Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they first synthesize a database and scenario, then derive tools and tasks from them. As a result, tool interfaces may not match real ones, tool compositions are not grounded in execution, and tasks rarely span more than one environment. We propose ToolSpace, a tool-centric framework that reverses this order. ToolSpace mines data, state, and retry dependencies from adjacent calls in execution traces of real MCP services and open agent corpora, using deterministic rules rather than LLM judgment, and clusters the resulting weighted tool-composition graph into environments. Databases are synthesized only for state-mutating environments, while query and stateless tools replay recorded returns. ToolSpace then performs state-aware random walks with rollback and decompiles each chain into a natural-language task with assertion-based checks, keeping only samples that replay successfully from the initial state. Applied to AutomationBench and tau3-Bench Banking, the pipeline produces harder Pro versions on which 7 frontier models drop by up to 38.2 points. Across seven long-horizon tool-use benchmarks, ToolSpace raises Qwen3.6-35B-A3B from 23.0 to 41.0 average score (43.2 with RL) and GLM-5.2 from 44.6 to 56.6, on par with Claude Opus 5. Ablations show that execution-witnessed edges clearly outperform LLM-judged ones, and performance keeps improving with data and environment scale.
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-quality delivery on complex productivity tasks and continued monitoring and decision-making over long horizons, a combination that remains an open challenge. We introduce CoworkOS, a general-purpose harness for long-horizon work that separates task strategy from execution management: the model decides actions, delegation, and acceptance, while the runtime maintains state and feedback. Its three-layer architecture enables direct execution or delegation to Subagents, synchronously or asynchronously, under stable responsibilities. Through a shared application layer, humans and agents inspect and revise the same evolving documents, presentations, CAD models, and Blender scenes, so human-in-the-loop participation can enter both through conversation and through direct modification of the work itself. To sustain continuity across agents and sessions, CoworkOS further introduces hierarchical workspaces and persistent semantic memory, so working files, key decisions, and long-running Job logs remain shareable, reusable, and resumable after interruption. Across 12 benchmarks and 6 categories of real-world applications, CoworkOS proves highly competitive with frontier agent applications such as Codex and DeepSeek Harness. As a sustained-work case study, CoworkOS uses GLM-5.3 as its backbone to conduct RSI-driven automated post-training on Qwen3.6-35B-A3B. Over five rounds, the model's average score across eight benchmarks rose from 33.19 to 42.95 (+9.76). Looking ahead, we believe CoworkOS opens a meaningful path toward general cowork-agent intelligence.
Mingxin Li, Enge Song, Yueshang Zuo, Xiaodong Liu, Rong Wen, Qiang Fu, Gianni Antichi, Jian He 等 30 位作者
LLM agents increasingly rely on tool calling to complete tasks. Model Context Protocol (MCP) standardizes tool calling between LLM agents and tool providers. It reduces integration cost and drives rapid growth in tool scale. In production deployments, tool access becomes difficult to scale. On the tool provider side, legacy services are not directly callable through MCP; the rapid protocol development creates ongoing compatibility cost. On the agent side, the number of mounted tools is limited by the LLM context window and inference overhead; mounting a large tool set increases token usage and inference latency and can reduce task success rate. Moreover, for stateful MCP backends with multiple replicas, preserving session affinity increases client-side complexity. We present a cloud-scale MCP Gateway system. It breaks the direct-connect model on the data plane and offloads legacy service integration, consolidating incompatible MCP variants, access control, tool recommendation, and session-aware routing at the gateway. The conversion module supports 315 OpenAPI services in the cloud and integrates MCP transport variants. Session-aware routing decouples the scalability of the gateway layer and the MCP service layer. The hybrid retrieval engine sustains $\sim$98\% Top-15 recall; it scales agent tool access to 3{,}000+ tools with improved tool selection accuracy. We also share the lessons learned from deploying the gateway system in production.
Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration. Multi-solver calibration targets disagreement within a heterogeneous solver pool, whereas contrastive solver calibration targets a designated strong-pass/weak-fail relation; both operationalize a solver-relative learnable zone anchored in demonstrated solvability. Using CalibForge, we construct 5,431 calibrated terminal tasks. Our ablations show that both strategies yield more effective supervision than authoring and validation alone or ordinary single-solver feedback. Models trained on the full collection achieve 31.84% and 47.57% on Terminal-Bench 2.1. The largest improvements over the corresponding base model reach 23.97 percentage points on Terminal-Bench 2.1, 26.54 points on SWE-bench Pro, and 30.04 points on Doc2Repo. Together, these results support solver-relative learnability as a practical target for constructing effective and transferable agent training data.
Zhaoheng Huang Alibaba Group, Yutao Zhu, Ji-Rong Wen Renmin University of China, Zhicheng Dou Renmin University of China
Retrieval-augmented generation (RAG) effectively enhances the accuracy and timeliness of large language models (LLMs) by incorporating external knowledge retrieved from external sources. However, with the increasing prevalence of LLM-generated content, external corpora used by RAG systems may become contaminated with LLM-generated texts. Such contamination compromises the reliability and quality of retrieved results, ultimately leading to a degradation in RAG performance, and raises concerns about the diminishing presence of human texts and the “Spiral of Silence” effect. A natural solution is to incorporate LLM text detectors into the RAG pipeline to filter out LLM-generated texts from the retrieved results. However, their effective use in RAG remains under-explored. In this paper, we explore the usage paradigms of LLM text detectors for RAG and highlight key limitations of off-the-shelf or directly fine-tuned detectors. To this end, we propose a RAG-aware data augmentation strategy that aligns detector training with realistic contamination patterns. Our approach synthesizes training data from both LLM and human texts under diverse generation modes. Experiments show that our method mitigates performance degradation and improves the long-term stability of RAG systems.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zhaoheng Huang Alibaba Group, Dacheng Wen, Yutao Zhu, Xiaoying Lian Microsoft, Yushi Liang Microsoft, Kai Hao Microsoft, Nan Li Microsoft, Liangjie Zhang 等 12 位作者
Large language models (LLMs) in retrieval-augmented generation systems can still produce hallucinations, generating content that is unsupported or contradicted by the source texts and undermines reliability. Recent work addressed this problem by training span-level hallucination detectors using reinforcement learning (RL) and chain-of-thought (CoT) reasoning. In this work, we show through error analysis that incorrect predictions by existing reasoning-based detectors are strongly associated with CoT processes that lack explicit grounding in source evidence, particularly when verification steps do not quote or verify claims against the retrieved documents. This behaviour contrasts with human verification practices in benchmarks such as RAGTruth, where evidence quotation is a prerequisite for determining hallucinated spans. Motivated by this observation, we propose an evidence-grounded RL framework, namely RLSeek, to explicitly enforce active evidence seeking during CoT reasoning by requiring quotation of relevant source segments at each verification step. Experiments on the RAGTruth and NewsSum dataset demonstrate consistent improvements in hallucination span detection performance, with limited additional reasoning overhead and improved robustness in out-of-domain settings.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Jia Deng, Junyi Li, Xin Zhao Renmin University of China, Jinpeng Wang, Hongyu Lu, Ji-Rong Wen Renmin University of China
Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training methods largely rely on random masking strategies that overlook intrinsic token dependencies. In this work, we present an empirical analysis of attention in dLLMs and show that tokens attending more strongly to revealed context exhibit greater generation stability and play a critical role in reasoning. Motivated by these findings, we propose AGDO, an attention-guided denoising and optimization framework that aligns both training and optimization with attention-derived dependencies. AGDO determines the denoising order based on attention structure and emphasizes attention-critical tokens during supervised fine-tuning and reinforcement learning. Experiments on mathematical and coding benchmarks demonstrate that AGDO consistently improves reasoning performance, outperforming state-of-the-art post-training methods for dLLMs.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Fengqi Zhu Renmin University of China, Rongzhen Wang Renmin University of China, Shen Nie, Xiaolu Zhang Ant Group, Chunwei Wu Ant Group, Jun Zhou Ant Group, Yankai Lin Renmin University of China, Ji-Rong Wen Renmin University of China 等 9 位作者
Masked diffusion language models present a promising paradigm for language modeling, yet the systematic theoretical analysis and comprehensive empirical validation of their alignment on general tasks remain relatively underexplored. In this paper, we identify the primary challenge for this problem: the high variance in Evidence Lower Bound (ELBO)-based likelihood estimates required for preference optimization. To address this issue, we propose Variance-Reduced Preference Optimization (VRPO), a framework that formally analyzes the bias and variance of the preference optimization loss and gradient based on Direct Preference Optimization, showing both are governed by a score-estimator variance. Building on this foundation, we introduce multiple unbiased variance reduction strategies, including optimal budget allocation and antithetic sampling, to improve alignment performance. We demonstrate the effectiveness of VRPO by applying it to LLaDA, a large diffusion language model. The resulting model, LLaDA 1.5, consistently outperforms its SFT-only predecessor consistently across various general benchmarks, such as mathematics (GSM8K +4.7), coding (HumanEval +3.0, MBPP +1.8), and alignment (IFEval +4.0, Arena-Hard +4.3). Furthermore, LLaDA 1.5 demonstrates a highly competitive mathematical performance compared to other strong language MDMs and ARMs. Our model is available at https://huggingface.co/GSAI-ML/LLaDA-1.5.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Haoxiang Sun University of California Berkeley, Yingqian Min, Zhipeng Chen, Xin Zhao Renmin University of China, Ji-Rong Wen Renmin University of China
The rapid advancement of large reasoning models has saturated existing math benchmarks, underscoring the urgent need for more challenging evaluation frameworks. To address this, we introduce OlymMATH, a rigorously curated, Olympiad-level math benchmark comprising 350 problems, each with parallel English and Chinese versions. OlymMATH is the first benchmark to unify dual evaluation paradigms within a single suite: (1) natural language evaluation through OlymMATH-EASY and OlymMATH-HARD, comprising 200 computational problems with numerical answers for objective rule-based assessment, and (2) formal verification through OlymMATH-LEAN, offering 150 problems formalized in Lean 4 for rigorous process-level evaluation. All problems are manually sourced from printed publications to minimize data contamination, verified by experts, and span four core domains. Extensive experiments reveal the benchmark’s significant challenge, and our analysis also uncovers consistent performance gaps between languages and identifies cases where models employ heuristic “guessing” rather than rigorous reasoning. To further support community research, we release 582k+ reasoning trajectories, a visualization tool, and expert solutions at https://github.com/RUCAIBox/OlymMATH.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表