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.
super hub Mixed citations
GLM-5: from Vibe Coding to Agentic Engineering
Mixed citation behavior. Most common role is background (68%).
105
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 105representative citing papers
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.
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.
MetaSyn benchmark shows LLM agents recover at most 52.7% of relevant studies in meta-analysis pipelines due to failures in PI/ECO-based screening despite strong retrieval.
DirectorBench is a profile-aware diagnostic benchmark that localizes bottlenecks in long-form video generation workflows using structured checkpoints and multi-agent evaluation.
PassNet provides a dataset of 18K graphs and PassBench for LLM-generated compiler passes, with fine-tuned models achieving 2.67x gains on long-tail tasks where TorchInductor underperforms.
SCDBench introduces a 600-contract dataset and cumulative four-stage evaluation showing frontier LLMs achieve perfect semantic decompilation on only 42 contracts.
LiveBrowseComp shows search agents rely on intrinsic knowledge on standard benchmarks, with scores dropping 25-40 points and closed-book accuracy below 2% on questions about facts from the prior 90 days.
LiveK12Bench is a growing multi-disciplinary benchmark showing LMMs like GPT-5 drop from 79 to 53 under realistic exam constraints including process rigor and efficiency.
LLM-Wiki structures external knowledge as compilable wiki pages with links and persistent self-correction, achieving SOTA results on HotpotQA, MuSiQue, and 2WikiMultiHopQA by 2.0-8.1 F1 points over prior RAG systems.
AuthTrace is a diagnostic benchmark that annotates fan-in gradients in single-author corpora to measure evidence recall, precision, and answer correctness across eight systems in retrieval, memory, graph, and structured-evidence paradigms.
MemMark enables snapshot-only attribution for agent long-term memory by embedding signals via keyed distribution-preserving sampling at memory-write decisions, recovering 40-bit payloads with near-baseline utility.
AMUSE is a new optimizer integrating Muon orthogonalization with Schedule-Free averaging via adaptive interpolation for schedule-free anytime training that improves Pareto frontiers on vision and LLM tasks.
Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
WebGameBench is a new benchmark that evaluates coding agents on building browser-native games from frozen specifications, with runtime browser evaluation showing best agents reach 76.9% usable rate but only 20.2% excellent rate.
Decoupling prefix source from token-level KL direction in autoregressive sequence KL yields four objectives unifying SFT, DAgger, offline RL and OPD, with KL mixing and entropy-gated curriculum improving math reasoning accuracy and shortening responses.
AssayBench is a new gene-ranking benchmark for phenotypic CRISPR screens that shows zero-shot generalist LLMs outperform both biology-specific LLMs and trainable baselines on adjusted nDCG.
StereoTales shows that all tested LLMs emit harmful stereotypes in open-ended stories, with associations adapting to prompt language and targeting locally salient groups rather than transferring uniformly across languages.
ProofRank benchmark shows substantial differences in LLM proof quality not captured by correctness, with trade-offs between quality metrics and accuracy.
OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.
vOPD stabilizes on-policy distillation gradients by subtracting a closed-form per-token negative reverse KL baseline as a detached control variate, preserving unbiasedness while lowering variance and matching expensive full-vocabulary methods.
citing papers explorer
-
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
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.
-
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.
-
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation
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.
-
Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio
MetaSyn benchmark shows LLM agents recover at most 52.7% of relevant studies in meta-analysis pipelines due to failures in PI/ECO-based screening despite strong retrieval.
-
DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation
DirectorBench is a profile-aware diagnostic benchmark that localizes bottlenecks in long-form video generation workflows using structured checkpoints and multi-agent evaluation.
-
Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki
LLM-Wiki structures external knowledge as compilable wiki pages with links and persistent self-correction, achieving SOTA results on HotpotQA, MuSiQue, and 2WikiMultiHopQA by 2.0-8.1 F1 points over prior RAG systems.
-
AuthTrace: Diagnosing Evidence Construction in Thematically Dense Single-Author Corpora
AuthTrace is a diagnostic benchmark that annotates fan-in gradients in single-author corpora to measure evidence recall, precision, and answer correctness across eight systems in retrieval, memory, graph, and structured-evidence paradigms.
-
Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
-
Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
ProofRank benchmark shows substantial differences in LLM proof quality not captured by correctness, with trade-offs between quality metrics and accuracy.
-
Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.
-
MolViBench: Evaluating LLMs on Molecular Vibe Coding
MolViBench is the first benchmark designed to evaluate LLMs on generating executable programs for molecular tasks in drug discovery.
-
MathDuels: Evaluating LLMs as Problem Posers and Solvers
Self-play between LLMs for problem authoring and solving, scored via Rasch modeling, shows that authoring and solving skills are partially decoupled and that the benchmark difficulty evolves with new models.
-
ClawBench: Can AI Agents Complete Everyday Online Tasks?
ClawBench is a benchmark of 153 live-web tasks where AI agents achieve low success rates, e.g. 33.3% for Claude Sonnet 4.6.
-
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
LiteCoder-Terminal-Gen creates synthetic terminal datasets that, after SFT and DMPO on Qwen models, yield 29.06%, 18.54%, and 34.00% pass@1 on Terminal Bench 1.0, 2.0, and Pro.
-
Pruning and Distilling Mixture-of-Experts into Dense Language Models
A systematic MoE-to-dense conversion via expert scoring, grouping, and distillation yields +6.3 pp average accuracy over dense-to-dense pruning at matched parameter count on tested models.
-
OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations
OnePred maintains a recursively updated intent memory and uses two-stage RL to predict next queries, cutting token use by up to 22x while outperforming baselines on a new NQP-Bench dataset.
-
OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents
OpenSkillEval dynamically builds task instances across five application domains to evaluate 30 open skills with over 600 tests, finding that skill use depends heavily on model and framework and that many popular skills do not beat base agents.
-
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
CHI-Bench shows current AI agents achieve at most 28% success on long-horizon healthcare workflows that require dense policy adherence, multi-role handoffs, and multi-turn interactions.
-
Argus: Evidence Assembly for Scalable Deep Research Agents
Argus coordinates a Navigator and multiple Searchers via an evidence graph for deep research, reporting average gains of 5.5 points with one Searcher and 12.7 points with eight parallel Searchers across eight benchmarks, reaching 86.2 on BrowseComp with 64 Searchers.
-
Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation
Local teachability collapse occurs in later trajectory segments during strong-to-weak OPD; a margin-based release rule using top-K teacher advantage and BIC change-point detection on sentence segments outperforms full-trajectory supervision on five in-domain benchmarks and preserves out-of-domain pe
-
Evaluation Awareness in Language Models Has Limited Effect on Behaviour
Verbalised evaluation awareness in large reasoning models has only small effects on their outputs across safety and alignment tests.
-
Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding
EVICT adaptively truncates draft trees in MoE speculative decoding by combining drafter signals with profiled costs to retain only cost-effective prefixes, delivering up to 2.35x speedup over autoregressive decoding.
-
MAIC-UI: Making Interactive Courseware with Generative UI
MAIC-UI provides a zero-code authoring system for generating and iteratively editing interactive courseware from educational materials via structured analysis and incremental generation, with lab and classroom evaluations showing usability gains and learning improvements.
-
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
A 35B MoE agent model trained on 45K-token trajectories via three-stage SFT and domain-routed distillation achieves leading or competitive scores against 1T models on SEAL-0, IFBench, HiPhO, FrontierScience-Olympiad and MolBench-Bind.
-
Parametric Skills
ParametricSkills uses a hypernetwork to turn textual skills into LoRA adapters, outperforming in-context learning by 6.44 points on average across six SWE subtasks with higher BERT Score and F1.
-
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
Yuvion LLM applies adversarially aware training and introduces the YLRE benchmark set, claiming superior safety robustness over larger models on multiple tasks.
-
Agentic Insight Generation in VSM Simulations
A two-step agentic system for extracting insights from VSM simulations achieves up to 86% accuracy with top LLMs by using progressive data discovery and slim context.
-
Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
LLM post-training is unified as off-policy or on-policy interventions that expand support for useful behaviors, reshape policies within reachable states, or consolidate behavior across training stages.
- Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?
- Toward Autonomous Long-Horizon Engineering for ML Research