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.
super hub Canonical reference
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Canonical reference. 80% of citing Pith papers cite this work as background.
129
Pith papers citing it
Background
80% of classified citations
abstract
Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software engineering, we posit that LM agents represent a new category of end users with their own needs and abilities, and would benefit from specially-built interfaces to the software they use. We investigate how interface design affects the performance of language model agents. As a result of this exploration, we introduce SWE-agent: a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively, far exceeding the previous state-of-the-art achieved with non-interactive LMs. Finally, we provide insight on how the design of the ACI can impact agents' behavior and performance.
hub tools
citation-role summary
background 22
method 2
baseline 1
citation-polarity summary
claims ledger
- abstract Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software engineering, we posit that LM agents represent a new category of end users with their own needs and abilities, and would benefit from specially-built interfaces to the software they use. We investigate how interface design affects the performance of language model agents. As a result of this exploration, we introduce SWE-agent: a system that facilitat
authors
co-cited works
representative citing papers
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.
FermiLink is a unified AI agent framework that automates multidomain scientific simulations via separated package knowledge bases and a four-layer progressive disclosure mechanism, reproducing 56% of target figures in benchmarks and generating research-grade results on unpublished problems.
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.
AOI adds keyframe capture, volume-gated audio transcription, and visual narration to computer-use agents, producing +17 to +48 pp gains over screenshot baselines on DynaCU-Bench with no retraining.
Glite ARF introduces a verifier-driven three-role framework for parallel LLM coding agents, demonstrated by first- and second-place finishes in the BEA 2026 vocabulary-difficulty shared task across three languages with 29.9-35.9% RMSE reduction at ~$450 API cost.
RigorBench evaluates AI coding agents on process discipline via five pillars and reports 41% higher process scores and 17% better outcome correctness with structured approaches on 30 tasks.
Claw-SWE-Bench is a 350-instance multilingual benchmark for OpenClaw-style agent harnesses that shows adapter design raises Pass@1 from 19.1% to 73.4% on the same model while releasing data for reproducible comparison.
DeLM decentralizes LLM multi-agent coordination with shared verified context, delivering up to 10.5pp gains on SWE-bench Verified and 5.7pp on LongBench-v2 while cutting cost per task by ~50%.
Self-Harness lets LLM agents autonomously refine their interaction harnesses through weakness mining, proposal generation, and validation, raising held-out pass rates on Terminal-Bench-2.0 from 40.5% to 61.9%, 23.8% to 38.1%, and 42.9% to 57.1% across three models.
ADK Arena evaluates 51 Python ADKs by having an LLM learn each framework's API, write and repair agent code, and run on benchmarks, finding 57% success rate, 5.6x cost variation, no dominant framework, and substitutable information sources.
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.
DeployBench is a new benchmark of 51 research-artifact deployment tasks where four LLMs with OpenHands achieve 7.8-51% pass rates, with failures mostly from agents stopping after weaker self-checks than the paper requires.
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.
ContextEcho benchmark shows persona drift occurs across 23 frontier models in long agentic-coding sessions, is not reliably reset by compaction, and can be restored by single-shot anchors with mode-dependent effects.
MBABench evaluates LLM agents on end-to-end financial spreadsheet tasks and shows current models fail to meet professional finance standards, especially beyond simple calculations.
TDDev automates the full TDD loop for web app generation from requirements, delivering 34-48 percentage point quality gains and zero manual intervention in user studies.
Constrained Diffusion for Code (CDC) integrates constraint satisfaction into the reverse denoising process of discrete diffusion models via constraint-aware operators that use optimization and program analysis to steer generation toward feasible programs.
BootstrapAgent distills repository bootstrapping heuristics into a persistent .bootstrap contract via multi-agent evidence extraction, Docker verification, and trace-driven repair, reporting 92.9% success and efficiency gains on three benchmarks.
Neo combines LLM-based agents with code search primitives to detect privilege escalation in polyglot microservices, reporting 81% precision and 85% recall while uncovering 24 zero-day vulnerabilities across 25 applications.
AEvo introduces a meta-agent that edits the evolution procedure or agent context based on accumulated state, outperforming baselines by 26% relative improvement on agentic benchmarks and achieving SOTA on open-ended tasks.
Checkup2Action is a new multimodal dataset and benchmark for generating safe, prioritized action cards from real-world clinical check-up reports using large language models.
CrackMeBench introduces 20 deterministic binary validation tasks and reports GPT-5.5 solving 11/12 generated ones at pass@3 while Claude and Kimi lag, especially on harder tasks.
PaperFit uses rendered page images in a closed loop to diagnose and repair typesetting defects in LaTeX documents, outperforming baselines on a new benchmark of 200 papers.
citing papers explorer
-
KISS Sorcar: A Stupidly-Simple General-Purpose and Software Engineering AI Assistant
The paper introduces KISS Sorcar, a simple open-source AI agent framework with a five-layer hierarchy and git worktree isolation to address context limits, error propagation, and reviewability in software engineering tasks.
-
Reliability of AI Bots Footprints in GitHub Actions CI/CD Workflows
Large-scale analysis of AI bot PRs shows Copilot and Codex achieve the highest CI/CD success rates but more frequent AI contributions correlate with reduced workflow reliability.
-
Spatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent Benchmarks
Spatial Atlas implements compute-grounded reasoning via a structured scene graph engine and deterministic computations to deliver competitive accuracy on spatial QA and Kaggle ML benchmarks while preserving interpretability.
-
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
-
Deep Researcher Agent: An Autonomous Framework for 24/7 Deep Learning Experimentation with Zero-Cost Monitoring
Deep Researcher Agent is a framework for autonomous 24/7 deep learning experimentation by LLM agents using zero-cost monitoring, constant-size memory, and a minimal-toolset multi-agent design.
-
Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol
An MCP-native workflow engine decouples agent reasoning from execution by using declarative blueprints, reducing token cost by over 99% on a 67-step Kubernetes synchronization task.
-
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
UI-TARS-2 reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld while attaining 59.8 mean normalized score on a 15-game suite through multi-turn RL and scalable data generation.
-
Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
Magentic-One is a modular multi-agent system that matches state-of-the-art performance on GAIA, AssistantBench, and WebArena using an orchestrator-led team of specialized agents.
-
ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair
ContextSniper reduces token use by 38.9-51.5% in repository-level program repair agents on SWE-bench Lite with 2 percentage point drops in resolution rate.
-
Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering
Coding benchmarks misalign with agentic software engineering because they conflate model and harness, grade against single references, and provide no component-level iteration signals.
-
The End of Code Review: Coding Agents Supersede Human Inspection
Coding agents have reached a capability level where human code review is no longer necessary because agents can serve every review goal more efficiently and the hybrid human-reviewer model does not scale.
-
Exploration Structure in LLM Agents for Multi-File Change Localization
Non-linear domain-scoped parallel LLM agents achieve higher micro F1 than linear exploration and some baselines for multi-file change localization on SWE-bench Pro ansible tasks.
-
What makes a harness a harness: necessary and sufficient conditions for an agent harness
Proposes and tests a constitutive definition of 'agent harness' via conceptual analysis of literature and six real systems.
-
From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design
Proposes four operational criteria for MetaAI recursive self-design, maps public systems including DGM's reported benchmark gains, and supplies a reproducible protocol without completed experimental runs.
-
CLI-Anything: Towards Agent-Native Computer Use
CLI-Anything advocates transforming applications into CLI-based protocols for agent-native interaction and introduces the CLI-Hub platform to support this shift away from GUI agents.
-
Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
A fine-tuned 4B model matches or exceeds frontier LLMs in terminal execution subagent tasks for coding agents, reducing main agent token usage by 30% with no performance loss.
-
AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices
AgentStop uses execution signals to early-terminate failing local LLM agent trajectories, cutting energy use 15-20% with minimal utility loss.
-
Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures
Proposes autopoietic architectures for self-constructing software as a fundamental shift in the SDLC, leveraging foundation models for autonomous evolution and maintenance.
-
OpenKedge: Governing Agentic Mutation with Execution-Bound Safety and Evidence Chains
OpenKedge redefines AI agent state mutations as a governed process using intent proposals, policy-evaluated execution contracts, and cryptographic evidence chains to enable safe, auditable agentic behavior.
-
From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap
A semi-structured thematic synthesis identifies core challenges in FM selection, alignment, prompting, orchestration, testing, deployment, and cross-cutting concerns like observability for production-ready FMware.
-
The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning
Comparative study of four execution substrates for coding-agent RL rollouts finds 110x cold-start latency variation and 1.8x spread in worker-hours for one million 150-step trajectories.
-
The Rise of AI-Native Software Engineering: Implications for Practice, Education, and the Future Workforce
A systematic review of 48 papers on AI in software engineering synthesizes evidence into frameworks for AI-native practice, a nine-dimension competency model, a four-phase curriculum roadmap, and an agenda of research gaps, while noting contradictory productivity findings.
-
Agent System Operations: Categorization, Challenges, and Future Directions
This survey categorizes anomalies in agent systems into intra-agent and inter-agent types and introduces the AgentOps framework with four operational stages.
-
Meta-Engineering Harnesses for AI-Native Software Production: A Contract-Driven Adversarial Verification Architecture with Early Deployment Report
Presents a contract-driven adversarial verification architecture for AI-native software production with early deployment observations from 17 features.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
-
Challenges and Future Directions in Agentic Reverse Engineering Systems
Agentic LLM systems for reverse engineering fail on obfuscation, timing, and unique architectures due to token limits and missing guardrails, with challenges and directions proposed.
-
Building an Internal Coding Agent at Zup: Lessons and Open Questions
Engineering choices for tools, safety guardrails, and human oversight determine whether an internal coding agent delivers value in practice more than the underlying model quality.
- VeRO: A Harness for Agents to Optimize Agents
- Toward Training Superintelligent Software Agents through Self-Play SWE-RL