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%).
111
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 111representative 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.
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.
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.
SkillSafetyBench is a benchmark of 155 cases across 47 tasks and 6 risk domains showing that non-user attacks via skills, artifacts, or environments can consistently induce unsafe agent behavior.
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.
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.
-
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
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.
-
When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
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: 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.
-
No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs
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: Evaluating Agents on End-to-End Business Spreadsheet Workflows
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: Environment-Free Program Verifier for Coding Agents
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.
-
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.
-
PassNet: Scaling Large Language Models for Graph Compiler Pass Generation
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: A Benchmark for LLM-Based Smart Contract Decompilers
SCDBench introduces a 600-contract dataset and cumulative four-stage evaluation showing frontier LLMs achieve perfect semantic decompilation on only 42 contracts.
-
LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?
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: Have Large Multimodal Models Truly Conquered High School-level Examinations?
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.
-
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.
-
MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systems
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: Anytime Muon with Stable Gradient Evaluation
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: 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.
-
WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games
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 KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
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.
-
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
SkillSafetyBench is a benchmark of 155 cases across 47 tasks and 6 risk domains showing that non-user attacks via skills, artifacts, or environments can consistently induce unsafe agent behavior.
-
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
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: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
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.
-
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.
-
KL for a KL: On-Policy Distillation with Control Variate Baseline
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.
-
MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference
MISA routes to a small subset of indexer heads via block statistics, matching full DSA performance on LongBench with 4-8x fewer heads and 3.82x speedup while recovering over 92% of selected tokens.
-
Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution
TEBench is a new project-level benchmark for test evolution showing coding agents achieve only 45-49% F1 on identifying tests needing changes, with stale tests hardest due to reliance on execution failures.
-
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.
-
When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
A malicious relay can strategically rewrite aligned LLM outputs in BYOK agent architectures to achieve up to 99.1% attack success on benchmarks like AgentDojo and ASB.
-
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.
-
Single-Language Evidence Is Insufficient for Automated Logging: A Multilingual Benchmark and Empirical Study with LLMs
MultiLogBench shows that LLM performance on automated logging varies substantially across programming languages, demonstrating that single-language evidence is insufficient for general claims about model behavior or tool design.
-
BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation
BARD bridges autoregressive and diffusion VLMs with progressive block merging plus stage-wise intra-diffusion distillation, delivering 3x speedup and new SOTA on open dVLMs using under 4.4M data points.
-
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
SkillMOO applies LLM-proposed edits and NSGA-II Pareto optimization to skill bundles for SE agents, ranking top in pass rate on most SkillsBench tasks while cutting costs up to 31.7%.
-
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.
-
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.
-
DWDP: Distributed Weight Data Parallelism for High-Performance LLM Inference on NVL72
DWDP distributes MoE weights across GPUs for independent execution without collective synchronization, improving output TPS/GPU by 8.8 percent on GB200 NVL72 for DeepSeek-R1 under 8K input and 1K output lengths.
-
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
PERMA is a new benchmark using temporally ordered events, text variability, and linguistic alignment to evaluate LLM memory agents on persona consistency beyond simple retrieval.
-
CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
CoLT replaces text-based chain-of-thought in MLLMs with 3-step latent thought chains supervised by a removable external decoder in forward and backward modes, yielding 10.1x faster inference on eight benchmarks.
-
Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index
Introduces RSI metric and RSI-S filtering method for adaptive token selection in RLVR, reporting 2-3 point gains over GRPO on AIME/AMC benchmarks.
-
Cognitive World Models for Process-Level Social Influence Evaluation
CogWM is a new LLM user model for evaluating social influence by predicting and tracking cognitive state evolution in dialogues, trained on 150k samples and shown to differentiate AI agents effectively.
-
Aurora: A Leverage-Aware Spectral Optimizer
Aurora is a leverage-aware spectral optimizer that enforces uniform row norms in matrix updates while preserving Muon's polar geometry, outperforming Muon and achieving SOTA among spectral methods on modded-nanoGPT.
-
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
Agent-as-a-Router turns static LLM routing into an iterative C-A-F loop that accumulates execution feedback to lower cumulative regret on coding tasks.
-
Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches
A survey of RLM use in 28 disciplines reveals uneven adoption and introduces a maturity assessment framework showing larger gaps when limited to public resources.
-
Memory Shot for Long-Term Dialogue
MemShot renders local dialogue spans as structured visual memory units to improve long-term dialogue modeling in LLMs, achieving competitive benchmark performance with 70x faster memory construction.
-
AMix-2: Establishing Protein as a Native Modality in Large Language Models
AMix-2 unifies protein sequences and text in one LLM via shared tokens and block-wise diffusion modeling, introduces the ProteinArena benchmark, and reports competitive performance against task-specific protein models and frontier LLMs.
-
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.
-
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
ADWIN adaptively selects training horizons in on-policy distillation via prefix alignment checks, cutting end-to-end cost by up to 4.1x while matching or exceeding full-rollout accuracy on math and code benchmarks.
-
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.