MetaSyn benchmark shows LLM pipelines recover at most 52.7% of ground-truth included studies due to screening failures on PI/ECO eligibility, despite 90.9% retrieval recall at K=200.
super hub Mixed citations
GLM-5: from Vibe Coding to Agentic Engineering
Mixed citation behavior. Most common role is background (68%).
139
Pith papers citing it
Background
68% of classified citations
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.
hub tools
citation-role summary
background 22
baseline 6
dataset 2
method 2
other 2
citation-polarity summary
claims ledger
- 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 fur
authors
co-cited works
years
2026 139representative citing papers
AutoLab benchmark shows frontier models mostly fail at sustained iterative optimization due to premature termination, with persistence as the key success factor.
CiteVQA requires models to cite specific document regions with bounding boxes alongside answers and finds that even the strongest MLLMs frequently cite the wrong region, with top SAA scores of only 76.0 for closed models and 22.5 for open-source ones.
A new native-runtime benchmark reveals that current frontier AI agents succeed on at most 62 percent of realistic long-horizon CLI tasks.
Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
SignSGD provably beats SGD by a factor of d under sparse noise via matched ℓ1-norm upper and lower bounds, with an equivalent result for Muon on matrices, and this predicts faster GPT-2 pretraining.
OccuBench is a new benchmark for AI agents on real-world occupational tasks via LLM-driven simulators, showing no model dominates all industries, implicit faults are hardest, and larger models with more reasoning perform better.
SmoothAgent introduces lookahead context engineering to eliminate transformation overhead in LLM agents, reducing TTFT by up to 11.9x through proactive KV cache preparation.
Introduces VidPair-Halluc benchmark of 1K background-controlled adversarial video pairs and 11K QA pairs generated via PairFlow pipeline to evaluate hallucination in LVMs.
SpreadsheetBench 2 provides 321 expert-validated tasks from authentic business data showing frontier LLMs reach only 34.89% overall accuracy on end-to-end spreadsheet workflows.
Dockerless uses agentic repository exploration to verify patches without execution, enabling SFT and RL training of coding agents that reach 62.0/50.0/35.2% resolve rates on SWE-bench Verified/Multilingual/Pro while matching environment-based results.
Self-Harness lets LLM agents autonomously refine their interaction harnesses through weakness mining, proposal generation, and validation, raising held-out pass rates on Terminal-Bench-2.0 from 40.5% to 61.9%, 23.8% to 38.1%, and 42.9% to 57.1% across three models.
SkeMex distills agent trajectories into value-aware skills organized in general/task/action branches and evolves them via a closed-loop Read-Write-Assess-Govern process, outperforming prior memory agents on clinical tasks.
OPRD performs distillation in hidden-state space on on-policy data for deterministic gradients and better math benchmark performance, plus OPRD-Bridge for cross-architecture transfer via low-rank projectors.
DistIL applies distributional DAgger with forward cross-entropy to achieve monotonic policy improvement and better Pass@N from rich feedback in RL for reasoning tasks.
Introduces KINA benchmark with 899 items over 261 disciplines, formal (1-1/e) coverage guarantee and bonus-on-bar tournament theorem, plus evaluations of 42 models with top score 53.17%.
D^2SD uses two diffusion drafters in a prefix tree structure with confidence scores to select and recover alternative draft sequences, achieving higher acceptance rates in speculative decoding.
Muon momentum matrices show layer-dependent power-law scaling of stabilized singular value quantiles with model size from 77M to 2.8B parameters.
EntSQL is a new benchmark with 1,066 examples across five domains where top systems reach only 15.9% accuracy on English inputs when long-form enterprise documents are provided.
Moment-Video benchmark shows top video MLLM achieves only 39.6% accuracy on momentary visual event tasks, with most open-source models below 25%.
AutoMedBench evaluates AI agents on long-horizon medical workflows across five stages and finds validation and submission as dominant failure points based on thousands of runs.
CRAB-Bench and RUSE create a new evaluation framework for LLM agents on constraint-graph tasks with realistic human-like user behaviors, reporting 61% pass@1 for the best model and up to 57% further drops under RUSE.
Introduces LongJudgeBench benchmark showing LLM judges remain unstable for long-form output evaluation even with rubrics or references.
On a real multi-node H100 cluster the authors show that for MLA, routing the ~1 KB compressed query row is cheaper than moving cache chunks and supply a topology-aware cost model accurate to ~7% on IBGDA fabrics.
citing papers explorer
-
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
A new native-runtime benchmark reveals that current frontier AI agents succeed on at most 62 percent of realistic long-horizon CLI tasks.
-
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
AgentHazard benchmark shows computer-use agents remain highly vulnerable, with attack success rates reaching 73.63% on models like Qwen3-Coder powering Claude Code.
-
Affordance Agent Harness: Verification-Gated Skill Orchestration
Affordance Agent Harness is a verification-gated orchestration system that unifies skills via an evidence store, episodic memory priors, an adaptive router, and a self-consistency verifier to improve accuracy-cost tradeoffs in open-world affordance grounding.
-
Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
Claw-Eval is a new trajectory-aware benchmark for LLM agents that records execution traces, audit logs, and environment snapshots to evaluate completion, safety, and robustness across 300 tasks, revealing that opaque grading misses 44% of safety issues.
-
InCoder-32B-Thinking: Industrial Code World Model for Thinking
InCoder-32B-Thinking uses error-feedback synthesized thinking traces and a code world model to reach top open-source scores on general and industrial code benchmarks including 81.3% on LiveCodeBench and 84.0% on CAD-Coder.
-
Learning CLI Agents with Structured Action Credit under Selective Observation
CLI agents trained with RL benefit from selective observation via σ-Reveal and structured credit assignment via A³ that leverages AST action sub-chains and trajectory margins.