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.
hub Canonical reference
Swe-agent: Agent-computer interfaces enable automated software engineering.Advances in Neural Information Processing Systems, 37:50528–50652
Canonical reference. 88% of citing Pith papers cite this work as background.
23
Pith papers citing it
Background
88% of classified citations
hub tools
citation-role summary
background 7
method 1
citation-polarity summary
representative citing papers
AgentKernelArena is a new open benchmark that measures complete AI agent workflows on 196 GPU kernel tasks with correctness, performance, and generalization checks to unseen configurations.
Presents CUActSpot benchmark and renderer-LLM data synthesis that lets a 4B model outperform larger open-source models on complex computer interactions.
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
ClawMark is a new benchmark for multi-turn multi-day multimodal coworker agents in stateful evolving services, with deterministic Python checkers showing frontier models achieve only 20% strict task success.
SkVM uses capability profiling and compiler-style techniques to make skills portable across LLMs and harnesses, raising task completion rates while cutting token use by up to 40% and delivering up to 3.2x speedup.
KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.
SynAE is a multi-metric framework that evaluates how well synthetic benchmarks replicate real data characteristics for multi-turn tool-calling agent testing.
Priority ranking offers a low-cost direct evaluation for harness optimizers that correlates with their real multi-step optimization performance, supported by the Shor dataset of 182 scenarios.
RMA, a multi-agent system with structured memory and iterative feedback loops, solves 8 out of 10 research-level math problems on the new First Proof benchmark and outperforms GPT-5.2R and Aletheia according to expert evaluation.
DAgger-style training with turn-level policy interpolation raises 4B and 8B LLM agents to 27.3% and 29.8% on SWE-bench Verified, beating several larger published systems.
Learns state-conditioned commitment depth in a 7B vision-language policy that jointly predicts actions and replan intervals, outperforming fixed-depth baselines and larger models on Sliding Puzzle and Sokoban while providing a theoretical dominance result.
SOD reweights on-policy distillation strength step-by-step using divergence to stabilize tool use in small language model agents, yielding up to 20.86% gains and 26.13% on AIME 2025 for a 0.6B model.
Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.
LLM safety judges flip verdicts on equivalent policy rewrites up to 9.1% of the time and cannot distinguish meaningful from meaningless changes, requiring new invariance-based reliability metrics.
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.
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.
Smart Paste applies deep learning to predict and suggest post-paste code edits in Google's IDE, achieving 45% acceptance and contributing over 1% of all code written company-wide after deployment.
Argues that trustworthiness in Agent-to-Agent networks requires a new conceptual framework with four design pillars baked in from the beginning, as retrofitting existing single-agent methods is insufficient.
The paper organizes repository-level retrieval-augmented code generation into a unified framework covering retrieval substrate, control regime, and evaluation setting while summarizing strategies, datasets, and challenges.
citing papers explorer
-
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
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.
-
AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents
AgentKernelArena is a new open benchmark that measures complete AI agent workflows on 196 GPU kernel tasks with correctness, performance, and generalization checks to unseen configurations.
-
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
Presents CUActSpot benchmark and renderer-LLM data synthesis that lets a 4B model outperform larger open-source models on complex computer interactions.
-
Inference-Time Budget Control for LLM Search Agents
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
-
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
ClawMark is a new benchmark for multi-turn multi-day multimodal coworker agents in stateful evolving services, with deterministic Python checkers showing frontier models achieve only 20% strict task success.
-
SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
SkVM uses capability profiling and compiler-style techniques to make skills portable across LLMs and harnesses, raising task completion rates while cutting token use by up to 40% and delivering up to 3.2x speedup.
-
Efficient Remote KV Cache Reuse with GPU-native Video Codec
KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.
-
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.
-
Towards Direct Evaluation of Harness Optimizers via Priority Ranking
Priority ranking offers a low-cost direct evaluation for harness optimizers that correlates with their real multi-step optimization performance, supported by the Shor dataset of 182 scenarios.
-
RMA: an Agentic System for Research-Level Mathematical Problems
RMA, a multi-agent system with structured memory and iterative feedback loops, solves 8 out of 10 research-level math problems on the new First Proof benchmark and outperforms GPT-5.2R and Aletheia according to expert evaluation.
-
Revisiting DAgger in the Era of LLM-Agents
DAgger-style training with turn-level policy interpolation raises 4B and 8B LLM agents to 27.3% and 29.8% on SWE-bench Verified, beating several larger published systems.
-
When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
Learns state-conditioned commitment depth in a 7B vision-language policy that jointly predicts actions and replan intervals, outperforming fixed-depth baselines and larger models on Sliding Puzzle and Sokoban while providing a theoretical dominance result.
-
SOD: Step-wise On-policy Distillation for Small Language Model Agents
SOD reweights on-policy distillation strength step-by-step using divergence to stabilize tool use in small language model agents, yielding up to 20.86% gains and 26.13% on AIME 2025 for a 0.6B model.
-
Why Does Agentic Safety Fail to Generalize Across Tasks?
Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.
-
Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges
LLM safety judges flip verdicts on equivalent policy rewrites up to 9.1% of the time and cannot distinguish meaningful from meaningless changes, requiring new invariance-based reliability metrics.
-
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.
-
Smart Paste: Automatically Fixing Copy/Paste for Google Developers
Smart Paste applies deep learning to predict and suggest post-paste code edits in Google's IDE, achieving 45% acceptance and contributing over 1% of all code written company-wide after deployment.
-
Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
Argues that trustworthiness in Agent-to-Agent networks requires a new conceptual framework with four design pillars baked in from the beginning, as retrofitting existing single-agent methods is insufficient.
-
Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches
The paper organizes repository-level retrieval-augmented code generation into a unified framework covering retrieval substrate, control regime, and evaluation setting while summarizing strategies, datasets, and challenges.
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- CogniFold: Always-On Proactive Memory via Cognitive Folding
- AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery