Open library
The essential reading of generative AI and agents, open in a clean reading view, with Meow and Standard summaries when available. No account needed to read.
563 papers · 561 with a Meow summary · 333 posts
The selected papers and blogs: the essential papers of generative AI and agents, and the key lab publications and essays, each with Meow and Standard summaries.
Qwen Pilot Team, Alibaba Group
We present **Future-KL Influenced Policy Optimization (FIPO)**, a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on outcome-based rewards (ORM) that distribute a global advantage uniformly across ev…
Tianzhu Ye Li Dong
The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose **Online Experiential Learning** (OEL), a framework that enables language models…
Bingxiang He, Yuxin Zuo, Zeyuan Liu et al.
Unsupervised reinforcement learning with verifiable rewards (URLVR) offers a pathway to scale LLM training beyond the supervision bottleneck by deriving rewards without ground truth labels. Recent works leverage model intrinsic signals, showing promising early gains, yet their potential and limitations remain unclear.…
Chen Yueh-Han NYU, MATS Robert McCarthy UCL, MATS Bruce W. Lee UPenn, MATS He He NYU
Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what they verbalize in their CoT, it could undermine CoT monitorability. To measure this undesirable capability — CoT controllability — we introd…
Wenkai Yang, Weijie Liu, Ruobing Xie et al.
On-policy distillation (OPD), which aligns the student with the teacher’s logit distribution on student-generated trajectories, has demonstrated strong empirical gains in improving student performance and often outperforms off-policy distillation and reinforcement learning (RL) paradigms. In this work, we first theore…
Penghui Qi, Xiangxin Zhou, Zichen Liu et al.
Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio clipping mechanism in PPO is structurally ill-suited for the large vocabularies inher…
Jonas Hübotter Frederike Lübeck Lejs Behric Anton Baumann, Marco Bagatella Daniel Marta Ido Hakimi Idan Shenfeld, Thomas Kleine Buening Carlos Guestrin Andreas Krause
Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from a scalar outcome reward per attempt, creating a severe credit-assignment bottleneck. Many verifiabl…
Yanqi Dai, Yuxiang Ji, Xiao Zhang et al.
Reinforcement Learning with Verifiable Rewards (RLVR) offers a robust mechanism for enhancing mathematical reasoning in large models. However, we identify a systematic lack of emphasis on more challenging questions in existing methods from both algorithmic and data perspectives, despite their importance for refining u…
Fengkai Yang, Zherui Chen, Xiaohan Wang et al.
Reinforcement Learning from Verifier Rewards (RLVR) has emerged as a widely used approach for post-training large language models on reasoning tasks, with group-based methods such as GRPO and its variants gaining broad adoption. These methods rely on group-relative advantage estimation to avoid learned critics, yet it…
Sunzhu Li, Jiale Zhao, Miteto Wei et al.
Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation remains challenging due to the lack of ground truth. While rubric-based evaluation offers a structured proxy for verification, existing method…
Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Daxin Jiang, Xiangyu Zhang, Heung-Yeung Shum
We introduce Parallel Coordinated Reasoning (PaCoRe), a training-and-inference framework designed to overcome a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window. PaCoRe departs from the traditional sequenti…
Shih-Yang Liu¹, Xin Dong, Ximing Lu et al.
As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety of scenarios. To achieve this, Reinforcement learning (RL) pipelines have begun incorporating multiple rewards, each capturing a distinct p…
Muxi Diao, Lele Yang, Wuxuan Gong, Yutong Zhang,
Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities. We investigate this discrepancy and identify a fundamental distributional gap:…
Yubo Li, Yidi Miao, Ramayya Krishnan et al.
LLM-as-a-judge scales evaluation, but reasoning judges are slow and costly. We study **JEV-as-a-Judge**: evaluation with JEV, a decision-only judge that returns label probabilities instead of text, and whose confidence decides whether to accept its verdict or escalate to a reasoning judge. Against sixteen generative a…
Peng Xia, Rujun Han, Zifeng Wang et al.
An LLM agent’s capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent harness, practically…
LimiX Team
We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM). CMNs shifts the organizing principle of…
Tong Zheng, Xidong Wu, Zheng Zhang et al.
Recursive self-improvement is becoming essential for autonomous AI agents, whose progress depends on discovering high-value solutions across complex domains. Effective exploration drives this process, yet managing and improving exploration strategies remains a major bottleneck. Current systems face a fundamental dilem…
Recent work extends Recursive Self-Improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve their execution mechanisms from experience. However, achieving **generalizable harness RSI** faces two challenges: evolution on downstream benchmarks makes transferable improve…
NeoHorse Team https://hf.co/collections/TokenRhythm/neohorse-1 https://github.com/TokenRhythm/NeoHorse
Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its own capabilities and converts that evidence into the next round of learning. We argue that a deployed routing harness already contains such a mechanism: beyond task outputs, agentic interaction leaves execution traje…
As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly termed the agent harness. Changing this harness while holding model weights fixed can substantially alter task performance. Current agent evaluations typically report do…
Ziyu Ma, Hailang Huang, Shun Zou et al.
Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interdependent steps. However, existing agent harnesses maintain task execution, task state, and completion assessment within a growing context, making the state difficult to…
Yifan Zhang, Yutong Dai, Juntao Tan et al.
Horizon Research, Frontis.AI, Tsinghua University
Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a concrete, executable testbed for studying this capability. We introduce **OpenMLE**, an open full-stack system for RSI research in MLE, spanning verifiable task enviro…
Ruhan Wang, Yucheng Shi, Zongxia Li et al.
The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, execution environments, and application requirements change, the harness must be continually modified to add capabili…
Jiaru Zou, Rui Pan, Ruizhong Qiu et al.
Project Page: [https://recursivemas.github.io](https://recursivemas.github.io) Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend such scaling principle from a single model to multi-agent s…
Guanyu Jiang, Zhaochen Su, Xiaoye Qu et al.
Multimodal agents can now tackle complex reasoning tasks with diverse tools, yet they still suffer from inefficient tool use and inflexible orchestration in open-ended settings. A central challenge is enabling such agents to continually improve without parameter updates by learning from past trajectories. We identify…
Orca Team, Beijing Academy of Artificial Intelligence
We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-…
Han Luo, Bingbing Wen, Lucy Lu Wang
LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete user goals. Yet not every goal is well specified or achievable in the available environment. In such cases, a reliable agent should recognize that further interaction is unlikely to help and abstain fr…
Jiajie Jin, Yuyang Hu, Kai Qiu et al.
Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the resulting lessons into later attempts. We study how an AI agent can run this loop autonomously over long horizons. We introduce Arbor, a general…
Jiaqi Liu, Shi Qiu, Mairui Li et al.
Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across cycles. Existing autonomous research systems often model this process as a linea…
Kangning Zhang, Shuai Shao, Qingyao Li et al.
Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable code, or learned routines. For visual agents, however, procedural knowledge is inherently multimodal: reuse depends not only on what operatio…
Siru Ouyang, Jun Yan, Yanfei Chen et al.
LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills distilled from experience provide a natural substrate for self-evolution, where high-quality skill curation serves as the key bottleneck. Existi…
Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress, top-tier multimodal search agents remain difficult to reproduce, largely due to the absence of open high…
Ruofeng Yang, Yongcan Li, Shuai Li
This report describes Aris(**A**utonomous **R**esearch via Adversarial Multi-Agent Collaboration), an open-source research harness for autonomous ML research, including its architecture, assurance mechanisms, and early deployment experience.The performance of agent systems built on large language models depends on bot…
Shuzheng Si, Haozhe Zhao, Yu Lei et al.
Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation: extracting the corresponding rules…
Ziyu Ma, Shidong Yang, Yuxiang Ji et al.
Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experi…
Chenxi Wang, Zhuoyun Yu, Xin Xie et al.
Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited experience, resulting in redundant exploration and poor generalization. To address this…
Ao Qu, Han Zheng, Zijian ZhouYihao Yan et al.
Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded exploration rules, which limit the autonomy of LLM agents. We present **CORAL**, the f…
Jingwei Ni, Yihao Liu, Xinpeng Liu et al.
Large Language Model (LLM) agents increasingly rely on domain-specific skills, yet manually authoring such skills does not scale, and skills generated purely from parametric knowledge often miss critical operational pitfalls. We introduce Trace2Skill, a framework that consolidates broad execution trajectories in paral…
Peng Xia, Jianwen Chen, Xinyu Yang et al.
Large language model (LLM) agents have rapidly emerged as powerful assistants for complex, multi-step tasks, yet agents deployed in the wild remain largely static, trained once and served unchanged regardless of how user needs evolve. This creates a fundamental tension: they must serve users continuously without inter…