Heimdall automates translation of eBPF C programs to Rust with formal equivalence proofs for 94.1% of 102 tested programs using LLMs, static analysis, and Z3-based checking.
super hub Canonical reference
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
Canonical reference. 82% of citing Pith papers cite this work as background.
288
Pith papers citing it
Background
82% of classified citations
abstract
Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We find real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models. To this end, we introduce SWE-bench, an evaluation framework consisting of $2,294$ software engineering problems drawn from real GitHub issues and corresponding pull requests across $12$ popular Python repositories. Given a codebase along with a description of an issue to be resolved, a language model is tasked with editing the codebase to address the issue. Resolving issues in SWE-bench frequently requires understanding and coordinating changes across multiple functions, classes, and even files simultaneously, calling for models to interact with execution environments, process extremely long contexts and perform complex reasoning that goes far beyond traditional code generation tasks. Our evaluations show that both state-of-the-art proprietary models and our fine-tuned model SWE-Llama can resolve only the simplest issues. The best-performing model, Claude 2, is able to solve a mere $1.96$% of the issues. Advances on SWE-bench represent steps towards LMs that are more practical, intelligent, and autonomous.
hub tools
citation-role summary
background 56
dataset 10
baseline 3
method 3
citation-polarity summary
claims ledger
- abstract Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We find real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models. To this end, we introduce SWE-bench, an evaluation framework consisting of $2,294$ software engineering problems drawn from real GitHub issues and corresponding pull requests across $12$ popular Python repositories. Given a codebase along with a description of an issue to be resolved, a
authors
co-cited works
representative citing papers
ExploitBench decomposes LLM exploitation into 16 oracle-verified capability flags and finds public frontier models trigger crashes but rarely reach arbitrary code execution on 41 V8 bugs.
EnergyAgentBench is a new benchmark with 70 task variants that evaluates LLM agents on live energy data for datacenter siting, long-horizon optimization, and causal grid diagnosis.
Agent-BRACE improves LLM agent performance on long-horizon partially observable tasks by 5.3-14.5% through a decoupled belief state of verbalized atomic claims with certainty labels that keeps context length constant.
A new native-runtime benchmark reveals that current frontier AI agents succeed on at most 62 percent of realistic long-horizon CLI tasks.
PDEAgent-Bench is the first multi-metric, multi-library benchmark for AI-generated PDE solvers, evaluating executability, numerical accuracy, and efficiency across DOLFINx, Firedrake, and deal.II.
SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
VibeServe demonstrates that AI agents can synthesize bespoke LLM serving systems end-to-end, remaining competitive with vLLM in standard settings while outperforming it in six non-standard scenarios involving unusual models, workloads, or hardware.
StabilizerBench is a new benchmark for evaluating AI agents on generating, optimizing, and making fault-tolerant stabilizer circuits for quantum error correction, with efficient verification and multi-tier scoring.
neuralCAD-Edit benchmark shows even the best foundation model (GPT 5.2) scores 53% lower than human CAD experts in acceptance trials for multimodal-instructed 3D model edits.
HWE-Bench is the first repository-level benchmark for LLM agents on real hardware bug repair, where the best agent fixes 70.7% of 417 tasks but drops below 65% on complex SoC projects.
SlopCodeBench shows coding agents degrade in structural quality and verbosity across iterative extensions, with no agent solving any problem completely and agent code 2x more eroded than human code.
MCP-Atlas is a new benchmark with 1000 tasks on production MCP servers that uses claim-level scoring to evaluate LLM agents on realistic multi-step tool-use competency.
ExCyTIn-Bench is the first benchmark of 7542 questions from Microsoft Sentinel threat investigation graphs, where the best LLM agent achieves a reward of 0.606.
The AI Scientist framework enables LLMs to independently conduct the full scientific process from idea generation to paper writing and review, demonstrated across three ML subfields with papers costing under $15 each.
OSWorld provides the first unified real-computer benchmark for open-ended multimodal agent tasks, exposing large performance gaps between humans and state-of-the-art LLM/VLM agents.
LLMs brew code answers in early layers before resolving into Resolved, Overprocessed, Misresolved, or Unresolved states, with 41.5% resolved overall and brewing duration stable at 24-42% across 16 models.
Visual graphs of repository structure added to text inputs for multimodal LLM agents reduce token consumption by up to 26% while maintaining or improving issue-resolution accuracy.
A new six-dimension process taxonomy for AI software development frameworks shows convergence on artifact persistence and human oversight but reveals that no framework covers all dimensions strongly, indicating a depth-portability trade-off.
Sakura is a multi-agent system that generates structurally complex tests from NL descriptions, achieving 50-78% higher compilability and 38-66% higher coverage overlap than baselines on 1,464 scenarios from 20 Apache Commons applications.
AgentCARD benchmark shows heterogeneous LLM agent teams with mixed deployments reach the cost-accuracy frontier, delivering up to 44% higher accuracy or 12x lower cost than uniform teams, with domain-specific role bottlenecks.
EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
VirtualME is a new infrastructure that continuously extracts and interprets in-IDE developer behaviors to build personalized personas, delivering 33.8% better performance on repository-level knowledge Q&A than generic baselines.
OR-Space is a benchmark for LLM agents performing full-lifecycle optimization tasks across Build, Revise, and Explain modes in executable multi-artifact workspaces.
citing papers explorer
-
Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
Agent-BRACE improves LLM agent performance on long-horizon partially observable tasks by 5.3-14.5% through a decoupled belief state of verbalized atomic claims with certainty labels that keeps context length constant.
-
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.
-
Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench
ConsumerSimBench evaluates 13 LLMs on reconstructing crowd reactions from 1,553 Chinese social-media topics using 23,122 auditable yes-no criteria, finding maximum coverage of 47.8% by Gemini-3.1-Pro.
-
Learning Agentic Policy from Action Guidance
ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
-
TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems
TacoMAS performs test-time co-evolution of agent capabilities and communication topology in LLM multi-agent systems via fast capability updates and slow meta-LLM topology edits, delivering 13.3% average gains over strong baselines on four benchmarks.
-
LLM Agents Already Know When to Call Tools -- Even Without Reasoning
LLM agents encode tool necessity in pre-generation hidden states with high linear decodability (AUROC 0.89-0.96); Probe&Prefill uses this to reduce tool calls 48% with 1.7% accuracy loss.
-
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.
-
CodeComp: Structural KV Cache Compression for Agentic Coding
CodeComp uses Joern-extracted Code Property Graph priors for training-free structural KV cache compression, outperforming attention-only baselines on bug localization and code generation while matching full-context patch quality.
-
FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks
FrontierFinance benchmark shows human financial experts outperform state-of-the-art LLMs by achieving higher scores and more client-ready outputs on realistic long-horizon tasks.
-
Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy
LLMs display clear performance stratification on formal language tasks aligned with Chomsky hierarchy complexity levels, limited by severe efficiency barriers rather than absolute capability.
-
Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
MemoryAgentBench is a new multi-turn benchmark assessing four memory competencies in LLM agents—accurate retrieval, test-time learning, long-range understanding, and selective forgetting—showing that existing methods fall short.
-
MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
MLE-bench evaluates frontier language models as ML engineering agents on 75 Kaggle competitions, with the top setup (o1-preview + AIDE) reaching bronze medal level in 16.9% of tasks.
-
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.
-
Draft-OPD: On-Policy Distillation for Speculative Draft Models
Draft-OPD applies on-policy distillation via target-assisted generation and error replay to train speculative draft models, yielding over 5x lossless acceleration and gains over EAGLE-3 and DFlash.
-
SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations
SynAE is a multi-metric framework that evaluates how well synthetic benchmarks replicate real data characteristics for multi-turn tool-calling agent testing.
-
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.
-
FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
FocuSFT uses an inner optimization loop to adapt fast-weight parameters into a parametric memory that sharpens attention on relevant content, then conditions outer-loop supervised fine-tuning on this representation, yielding gains on long-context benchmarks.
-
AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
-
WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning
WebGen-R1 uses end-to-end RL with scaffold-driven generation and cascaded rewards for structure, function, and aesthetics to transform a 7B model into a generator of deployable multi-page websites that rivals much larger models.
-
AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation
AdaExplore improves correctness and speed of Triton kernel generation by converting recurring failures into a memory of rules and organizing search as a tree that mixes local refinements with larger regenerations, yielding 3.12x and 1.72x speedups on KernelBench Level-2 and Level-3 within 100 steps.
-
LLMs Corrupt Your Documents When You Delegate
LLMs corrupt an average of 25% of document content during long delegated editing workflows across 52 domains, even frontier models, and agentic tools do not mitigate the issue.
-
Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation
Localizing judge prompts to five languages shows that LLM backbones interact with language in agent-as-a-judge evaluations, inverting rankings and revealing no universal best model with low inter-judge agreement.
-
EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
EchoKV compresses LLM KV caches by reconstructing missing components from partial data via inter- and intra-layer attention similarities, outperforming prior methods on LongBench and RULER while supporting on-demand full-cache inference.
-
Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI
Defines agentic trustworthiness via five properties and proposes HAAF, a scenario-distribution framework with a Trustworthy Optimization Factory that transfers interventions across 13 models from seven families on a 100-scenario suite.
-
CodeScout: Contextual Problem Statement Enhancement for Software Agents
CodeScout converts underspecified coding requests into comprehensive problem statements via codebase pre-exploration, yielding a 20 percent gain in resolution rates on SWEBench-Verified.
-
EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
EcoGym is a new open benchmark with three economic environments that reveals no leading LLM dominates at sustained plan-and-execute decision making across scenarios.
-
MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
MTraining scales LLM training to 512K-token contexts on 32 A100 GPUs by integrating dynamic sparse training patterns with balanced and hierarchical sparse ring attention, achieving up to 6x throughput gains without accuracy loss on long-context benchmarks.
-
MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
MOSAIC is a training-free multi-agent LLM framework with rationale, coding, reflection, and debugging agents plus a consolidated context window that outperforms prior methods on scientific coding benchmarks.
-
CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics
CFDLLMBench is a new benchmark suite with CFDQuery, CFDCodeBench, and FoamBench to evaluate LLMs on graduate-level CFD knowledge, numerical reasoning, and context-dependent code implementation.
-
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
DeepResearch Bench supplies 100 expert-crafted PhD-level tasks and two human-aligned evaluation frameworks to measure deep research agents on report quality and citation accuracy.
-
I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications
A Paper-to-Interactive-System Agent and I-WebGenBench benchmark with 19 papers enable converting scientific PDFs into executable interactive web systems, with PaperVoyager framework shown to improve quality.
-
Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs
Mix-Quant quantizes prefilling to NVFP4 and keeps BF16 for decoding in agentic LLMs, achieving up to 3x prefilling speedup while largely preserving task performance on long-context and agentic benchmarks.
-
Code as Agent Harness
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
-
Kimi K2.5: Visual Agentic Intelligence
Kimi K2.5 combines joint text-vision training with an Agent Swarm parallel orchestration framework to reach claimed state-of-the-art results on coding, vision, reasoning, and agent tasks while cutting latency up to 4.5 times.
-
Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework
Matrix provides a peer-to-peer multi-agent system for synthetic data generation that scales to tens of thousands of workflows and delivers 2-15x higher throughput than centralized designs without quality loss.
-
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
GLM-4.5, a 355B-parameter MoE model with hybrid reasoning, scores 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified while ranking 3rd overall and 2nd on agentic benchmarks.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
-
On The Landscape of Spoken Language Models: A Comprehensive Survey
A literature survey that organizes spoken language models by architecture, training, and evaluation choices and identifies key challenges and future directions.
-
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
- Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning