-based agents for performance engineering tasks such as instrumentation, analysis, and workflow porting. However, agent effectiveness depends heavily on the surrounding harness, which typ…
3. Do AI-for-Science Agents Preserve Model Safety?
arXiv CS.AI
arXiv:2610.32045v1 Announce Type: new Abstract: AI-for-Science agents are increasingly being used for formulating scientific hypotheses, running autonomous experiments, and interpreting evidence. These agents are constructed by integrating a large language model (LLM) into a domain-specific agent h…
4. TACS-RF: Tool-driven Agentic Circuit Synthesis of RF and mmWave Modules
arXiv CS.AI
arXiv:2610.31882v1 Announce Type: new Abstract: We present the framework of TACS-RF - a Tool-driven Agentic Circuit Synthesis of RF and mmWave modules. In this framework, a large-language-model (LLM) coding agent (Claude Opus 4.8) directly drives industry-standard electronic-design-automation (EDA)…
5. CEMIR vs. FISER: a comparative study of reasoning-based and enrichment-based approaches to pragmatic intent recognition
arXiv CS.AI
arXiv:2610.32022v1 Announce Type: new Abstract: Intent recognition in human-robot interaction requires agents to resolve ambiguous natural language instructions by inferring the speaker’s underlying goals. Research has increasingly focused on two notable paradigms for addressing this task: structur…
6. DriveMind: Mind-Evolving Belief Tracking for Closed-Loop Autonomous Driving
arXiv CS.AI
arXiv:2610.32069v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) can perceive a traffic scene, reason about it, and propose a driving action within a single model. However, existing MLLM-based drivers reason from scratch at each frame and commit to a single explanatio…
7. Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster
MarkTechPost
Stanford and UC Berkeley researchers released TokenGate, a drop-in learned token pruning module for LLMs. It cuts long-context prefill time-to-first-token by 1.4x to 11.3x and peak memory by 1.5x to 3.4x without accuracy loss. The post Researchers from Stanford and UC Berkeley Introduce TokenGate: T…
8. PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean
arXiv CS.AI
arXiv:2610.31810v1 Announce Type: new Abstract: Even a carefully proofread paper can leave small gaps in its proofs or its stated assumptions. We introduce PaperFormalizer, a Lean-based agentic pipeline that helps authors find and close such gaps in their own papers and turn each paper into a Lean-…
9. Beyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student?
arXiv CS.AI
arXiv:2610.31918v1 Announce Type: new Abstract: Distilling interactive LLM agents requires choosing between teacher-generated demonstrations and student-generated experience, corresponding broadly to off-policy and on-policy distillation. While both have proven effective, we argue that this distinc…
10. $M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process
arXiv CS.AI
arXiv:2610.31937v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) remain vulnerable to carefully orchestrated multi-turn interactions that progressively bypass safety mechanisms. However, many existing red-teaming approaches rely on heuristics or impose strong assumptions that lim…
11. The Helpful Agent Problem: When Emergent Cooperation Among LLM Agents Bypasses Intended Workflows
arXiv CS.AI
arXiv:2610.31985v1 Announce Type: new Abstract: LLM agents are increasingly deployed in collaborative settings where they pursue separate tasks while sharing resources and operating under review or oversight processes. Such settings create safety risks not only when agents are malicious, but also w…
12. PPO vs. SAC: A Comparative Study for Cooperative Motion Control of Dual-Arm Space Robots
arXiv CS.AI
arXiv:2610.32034v1 Announce Type: new Abstract: The growing population of orbital debris has intensified interest in active debris removal and on-orbit servicing, for which dual-arm space manipulators offer improved grasping stability and load distribution relative to single-arm systems. However, c…