FlowCompile performs compile-time design space exploration on structured LLM workflows to produce reusable high-quality configuration sets that outperform routing baselines with up to 6.4x speedup.
hub
Proceedings of the 29th symposium on operating systems principles , pages=
29 Pith papers cite this work. Polarity classification is still indexing.
29
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 29roles
background 1polarities
background 1representative citing papers
MM-JudgeBench shows substantial cross-lingual performance variance in 22 LVLM judges, with model size and architecture as poor predictors of multilingual robustness.
ArgBench unifies 33 existing datasets into a standardized benchmark for testing LLMs across 46 argumentation tasks and analyzes the impact of prompting techniques and model factors on performance.
P2R decouples perception from reasoning in VLMs via a two-stage process and PRA-GRPO alternating RL training, reporting gains such as 93.2% on V-Star for the 4B model over its Qwen3-VL backbone.
Base model text evades AI detectors better than instruction-tuned text, and the HIP method strengthens this trade-off across model sizes.
Rule2DRC is a benchmark for LLM agents synthesizing DRC scripts from natural language rules, paired with SplitTester that improves Best-of-N selection via execution-guided discriminative test generation.
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
POPO uses bounded importance sampling on positive rollouts and a siamese policy network to achieve implicit negative gradients and stable optimization, matching or exceeding GRPO on math benchmarks such as 36.67% on AIME 2025.
SATFormer uses a context-dependent gate for selective reuse of early Transformer representations, improving validation loss and zero-shot accuracy especially on retrieval benchmarks.
POSTCONDBENCH is a new multilingual benchmark that evaluates LLM postcondition generation on real code using defect discrimination to assess completeness beyond surface matching.
Compiling repeated SOP nodes into environment-grounded, versioned tools cuts production p50 latency by 42% and end-to-end error rate by up to 53% in a 44-node fulfillment-center alarm-triage agent.
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance with small text-to-voice gaps.
ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
LegalCiteBench reveals that current LLMs achieve under 7% accuracy on closed-book legal citation retrieval and completion tasks, with misleading answer rates above 94% for nearly all tested models.
CodeClinic benchmark demonstrates that LLM-generated Python skill libraries from clinical guidelines enhance consistency and reduce token consumption by up to 40% compared to zero-shot approaches on MIMIC-IV based tasks.
ReFlect is a harness that wraps LLMs to detect and recover from reasoning errors, achieving 7-29 pp gains over direct CoT on long-horizon tasks and improving code patch quality to 82-87%.
DASH-KV accelerates long-context LLM inference to linear complexity via asymmetric KV cache hashing and mixed-precision retention, matching full attention performance on LongBench.
Small LLMs under 2B parameters achieve better economic break-even, energy efficiency, and hardware density than larger models on legacy GPUs for industrial tasks.
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
NeuFS selects active few-shot samples for LLMs by representing samples via neuron activation patterns and applying a dual-criteria strategy of diversity and neuron consensus to identify informative examples.
Orthonormal initialization for LoRA in RLVR achieves the minimal gap to full fine-tuning, stabilizes training, and outperforms standard LoRA and prior variants on mathematical reasoning benchmarks.
RaBitQCache proposes rotated binary quantization with binary-INT4 arithmetic for unbiased attention weight estimation in long-context LLMs, enabling adaptive Top-p retrieval and hardware optimizations.
Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.
By restricting token mixing to rank-1 decayed matrices, the same model trains in parallel but generates recurrently with constant memory, yielding large throughput gains in compute-matched benchmarks.
citing papers explorer
-
FlowCompile: An Optimizing Compiler for Structured LLM Workflows
FlowCompile performs compile-time design space exploration on structured LLM workflows to produce reusable high-quality configuration sets that outperform routing baselines with up to 6.4x speedup.
-
Lost in Translation: Do LVLM Judges Generalize Across Languages?
MM-JudgeBench shows substantial cross-lingual performance variance in 22 LVLM judges, with model size and architecture as poor predictors of multilingual robustness.
-
ArgBench: Benchmarking LLMs on Computational Argumentation Tasks
ArgBench unifies 33 existing datasets into a standardized benchmark for testing LLMs across 46 argumentation tasks and analyzes the impact of prompting techniques and model factors on performance.
-
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
P2R decouples perception from reasoning in VLMs via a two-stage process and PRA-GRPO alternating RL training, reporting gains such as 93.2% on V-Star for the 4B model over its Qwen3-VL backbone.
-
Base Models Look Human To AI Detectors
Base model text evades AI detectors better than instruction-tuned text, and the HIP method strengthens this trade-off across model sizes.
-
Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation
Rule2DRC is a benchmark for LLM agents synthesizing DRC scripts from natural language rules, paired with SplitTester that improves Best-of-N selection via execution-guided discriminative test generation.
-
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
-
Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients
POPO uses bounded importance sampling on positive rollouts and a siamese policy network to achieve implicit negative gradients and stable optimization, matching or exceeding GRPO on math benchmarks such as 36.67% on AIME 2025.
-
Transformers with Selective Access to Early Representations
SATFormer uses a context-dependent gate for selective reuse of early Transformer representations, improving validation loss and zero-shot accuracy especially on retrieval benchmarks.
-
POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference
POSTCONDBENCH is a new multilingual benchmark that evaluates LLM postcondition generation on real code using defect discrimination to assess completeness beyond surface matching.
-
Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems
Compiling repeated SOP nodes into environment-grounded, versioned tools cuts production p50 latency by 42% and end-to-end error rate by up to 53% in a 44-node fulfillment-center alarm-triage agent.
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance with small text-to-voice gaps.
-
Search Your Block Floating Point Scales!
ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
-
LegalCiteBench: Evaluating Citation Reliability in Legal Language Models
LegalCiteBench reveals that current LLMs achieve under 7% accuracy on closed-book legal citation retrieval and completion tasks, with misleading answer rates above 94% for nearly all tested models.
-
CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents
CodeClinic benchmark demonstrates that LLM-generated Python skill libraries from clinical guidelines enhance consistency and reduce token consumption by up to 40% compared to zero-shot approaches on MIMIC-IV based tasks.
-
ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning
ReFlect is a harness that wraps LLMs to detect and recover from reasoning errors, achieving 7-29 pp gains over direct CoT on long-horizon tasks and improving code patch quality to 82-87%.
-
DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
DASH-KV accelerates long-context LLM inference to linear complexity via asymmetric KV cache hashing and mixed-precision retention, matching full attention performance on LongBench.
-
Are Large Language Models Economically Viable for Industry Deployment?
Small LLMs under 2B parameters achieve better economic break-even, energy efficiency, and hardware density than larger models on legacy GPUs for industrial tasks.
-
HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
-
Neuron-Aware Active Few-Shot Learning for LLMs
NeuFS selects active few-shot samples for LLMs by representing samples via neuron activation patterns and applying a dual-criteria strategy of diversity and neuron consensus to identify informative examples.
-
Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR
Orthonormal initialization for LoRA in RLVR achieves the minimal gap to full fine-tuning, stabilizes training, and outperforms standard LoRA and prior variants on mathematical reasoning benchmarks.
-
RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference
RaBitQCache proposes rotated binary quantization with binary-INT4 arithmetic for unbiased attention weight estimation in long-context LLMs, enabling adaptive Top-p retrieval and hardware optimizations.
-
Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.
-
Structured Recurrent Mixers for Massively Parallelized Sequence Generation
By restricting token mixing to rank-1 decayed matrices, the same model trains in parallel but generates recurrently with constant memory, yielding large throughput gains in compute-matched benchmarks.
-
On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length
Longer action horizons bottleneck LLM agent training through instability, but training with reduced horizons stabilizes learning and enables better generalization to longer horizons.
-
PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers
PipeMax integrates pipeline parallelism with offloading to achieve up to 2.51x higher throughput than vLLM for offline LLM inference on commodity 8-GPU servers.
-
When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models
Across 15 LLMs, first-answer accuracy on arithmetic procedural execution falls from 63% at 5 steps to 20% at 95 steps, with under-execution increasing.
-
Reducing Conversational Escalation in Large Language Model Dialogue with Nonviolent Communication Constraints
NVC-constrained prompting reduces conversational escalation and stabilizes interactions with resistant users in dual-agent LLM simulations across multiple models.
-
JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications
Oxygen AIIC is an industrial platform using LLMs and VLMs for scalable item knowledge production and service at JD.com, reporting 94.2% precision and 82.8% recall along with business metric improvements.