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.
103
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.
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.
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.
Enforcing role separation in agent teams reveals that prompt-only setups hide coordination failures, with verifiers approving 49% of failing work and teams sometimes harming performance when solo agents already succeed.
SLYP agentic pipeline discovers race condition vulnerabilities in Windows COM binaries and generates debugger-verified PoCs, scoring 0.973 F1 on a 40-case benchmark and finding 28 new confirmed vulnerabilities in production services.
ProgramBench introduces 200 tasks where models must reconstruct full programs like FFmpeg or SQLite from docs alone; none of 9 evaluated LMs fully solve any task and the best passes 95% tests on only 3% of tasks while favoring monolithic code.
Comet-H orchestrates LLMs via deficit-scoring prompt selection and half-life task tracking to co-evolve research software components, demonstrated by a static analysis tool reaching F1=0.768 versus a 0.364 baseline.
RepoDoc uses a repository knowledge graph with module clustering and semantic impact propagation to generate more complete documentation 3x faster with 85% fewer tokens and handle incremental updates 73% faster than prior LLM-based tools.
citing papers explorer
-
SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
SkillLens organizes skills into policies-strategies-procedures-primitives layers, retrieves via degree-corrected random walk, and uses a verifier for local adaptation, yielding up to 6.31 pp gains on MuLocbench and raising ALFWorld success from 45% to 51.31%.
-
Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture
RL Developer Memory is a feedback-normalized, safety-gated memory architecture for RL coding agents that logs contextual decisions and applies conservative off-policy gates to maintain 80% decision accuracy and full hard-negative suppression on a 200-case benchmark.
-
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
VLAA-GUI adds mandatory visual verifiers, multi-tier loop breakers, and on-demand search to GUI agents, reaching 77.5% on OSWorld and 61.0% on WindowsAgentArena with some models exceeding human performance.
-
Evaluation-driven Scaling for Scientific Discovery
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
-
OpenGame: Open Agentic Coding for Games
OpenGame is the first open-source agentic framework for end-to-end web game creation, using Game Skills and GameCoder-27B to achieve state-of-the-art results on 150 prompts via a new benchmark measuring build health, visual usability, and intent alignment.
-
AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems
AutoOR uses synthetic data generation and RL post-training with solver feedback to enable 8B LLMs to autoformalize linear, mixed-integer, and non-linear OR problems, matching larger models on benchmarks.
-
When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis
LLM agents avoid output stalling and reduce generation tokens by 48-72% via deferred template rendering guided by Output Generation Capacity and a Format-Cost Separation Theorem.
-
KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving
KAIROS reduces power by 27% on average (up to 39.8%) for agentic AI inference by using long-lived context to jointly manage GPU frequency, concurrency, and request routing across instances.
-
From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to Python
LLM-driven translation of a production Rust AI agent to Python achieves near-parity on SWE-bench (73.8% vs 70.0%) and Terminal-Bench (42.5% vs 47.5%) while evolving into a 15.9x smaller superset with 30 new capabilities.
-
Pioneer Agent: Continual Improvement of Small Language Models in Production
Pioneer Agent automates the full lifecycle of adapting and continually improving small language models via diagnosis-driven data synthesis and regression-constrained retraining, delivering gains of 1.6-83.8 points on benchmarks and large lifts in production-style tasks.
-
Auditable Agents
No agent system can be accountable without auditability, which requires five dimensions (action recoverability, lifecycle coverage, policy checkability, responsibility attribution, evidence integrity) and mechanisms for detect/enforce/recover.
-
Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
A unified framework for LLM agent memory is benchmarked, with a new hybrid method outperforming state-of-the-art on standard tasks.
-
ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files
ContextCov compiles agent instruction files into static, runtime, and architectural guardrails, raising constraint compliance to 88.3% on SWE-bench Lite tasks versus 67% and 50.3% for prompt and reflection baselines.
-
SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
The paper systematizes agentic skills beyond tool use, providing design pattern and representation-scope taxonomies plus security analysis of malicious skill infiltration in agent marketplaces.
-
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.
-
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.
-
Agentless: Demystifying LLM-based Software Engineering Agents
Agentless, a basic three-phase LLM pipeline for bug localization, repair, and validation, outperforms complex open-source agents on SWE-bench Lite with 32% success rate at $0.70 cost.
-
Direct Causation in International Humanitarian Law and the Challenge of AI-Mediated Civilian Cyber Operations
Autonomous AI cyber systems deployed by civilians fail the one-causal-step and integral-part requirements of the IHL direct participation test because harm arises from post-disengagement system decisions.
-
Automating Formal Verification with Reinforcement Learning and Recursive Inference
RLVR training raises verified Dafny pass rates from 9.7% to 31.1% on a filtered benchmark while a Lean proof scaffold lifts success from 46.2% to 69.2% on a pilot set and solves 7 of 42 prior unsolved tasks.
-
Agentic AI Workload Characteristics
Agentic workloads with context caching become decode-dominated with high KV-cache reuse and show tool use shifting from early read/explore to later execute/write phases.
-
Augment Engineering: A Methodology for Multi-Tool AI Orchestration Across Professional Domains
Introduces Augment Engineering as a six-phase multi-tool orchestration methodology, supported by exploratory statistics from a single-practitioner case study across seven domains.
-
Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators
Sibyl-AutoResearch introduces self-evolving trial-and-error harnesses with auditable conversion units that link trial signals to updated research behaviors and harness repairs in autonomous systems.
-
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.
-
Agentic Discovery of Cryomicroneedle Formulations
A closed-loop workflow using Gaussian process surrogate modeling and Bayesian optimization, updated over ten iterations with 106 wet-lab tests, adapted from literature data to identify a cryoprotectant formulation achieving 95.15% post-thaw viability for cryomicroneedles.
-
$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
f-OPD decomposes on-policy distillation drift into rollout and supervision components, then applies a sample-level freshness score to adaptively limit stale data influence and stabilize long-horizon agent training.
-
Interactive Evaluation Requires a Design Science
Interactive evaluation of AI must be reframed as a distinct paradigm that maps interaction trajectories to judgments on process, recoverability, coordination, robustness, and system performance, supported by a two-axis taxonomy and design principles.
-
Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
Grep retrieval generally outperforms vector retrieval in agentic search tasks, with performance varying strongly by agent harness and tool-calling style.
-
Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt-Engineering Quality Assurance
A case study of iterative auditing on AEGIS LLM multi-agent specs found 51 defects over nine rounds with non-monotonic convergence, a post-hoc seven-category taxonomy, and replications showing category kappa of 0.80.
-
Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves
GWAgent agentic workflow produces analytic surrogates for eccentric BBH waveforms with 6.9e-4 median mismatch and 8.4x speedup, outperforming baselines, and infers eccentricity for GW200129.
-
Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems
Safety constraints in LLM-based multi-agent systems commonly weaken during execution through memory, communication, and tool use, requiring them to be maintained as explicit state rather than asserted once.
-
Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair
Reshaping outcome rewards, process signals, and rollout comparability in GRPO raises strict compile-and-semantic accuracy in agentic code repair from 0.385 to 0.535 under weak feedback.
-
Toward a Science of Intent: Closure Gaps and Delegation Envelopes for Open-World AI Agents
Intent compilation turns vague human goals into verifiable artifacts, using closure-gap vectors and delegation envelopes to separate open-world agent challenges from closed-world solvers and to benchmark closure fixes against extra search.
-
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.
-
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.
-
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.
-
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.