ModularRSI: Frozen-Weight Agents Improve via Harness Self-Modification
IQuest Research, with Beihang University and the University of Manchester, released ModularRSI, a method for agent continuous self-improvement that modifies the execution harness while keeping the base model frozen. On Terminal-Bench 2.0, accuracy rose from 47.57 to 52.43 through harness evolution, with improvements transferring to unseen tasks, domains, and base models. The work defines an agent as A=(M,H), where H is the harness controlling environment observation, context maintenance, tool invocation, failure recovery, and task termination.
Coverage timeline
机器之心机器之心
近日，IQuest Research 同北京航空航天大学、曼彻斯特大学等合作伙伴发布 ModularRSI，尝试让 Agent 根据自身执行经验，持续修改模型外围的运行机制——Harness。 在基础模型全程冻结的情况下，经过 Harness 演化，系统在 Terminal-Bench 2.0 上的准确率从 47.57 提升至 52.43 。更关键的是，这些改进还能迁移到未参与演化的任务、不同领域乃至不同基础模型。 arXiv：https://arxiv.org/abs/2609.14857 Code: https://github.com/IQuestLab/ModularRSI Blog: https://recursive-self-improvement.notion.site/blog-1-modularrsi-toward-generalizable-harness-rsi 这项工作的核心问题很直接： 当模型本身不再变化，Agent 能否通过改造“模型如何工作”，获得持续的自我改进能力？ 研究团队把一个 Agent 写成：A=(M,H) 其中，(M) 是基础模型，(H) 是 Harness。 对于今天的 Agent 来说，最终表现已经越来越依赖模型外围的系统机制。模型能够看到哪些环境信息，怎样维护上下文，什么时候调用工具，失败后如何恢复，以及什么情况下可以宣布任务完成，都会影响最终结果。 这些机制共同构成了 Harness。 ModularRSI 进一步把变化对象放到了 Harness 上： 模型 (M) 始终冻结，Harness 则随着执行经验不断发生变化。 Agent 每完成一批任务，都会留下执行轨迹；系统从轨迹中寻找反复出现的缺陷，再修改自身运行代码，让下一轮执行建立在上一轮经验之上。 这构成了 Harness Recursive Self-Improvement，也就是 Harness RSI。 视频 1｜Performance of the harness across different evolution generations on Terminal-Bench 2.0 视频 1 展示的正是这一现象：基础模型保持冻结，外围 Harness 随着演化代次推进，Terminal-Bench 2.0 表现持续提高。作者据此提出，Agent 的迭
Related stories
Google open-sources Harness², a recursive self-improvement system for LLMs
Google has open-sourced Harness², a recursive self-improvement (RSI) system that enables LLMs to modify their own code, prompts, tools, and skill libraries during runtime. The system uses a dual-layer recursive architecture—task-level and harnessing-level—to address the lack of ground truth and overfitting in real-world tasks. In tests, equipping GLM-5 with Harness² improved its score on the WorkBuddy-Bench office benchmark by 11.5 points, surpassing native Gemini 3.5 Flash. The project is fully open-sourced and supports OpenCode and Codex.
1 reports · 1 sources
Tsinghua introduces SRHarness and MechBench for agentic symbolic regression and mechanism discovery
Tsinghua University researchers introduced SRHarness, a runtime framework for agentic symbolic regression, and MechBench, a benchmark for mechanism discovery, aiming to improve AI's ability to derive formulas from data and understand underlying physical mechanisms. Experiments show SRHarness achieves 72.97% symbol recovery with DeepSeek-v4-flash-0731, far exceeding Codex's 20.72%, while MechBench reveals that even GPT-5.6-sol-powered Codex recovers mechanisms at only 13.75% on the core set, highlighting a significant gap between pattern discovery and mechanism understanding.
1 reports · 1 sources
Kaiming He's Team Unveils VISTA, a Visual Harness for Multimodal Reasoning
Kaiming He's team released a paper introducing VISTA, a visual-native harness framework that lets multimodal models observe environments, store raw frames, and revisit them during reasoning without retraining. In evaluations, VISTA enabled Claude Opus 5.0 to complete all 25 public ARC-AGI-3 games with a perfect human-relative efficiency score of 100, using 57.4% fewer actions than first-time human baselines; GPT-5.6 Sol also cleared all games with a score of 99.
NTU Study: Agent Harness Quality Depends on Model-Task Combination
A team led by An Bo at Nanyang Technological University published a report systematically studying model-harness interactions across agent tasks. The study compared four configurable harnesses (OpenHands, DSH, PI, openJiuwen) with five models and two native pairings, concluding that harness quality is not a fixed property but depends on the specific model-task combination, recommending joint evaluation over seeking a universal harness.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe