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.
142
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.
Empirical study of real-world vibe-coded apps finds recurring vulnerabilities like placeholder logic and secret exposure caused by AI agent limitations such as memory loss and insufficient security knowledge.
CLI-Universe synthesizes a verified 6K dataset of terminal-agent tasks that, when used to fine-tune Qwen3-32B, reaches 33.4% on Terminal-Bench 2.0 and sets a new open-source SOTA for models at or below 32B parameters.
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.
citing papers explorer
-
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
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.
-
Understanding the (In)Security of Vibe-Coded Applications
Empirical study of real-world vibe-coded apps finds recurring vulnerabilities like placeholder logic and secret exposure caused by AI agent limitations such as memory loss and insufficient security knowledge.
-
Detecting Privilege Escalation in Polyglot Microservices via Agentic Program Analysis
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.
-
Agentic Vulnerability Reasoning on Windows COM Binaries
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.
-
Prompt Injection Attack to Tool Selection in LLM Agents
ToolHijacker optimizes malicious tool documents via a two-phase strategy to hijack LLM agents' tool selection in no-box settings.
-
VeriPort: Automated and Verified Patch Backporting at Scale
VeriPort is an end-to-end agentic system that backports vulnerability patches to all affected versions of a package at scale while producing verification evidence, achieving 95.3% success on 128 benchmark tasks and generating over 5,000 verified patches across 169 CVEs.
-
Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents
Multi-layer fingerprinting using TLS, HTTP, and browser behavior identifies distinct AI web agent frameworks at 97% accuracy via decision tree classification.
-
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.
-
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.