{"work":{"id":"ad29b1a2-bf77-46b3-9ead-fb62b1d2c6fe","openalex_id":null,"doi":null,"arxiv_id":"2602.15763","raw_key":null,"title":"GLM-5: from Vibe Coding to Agentic Engineering","authors":null,"authors_text":"GLM-5-Team: Aohan Zeng, Xin Lv, Zhenyu Hou, Zhengxiao Du, Qinkai Zheng, Bin Chen","year":2026,"venue":"cs.LG","abstract":"We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.","external_url":"https://arxiv.org/abs/2602.15763","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T05:45:23.229059+00:00","pith_arxiv_id":"2602.15763","created_at":"2026-05-09T06:05:35.492490+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"GLM-5: from Vibe Coding to Agentic Engineering","render_title":"GLM-5: from Vibe Coding to Agentic Engineering"},"hub":{"state":{"work_id":"ad29b1a2-bf77-46b3-9ead-fb62b1d2c6fe","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":79,"external_cited_by_count":null,"distinct_field_count":12,"first_pith_cited_at":"2026-03-24T14:04:11+00:00","last_pith_cited_at":"2026-05-22T14:16:21+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-06T05:20:17.450339+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":22},{"context_role":"baseline","n":6},{"context_role":"dataset","n":2},{"context_role":"method","n":2},{"context_role":"other","n":2}],"polarity_counts":[{"context_polarity":"background","n":23},{"context_polarity":"baseline","n":6},{"context_polarity":"unclear","n":2},{"context_polarity":"use_method","n":2},{"context_polarity":"use_dataset","n":1}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T13:00:47.515905+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":27},{"title":"Kimi K2.5: Visual Agentic Intelligence","work_id":"d690be8f-5d53-49b0-b1e7-79668eb8fcdb","shared_citers":26},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":17},{"title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","work_id":"07c85cc5-4086-4abc-823b-6d0f4ff784d0","shared_citers":16},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":11},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":11},{"title":"Kimi K2: Open Agentic Intelligence","work_id":"7f18284c-12d3-4137-bea1-1da97e8cf3c1","shared_citers":10},{"title":"MiMo-V2-Flash Technical Report","work_id":"1f3df90c-4bc3-49b1-ad9b-7f3b34e4ffba","shared_citers":9},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":9},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":8},{"title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","work_id":"64019d00-0b11-4bbd-b173-b46c8fad0157","shared_citers":7},{"title":"Group Sequence Policy Optimization","work_id":"3a98b53b-9f52-4d95-adf7-89353c0a9a65","shared_citers":7},{"title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","work_id":"0624be05-1d97-4fd6-8300-b04b8a3ab04b","shared_citers":6},{"title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","work_id":"6a8d8dc4-0cc0-4052-8109-abbcdcd4a962","shared_citers":5},{"title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","work_id":"96afb8b9-0e7e-442c-93b1-6638599fc041","shared_citers":5},{"title":"arXiv preprint arXiv:2603.11137 , year=","work_id":"5e961f0b-b20e-4580-965d-15fb63ec8965","shared_citers":5},{"title":"Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents","work_id":"57acc3ec-f4c3-49ab-bd0f-5aab91002df9","shared_citers":5},{"title":"Entropy-aware on-policy distillation of language models","work_id":"7dccbe12-e2aa-48d8-9b76-5521ccf02668","shared_citers":5},{"title":"gpt-oss-120b & gpt-oss-20b Model Card","work_id":"178c1f7e-4f19-4392-a45d-45a6dfa88ead","shared_citers":5},{"title":"https://thinkingmachines.ai/blog/ on-policy-distillation/","work_id":"bb76b11f-d59b-421e-88c6-fa0920ed09c3","shared_citers":5},{"title":"MiniLLM: On-Policy Distillation of Large Language Models","work_id":"16edb291-dd18-41c5-8486-c6c715ec5311","shared_citers":5},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":5},{"title":"Reinforcement Learning via Self-Distillation","work_id":"b193541d-5853-4ea4-8e4b-8e4c08617eb6","shared_citers":5},{"title":"Self-Distilled RLVR","work_id":"935a34f3-b83d-4214-b6a0-ae2395b3d107","shared_citers":5}],"time_series":[{"n":56,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T13:00:47.576109+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T13:00:55.331739+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"GLM-5: from Vibe Coding to Agentic Engineering","claims":[{"claim_text":"We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that fur","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks GLM-5: from Vibe Coding to Agentic Engineering because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T13:00:47.527325+00:00"}},"summary":{"title":"GLM-5: from Vibe Coding to Agentic Engineering","claims":[{"claim_text":"We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that fur","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks GLM-5: from Vibe Coding to Agentic Engineering because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":27},{"title":"Kimi K2.5: Visual Agentic Intelligence","work_id":"d690be8f-5d53-49b0-b1e7-79668eb8fcdb","shared_citers":26},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":17},{"title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","work_id":"07c85cc5-4086-4abc-823b-6d0f4ff784d0","shared_citers":16},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":11},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":11},{"title":"Kimi K2: Open Agentic Intelligence","work_id":"7f18284c-12d3-4137-bea1-1da97e8cf3c1","shared_citers":10},{"title":"MiMo-V2-Flash Technical Report","work_id":"1f3df90c-4bc3-49b1-ad9b-7f3b34e4ffba","shared_citers":9},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":9},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":8},{"title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","work_id":"64019d00-0b11-4bbd-b173-b46c8fad0157","shared_citers":7},{"title":"Group Sequence Policy Optimization","work_id":"3a98b53b-9f52-4d95-adf7-89353c0a9a65","shared_citers":7},{"title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","work_id":"0624be05-1d97-4fd6-8300-b04b8a3ab04b","shared_citers":6},{"title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","work_id":"6a8d8dc4-0cc0-4052-8109-abbcdcd4a962","shared_citers":5},{"title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","work_id":"96afb8b9-0e7e-442c-93b1-6638599fc041","shared_citers":5},{"title":"arXiv preprint arXiv:2603.11137 , year=","work_id":"5e961f0b-b20e-4580-965d-15fb63ec8965","shared_citers":5},{"title":"Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents","work_id":"57acc3ec-f4c3-49ab-bd0f-5aab91002df9","shared_citers":5},{"title":"Entropy-aware on-policy distillation of language models","work_id":"7dccbe12-e2aa-48d8-9b76-5521ccf02668","shared_citers":5},{"title":"gpt-oss-120b & gpt-oss-20b Model Card","work_id":"178c1f7e-4f19-4392-a45d-45a6dfa88ead","shared_citers":5},{"title":"https://thinkingmachines.ai/blog/ on-policy-distillation/","work_id":"bb76b11f-d59b-421e-88c6-fa0920ed09c3","shared_citers":5},{"title":"MiniLLM: On-Policy Distillation of Large Language Models","work_id":"16edb291-dd18-41c5-8486-c6c715ec5311","shared_citers":5},{"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","shared_citers":5},{"title":"Reinforcement Learning via Self-Distillation","work_id":"b193541d-5853-4ea4-8e4b-8e4c08617eb6","shared_citers":5},{"title":"Self-Distilled RLVR","work_id":"935a34f3-b83d-4214-b6a0-ae2395b3d107","shared_citers":5}],"time_series":[{"n":56,"year":2026}],"dependency_candidates":[]},"authors":[]}}