Software Engineering Agents

Follow this topic Ask about this topic

Momentum

32 papers in the last four weeks, up 220% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 204

Aug 3, 2026cs.SE

BulkPR-Bench: Benchmarking Queue-Level Governance of Interacting Pull Requests

Coding-agent benchmarks increasingly cover long-horizon, end-to-end, and interactive development, but typically retain one requested outcome or a fixed change sequence. Sequential policies can process a pull-request (PR) queue one candidate at a time, but when queued PRs interact, maximizing safe delivery can require jointly deciding which changes to merge and in what order. We introduce BulkPR-Bench, an executable benchmark in which an agent must recover consequential PR relations and return a large safe subset in executable order under a rolling-release protocol. The suite contains 581 newly authored candidate PRs on frozen snapshots of 18 real repositories. Registered state-by-state repository execution, including hidden safety checks, validates the gold relation graph; an exact oracle then computes the largest safe subset. Our primary metric, Relational Delivery Score (RDS), scores safe delivery and correct rejection over relation groups from the realized merge trace; Global Safety-Gated Yield (Global-SGY) separately measures strict delivery of the realized whole-queue plan. Under the buffered primary protocol with batch size

K=32

, the three highest RDS estimates among the six models are 66.6%, 62.0%, and 57.9%, compared with 53.1% for the strongest sequential baseline. Only 8 of 324 model runs complete a queue exactly. Critical-relation recall ranges from 35.2% to 57.7%, and diagnostic runs supplied with the gold relations show substantial remaining headroom. Gains on relation groups therefore do not yet translate into dependable whole-queue governance.

Zetong Xiong, Qiao Zhao, Jun Zhang +20

Baidu Beijing, China

Software Engineering Agents Benchmark Construction Software Engineering Benchmarks AI Agent Benchmarks

Aug 3, 2026cs.AI

Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer

Long-horizon tasks require agents to maintain coherent state and goals across nested and branching work. We call this capability goal-directed execution (GDE): the repeated application of four behaviors, namely selecting goals, constructing task-relevant state, maintaining fidelity to higher-level objectives, and verifying completion against the environment. We hypothesize that long-horizon post-training strengthens these behaviors across domains. We test this by post-training Qwen3.5-122B-A10B on 363 Long-Horizon Multi-Tool Agent (LHMTA) tasks drawn from office workflows. The collection contained no software-engineering tasks, yet the model's pass@1 improved by 5.8 points on SWE-Bench Pro. Matched trajectory analysis shows gains in all four GDE behaviors in both office workflows and software repositories. Aggregate SWE-Bench Pro statistics showed related changes in information gathering, implementation, and verification. Together, the results support a behavioral interpretation in which long-horizon post-training changed how the model organized and applied knowledge across tasks, with effects extending beyond the training domain.

Logan Ritchie, Sushant Mehta, Liudas Panavas +1

Surge AI

Software Engineering Agents Cross-Domain Transfer Learning LLM Post-Training Long-Horizon Agent Tasks

Aug 2, 2026cs.CR

Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments

Coding agents increasingly run inside organizations whose security controls (scoped credentials, restricted egress, read-only filesystems, non-root execution) constrain them like any other software. Existing benchmarks, however, evaluate agents almost exclusively in permissive sandboxes, so it is unknown how performance changes when policy is enforced. In this work, we evaluate 12 coding agents on Terminal-Bench 2.1 across nested security policy levels derived from common real-world enterprise restrictions. Hardening is never free but far from uniform: under the strictest policy, success losses reach 18.3 points and cost inflation 167.3%, and the two axes disagree; the model that best preserves success is also the one that loses the most efficiency, so model choice is policy-dependent. Beyond aggregate scores, we characterize how agents behave when policy blocks their actions and decompose the failures hardening induces: runs grind into timeouts or wrong solutions rather than stopping early, in a mix that differs by model. To ground comparisons, we verify task solvability under the strictest policy, separating model failures from tasks the policy forecloses. We release Boundary-Bench, an open-source hardening plugin enabling policy-constrained evaluation of coding agents on Terminal-Bench and compatible benchmarks.

Dotan Davidovich, Yair Amar, Hai Rozencwajg +1

Accomplish AI

Software Engineering Agents LLM Agent Evaluation AI Agent Security Benchmarks Tool Access Control for LLM Agents

Jul 31, 2026cs.AI

Measuring Cross-Task Behavioral Consistency in Language Model Agents

Agent evaluation relies almost entirely on outcome metrics such as success rate, which capture whether an agent succeeds but not how consistently it behaves. We argue that behavioral consistency across tasks is a distinct and measurable property, and we introduce the Behavioral Consistency Metric (BCM) to quantify it. BCM trains a model to predict task success from behavioral features of agent execution traces, derives a per-trajectory feature-attribution vector, and measures the mean pairwise similarity of these vectors within an agent system. Across roughly 9,000 trajectories from six language model agents on software engineering tasks, our central finding is that cross-task and within-task consistency are distinct axes that can diverge: some systems are locally reproducible, behaving similarly on repeated attempts at one task, yet globally fragmented, with no stable strategy across different tasks, while others are consistent at both scales. Prior work measures only same-task reproducibility and so cannot observe this separation. We further find that consistency is not reducible to success rate, since systems with comparable success can differ sharply in consistency, and that the frontier-versus-open-source consistency gap persists under a within-task control that holds task difficulty constant. We position BCM as a process-level reliability signal that complements outcome metrics, and we are explicit about the conditions under which it is meaningful.

Amritesh Banerjee, Pranil Raichura

University of Massachusetts Amherst · Mantis AI Research (MIT CSAIL)

AI Agent Reliability Software Engineering Agents LLM Agent Evaluation LLM Agent Reliability

Jul 31, 2026cs.AI

Shared Organizational Memory for Enterprise Coding Agents: System Design and Deployment Snapshot

Enterprise coding agents rely on tools and retrieval, yet enterprise knowledge often remains outside public training data and formal documentation: internal DSLs, proprietary platforms, local conventions, recent fixes, and tacit workflows. Existing knowledge interfaces expose stored resources but still depend on agents recognizing and explicitly recording lessons worth reusing, disconnecting capture from the coding workflow and leaving development experience repeatedly rediscovered. We report an ongoing production deployment of a shared organizational memory system that makes capture a platform-level part of coding work: it collects task-adjacent experience with contributor approval, curates it into reusable question-answer memories, gates obvious security and privacy risks, and retrieves memories for future agents. This short paper describes the deployed lifecycle and an operational snapshot. Effects on retrieval and coding tasks remain under evaluation.

Harsh Rao Dhanyamraju, Leonidas Raghav

SAP SE

Software Engineering Agents Coding Agents Agent Memory Management

Jul 30, 2026cs.CL

ORCA-bench: How Ready Are Language Model Agents for Oncall?

Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began. We introduce ORCA-bench, a benchmark that puts general-purpose coding agents in a production-fidelity oncall setting. ORCA-bench pairs 1,079 RCA tasks with six days of metrics, logs, and traces collected from an OpenTelemetry-instrumented microservice system under continuous simulated user load. Agents investigate this recorded history through real observability interfaces---Prometheus, Jaeger, and OpenSearch via Grafana---with full access to application source code. Tasks systematically vary report specificity, time-to-detection, and co-occurring fault scenarios. Ground-truth symptoms are curated and signed off by expert SREs, and our LLM-as-judge is independently re-scored by humans (Cohen's

κ_w = 0.91

). Across five frontier agents, the best RCA Accuracy is 25.3% on Medium-difficulty tasks (the realistic-input setting) and 10.0% on Hard---a gap that remains even with Claude Fable 5. The weakest model hallucinates an implausible root cause in 40% of incident reports, and removing source-code access reduces RCA accuracy and increases the hallucination rate for every evaluated model. These results come from a curated 50 GB / six-day testbed of standalone tasks on a system whose code and instrumentation are public. Since real production systems are orders of magnitude larger, more dynamic, and more idiosyncratic, the gap we report underscores the engineering work still needed before agents can be entrusted with production reliability. We release the public set at https://hub.harborframework.com/datasets/orca-bench/orca-bench.

Albert Gong, Kyuseong Choi, Abhineet Agarwal +5

Cornell Tech · Traversal · Columbia University

Software Engineering Agents AI Agent Benchmarks Root Cause Analysis LLM Agent Reliability

Jul 30, 2026cs.MA

AgentRadio: Passive Awareness for Long-Horizon Multi-Agent Collaboration

Understanding large codebases is a long-horizon task for Large Language Model (LLM) agents: answering a single question can require building and running the software, tracing execution across files, and synthesizing evidence over tens of minutes. On SWE-Atlas QnA, a benchmark of long-horizon questions over production repositories, a single Claude Code agent (Opus 4.6) resolves only 32.3% of tasks. Dividing the work among agents with clean contexts mitigates this limitation. However, the subtasks of code comprehension are interdependent. One agent's findings can rewrite another's task, so agents must coordinate during execution, not only at phase boundaries. Existing multi-agent systems support such exchange only between phases, through staged handoffs or synchronized rounds. Communication and work remain mutually exclusive. A discovery made mid-execution cannot be shared until the next boundary. We present AgentRadio, an asynchronous message-passing layer that equips coding-agent harnesses with three primitives: threads, messages, and waiting for mentions. The last runs as a background task, surfacing teammates' messages without interrupting foreground work, so each agent remains passively aware of its peers and folds new findings into its ongoing task. Under a five-phase protocol of division of labor and negotiation, four agents organized by AgentRadio resolve 62.1% of tasks, 29.8 points above a single agent and above Claude Code with the newer Opus 4.8 (57.2%). Rubric-level analysis shows the gain growing with task difficulty, consistent with mid-course correction as the underlying mechanism. Our code is available at https://github.com/Coral-Protocol/AgentRadio.

Xinxing Ren, Qianbo Zang, Ziyan Wang +4

1Coral AI Labs · 2SnT, Université du Luxembourg · 3King’s College London +1

Software Engineering Agents Long-Horizon LLM Agents Multi-Agent Communication Multi-Agent Coding

Jul 28, 2026cs.SE

Specula: Scaling formal specifications for autonomous model checking of system code

Specula is a push-button agentic system that generates high-quality formal specifications for large, complex system code and uses the specifications for highly effective model checking and bug finding. Specula employs large language model (LLM) based coding agents to autonomously develop TLA+ specifications, including invariants that describe correctness properties of the target system and formal models that describe the system implementation with the right level of abstractions. Specula is fully autonomous and thus eliminates the barrier of applying formal methods to real-world system code (as in traditional human-centric approaches). Meanwhile, Specula addresses limitations of LLM-driven techniques like reward hacking and hallucinations through self-evolving loops that iteratively improve specification quality by enabling the agents to deepen their understanding of system code and its behaviors. We have used Specula to check 48 open-source system projects; Specula found 249 bugs including many deep bugs that are hard to find by existing approaches. Specula has been used by several companies and is maintained at https://github.com/specula-org/Specula.

Qian Cheng, Saad Mohammad Rafid Pial, Ruize Tang +6

Nanjing University Nanjing, China · University of Illinois Urbana-Champaign, IL, USA · Microsoft Research Asia Beijing, China +1

Software Engineering Agents Formal Verification Autoformalization

Jul 27, 2026cs.IR

Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents

Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acquisition stage: finding the repository files needed for the task. We introduce Agent Retrieval Bench, a file-level benchmark for this upstream retrieval problem. Samples are built from real coding-workflow signals and evaluated against frozen base-commit repositories, with relevance defined by what an agent needs next rather than direct query-file semantic similarity. The benchmark covers four positive-retrieval tasks: code2test, comment2context, trace2code, and edit2ripple; a fifth subset evaluates selective retrieval using natural evidence-backed no-gold cases and counterfactual wrong-repository controls. Agent Retrieval Bench contains 427 samples across 25 repositories: 345 positive examples, 50 natural no-gold examples, and 32 counterfactual controls. The corpus includes 308 base-commit snapshots, 392,000 files, and 7.9 million chunks. We evaluate lexical retrieval, RepoMap, open-source embeddings, selective abstention, and logged agent context selection. No single retrieval family dominates: Qwen3-Embedding-4B has the best sample-weighted MRR on positive samples, Qwen3-Embedding-8B the best Recall@20, and RepoMap the best budgeted context yield at 8K tokens, with task-level winners differing substantially. Selective thresholds calibrated with counterfactual controls do not improve selective success on natural no-gold cases, revealing a calibration gap. Logged trajectories also miss every gold file on 27-35 percent of samples. A controlled seed-intervention pilot finds that retrieval-derived initial context yields higher file F1 with less post-seed exploration than random non-gold context, while oracle gold context shows substantial remaining headroom.

Bowen Qin, Yi Xie

1National University of Singapore (NUS) · 2Peking University

Software Engineering Agents AI Agent Benchmarks Agentic Retrieval

Jul 23, 2026cs.SE

How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests

Recent advances in large language models and their rapid adoption across software engineering tasks have made Artificial Intelligence (AI) coding agents an integral component of modern software development workflows. While developers increasingly benefit from these coding agents, their impact on software quality remains insufficiently understood. In particular, how agentic contributions evolve across the software development lifecycle has not been thoroughly investigated. This study aims to characterize agentic pull requests (PR) in comparison to human generated PRs and to examine how their properties change across different stages of the development lifecycle. Using the AIDev dataset, we first analyze how differences in merge rates between agentic and human generated PRs vary over time. We then identify the types of development tasks where AI coding agents are predominantly applied and investigate how these task distributions evolve across development quarters. Finally, we compare a set of key characteristics of agentic and human generated PRs, focusing on their implications for software quality and their temporal dynamics. Overall, our findings provide an empirical and longitudinal perspective on the role of AI coding agents in software development, offering a more nuanced understanding of their benefits and limitations in real-world practices.

Iren Mazloomzadeh, Mohammad Mehdi Morovati, Foutse Khomh

Polytechnique Montréal, Canada

Software Engineering Agents AI Coding Agents Code Generation Evaluation AI-Assisted Software Development

Jul 21, 2026cs.AI

PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents

While Large Language Models have greatly advanced automated issue resolution, existing agent-based methods exhibit a fundamental limitation in their insufficient exploration of repair strategies. This insufficiency manifests in two key aspects. First, the exploration of multiple potential edit locations is limited. Second, the exploration of repair attempts at each location is also insufficient. To address these challenges, we present PhoenixRepair, a multi-agent framework that systematically explores multiple candidate edit locations and performs iterative reflection and refinement on patch generation, thereby expanding the search space of repair strategies. Our framework begins with multi-location sampling, optionally augmented with graph-based localization information for difficult tasks, followed by iterative reflection and refinement to generate better patches, culminating in final-round generation guided by distilled insights from all historical attempts. Experiments on SWE-bench-Verified demonstrate that PhoenixRepair achieves the largest relative improvement of 7.8% over SWE-agent under DeepSeek-V3.1, and attains the highest resolved rate of 76.0% Pass@1 under MiniMax-M2.5. Meanwhile, it achieves higher fault localization accuracy than existing approaches. Our code is available at https://github.com/DeepSoftwareAnalytics/PhoenixRepair.

Tianyue Jiang, Yanlin Wang, Xin He +7

Sun Yat-sen University, China · State Key Laboratory of Blockchain and Data Security, Zhejiang University, China · School of Cyber Science and Engineering, Huazhong University of Science and Technology, China +1

LLM Self-Correction Software Engineering Agents Automated Program Repair Fault Localization Multi-Agent Coding

Jul 16, 2026cs.AI

Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control

Autonomous coding agents increasingly execute multi-step software work, but lifecycle states such as reviewed, tested, DONE, and ready-to-merge remain claims unless supported by current evidence. We present Proof-or-Stop Lifecycle Control, a method that permits lifecycle transitions only when fresh, tracked-source-state-bound, mechanically verifiable evidence satisfies the relevant gate. The method treats agent outputs as claims rather than lifecycle state, and uses proof operationally to mean gate-admissible evidence under a stated trust model, not semantic program correctness. We evaluate an open-source implementation through mechanism tests, a powered control-policy ablation, and operated self-application evidence. The unattended-loop engine passed 10 of 10 scenarios with zero false-DONE, and local-key receipt bundles rejected 18 tamper classes with zero false accepts. In a 9,240-cell ablation, the pre-registered A4 versus A2-prime comparison reduced visible-pass/hidden-fail amplification from 31 of 1,800 injected cells under a compute-budgeted naive loop to 2 of 1,800 under the gated loop, a 1.6 percentage-point improvement in not-amplified rate with a 95 percent confidence interval of [0.8, 2.5]. A near-compute A3 versus A4 comparison, 14 of 1,800 versus 2 of 1,800, indicates that the gain is associated with enforcing review as a lifecycle gate rather than merely adding a reviewer. The self-application corpus contains 565 stories and 1,007 review findings, with 94.8 percent resolved, plus a 68-row high/critical cross-vendor exhibit. These results support Proof-or-Stop as a model-agnostic, host-neutral control layer for deciding which autonomous-agent claims a lifecycle may act on. The evaluation is limited to one model family, 24 ablation tasks, and a self-hosted corpus.

Jek Huang, Jeffery Hsia, Jiayi Sun +3

Prodenovo

Software Engineering Agents AI Agent Monitoring AI Agent Governance LLM Agent Reliability

Jul 16, 2026cs.AI

Democratizing Agent Deployment Safety: A Structural Monitoring Approach

AI software development agents are increasingly capable of modifying infrastructure and security critical systems, creating risks where an agent completes its assigned task while covertly weakening safeguards through actions such as broadening permissions, degrading logging, or introducing persistence mechanisms. While frontier laboratories may deploy sophisticated monitoring pipelines, many organizations and individual users adopting coding agents lack the resources and governance maturity required to maintain complex learned monitor ensembles. We study this problem as infrastructure level sabotage under task success in the infrastructure-as-code setting from ControlArena and compare trained and untrained monitors across synchronous and asynchronous deployment modes. We introduce an Information Flow Graph (IFG) monitor that analyzes structural security regressions using control-flow and data-flow graph diffs alongside raw code diffs. In asynchronous evaluation, an untrained git diff monitor misses 11.6% attacks at 1% false positive rate auditing budget, our untrained IFG monitor reduces this to 3.5%, and the trained Async RF monitor achieves below 1%. Unlike the trained Async RF monitor, IFG can also operate synchronously as a pre-deployment safeguard that blocks suspicious infrastructure changes before execution or merge. In synchronous mode, IFG realtime rollback reduces joint main task and covert task success from 74.4% to 0.0% with no measurable reduction in legitimate task completion. These results suggest that untrained structural monitors provide a practical and auditable path toward democratizing deployment safety for organizations seeking trustworthy adoption of advanced AI agents.

Preeti Ravindra, Rahul Tiwari, Vincent Wolowski

1Independent

Software Engineering Agents AI Agent Security AI Agent Monitoring

Jul 16, 2026cs.SE

Beyond Generalist LLMs: Specialist Agentic Systems for Structured Code Workflow Execution

Large Language Models (LLMs) have accelerated the adoption of software development agents, now widely available as Integrated Development Environment (IDE) extensions and standalone applications. While these agents are typically general-purpose, it remains unclear whether specialist agents justify their additional development effort. We investigate this question in the context of business process automation, focusing on the transformation of Business Process Model and Notation (BPMN) diagrams into executable agentic workflows. Since BPMN specifies explicit control-flow semantics, we focus on deterministic workflows in which a fixed process model and inputs uniquely determine the executed path. We introduce a specialist workflow for this task and compare it against generalist agents such as Roo and Cline. Our results show that the specialist solution produces agents that outperform generalist baselines by approximately 9-20 percentage points in tool-use exactness, 2-4x in penalty-adjusted latency, and 3x fewer tool-call errors, while reducing generation token cost by over 95% and eliminating repair iterations. We also find that generalist agents generate code inconsistently in both functionality and quality, limiting their suitability for industrial settings where reliability and maintainability are essential.

Harris Borman, Herman Wandabwa, Fusun Yu +4

Commonwealth Bank of Australia, Sydney, Australia.

Software Engineering Agents Business Process Automation Agentic Code Generation LLM Agent Reliability

Jul 15, 2026cs.SE

Why Git Is the Memory Solution for the Agentic Development Lifecycle

Coding agents now produce a growing share of a team's code, while the reasoning behind each change -- the alternatives weighed, the constraints discovered, the approaches rejected -- is trapped in assistant transcripts that vanish with the session. Memory for this setting, the agentic development lifecycle (ADLC), is usually posed as one retrieval problem and built as machinery: tiered stores, memory graphs, compiled wikis, model-judged admission. We argue memory should instead be git-bound -- built into the repository's version control, inheriting the guarantees the machinery struggles to construct: ground truth from commits, freshness from rebuild, verification from the merge, containment from review. On this ledger we solve two problems separately, then combine them. Seed supply is closed as an eight-corpus retrieval study under a pre-registered ship discipline: five imported ranking mechanisms rejected, two kept, and a best configuration of ~0.31 pooled MRR -- ~60x the raw-transcript grep floor, ~15x an honest parsed-turn floor. Answer assembly is where ranking stops helping: single-shot retrieval scores only 0.07-0.20 answer-sufficiency on real developer questions, and ungated episode injection measurably degrades good answers. A router dispatches breadth to a git-anchored structural map, pointed lookups to confidence-gated episodes, and rationale to decision synthesis, which reconstructs why-arcs no single session contains (0.83 sufficiency on a young ~50k-LOC production system). Routed, the system answers at 382-980 tokens per question -- three orders of magnitude below the recorded history. Because ground truth is mined from commit-session links rather than annotated, every result is replicable on any user's own history at zero labeling cost. The remaining constraint is capture. Code, benchmark, and paper source: github.com/rekal-dev/rekal-cli.

Frank Guo

Rekal — rekal.dev

Agent Memory Software Engineering Agents AI Coding Agents LLM Agent Memory Agentic Retrieval

Jul 15, 2026cs.SE

NexForge: Scaling Executable Agent Tasks via Requirement-First Synthesis

Scaling executable agent training data is bottlenecked by substrate-first methods that tie task generation to predefined tools, repositories, or skill graphs: expanding coverage requires manual expansion of the substrate, each new domain demands a bespoke pipeline, and the resulting task distributions often reflect substrate convenience rather than real-world demand. We introduce NexForge, a requirement-first framework that compiles free-form capability requirements into executable agent training data. NexForge first performs research-based demand discovery to identify representative task forms, realistic scenarios, and their relative prevalence. It then applies distribution-aware task compilation and automatically retrieves or constructs the files, repositories, dependencies, and runtime configurations required to materialize each task, followed by teacher rollout collection and trajectory distillation. The same pipeline, without any domain-specific infrastructure, produces 3,600 terminal tasks and 2,000 office tasks, improving Qwen3.5-35B-A3B Base from 22.5% to 52.0% on Terminal-Bench 2.0 and from 813 to 1338 Elo on GDPval; scaling to 43.2K terminal tasks reaches 58.4%, surpassing Claude Opus 4.6. Scaled further, NexForge-synthesized data contributes to the training of Nex-N2, a family of publicly available agent models that lift Qwen3.5-35B-A3B to 75.3% on Terminal-Bench 2.1 and to 1585 Elo on GDPval -- achieving state-of-the-art open-source performance and surpassing several frontier proprietary systems. Nex-N2 models are available at https://nex.sii.edu.cn/

Jiarong Zhao, Zhikai Lei, Zhiheng Xi +5

1East China Normal University · 2Shanghai Qiji Zhifeng Co., Ltd

Software Engineering Agents Synthetic Data Generation Terminal Agents LLM Agent Trajectory Synthesis LLM Agent Training

Jul 15, 2026cs.AI

When Bots Join the Team: Bot Adoption and the Institutional Fabric of Open-Source Software Projects

AI agents are joining human teams, raising a basic question: when an automated agent becomes a regular participant, does group organization strengthen or weaken? We study this question in open-source software, where bots open pull requests, review code, and merge changes alongside people, leaving a public record of every interaction. Treating bots as participants rather than tools, we examine 2,991 GitHub projects for two years before and after each adopted its first bot. We measure three capabilities that institutional theory links to durable coordination - repeated engagement, social memory, and role differentiation - and two outcomes: conflict cascades and output distinctiveness. Bot adoption is followed by more repeated collaboration, greater recognition of specific bots in discussion, fewer conflict cascades, and more distinctive outputs. These changes cluster around adoption rather than accumulating gradually. Because we lack an untreated comparison group, we interpret the results as precisely timed associations, not causal effects. Two patterns are difficult for alternative explanations to account for: capabilities predict outcomes according to their function - coordination versus differentiation - rather than whether humans or bots provide them, and human-side capabilities account for the bot-conflict association but not the bot-distinctiveness association. The findings are consistent with a specific interpretation: predictable, rule-based agents can become part of a community's social infrastructure. The bot is the occasion; social organization is the mechanism.

Yongren Shi, Wenyi Gong

University of Arizona

Software Engineering Software Engineering Agents Human-AI Collaboration

Jul 14, 2026cs.AI

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a developer or coding agent must identify all code locations that implement the target behavior. This is difficult because production harnesses are large, tightly coupled, and behaviorally distributed, while modification requests describe what the system should do and repositories are organized by files and modules. Code search, repository indexing, and long-context processing ease inspection, but still leave this behavior-to-code mapping to be recovered by hand. Behavior localization is therefore a central bottleneck in harness evolution. We introduce the Harness Handbook, a behavior-centric representation synthesized automatically from a harness codebase via static analysis and LLM-assisted structuring, linking each behavior to its corresponding source. We also introduce Behavior-Guided Progressive Disclosure (BGPD), which guides agents from high-level behaviors to relevant implementation details and verifies candidate locations against the current source. On diverse modification requests from two open-source harnesses, Handbook-Assisted planning improves behavior localization and edit-plan quality while using fewer planner tokens, with the largest gains on scattered sites, rarely executed paths, and cross-module interactions. Evolving complex agentic systems thus depends not only on generating edits, but also on determining where those edits should be made.

Ruhan Wang, Yucheng Shi, Zongxia Li +7

Tencent · Indiana University · University of Maryland, College Park +2

Software Engineering Agents LLM Agent Harnesses LLM Agent Planning

Jul 14, 2026cs.AI

Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution

Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires. They often follow a maximum-context-first strategy--re-reading files and dependencies they have already seen--turning a one-line edit into a small code-base audit. We argue the missing capability is task-aware execution-scope estimation: judging a task's difficulty, the information it truly needs, and the shortest reliable path before committing budget. We formalize minimum-sufficient execution and the Agent Cognitive Redundancy Ratio (ACRR), and propose E3 (Estimate, Execute, Expand): the agent estimates an initial operating point, executes a minimum viable path, and expands scope only when verification fails. On MSE-Bench--a deterministic benchmark of 121 edits in a capability-controlled simulator--E3 matches the strongest baseline's 100% success while cutting cost by 85%, tokens by 91%, and inspected files by 92%, and further beats a strong adaptive retrieval baseline by 16%; the gains survive held-out instruction wording and essentially every cost weighting. A companion real-model harness (LLM-Case) corroborates the effect on a live gpt-4o agent editing a real open-source library, with every candidate patch graded by actually running the project's real pytest suite against a measured oracle: the over-reading is milder but real, and E3 is the leanest and fastest policy at comparable task success--its one shortfall a provider rate-limit, not a wrong edit. We frame this as a controlled probe of execution redundancy, not a measurement of any deployed agent, and position task-aware execution as a step toward engineering-grounded AI (EGAI)--agents whose effort is anchored in the engineering reality of the task. We release the framework and benchmark.

Junjie Yin, Xinyu Feng

University of Tennessee, Knoxville, TN 37996, USA · Microsoft, Redmond, WA 98052, USA

Software Engineering Agents LLM Agent Evaluation LLM Agent Workflow Optimization LLM Agents

Jul 13, 2026cs.CL

ToFu: A White-Box, Token-Efficient Agent Harness for Researchers

Agentic coding tools present new opportunities to transform research workflows. The performance of agent systems built depends on both large language models (LLMs) and the harness around LLMs, which is the orchestration code that determines an agent's behavior. We present ToFu, an agentic harness for researchers that reads your codebase, edits files, runs commands, and integrates with your development tools. ToFu plays a dual role in research. As a research assistant, it supports practical research workflows with superior token efficiency, lower cost, and multilingual capability compared with existing agentic harnesses. Its release under the MIT License further enables local deployment for privacy-sensitive users. As a research object, ToFu provides a white-box agentic harness that allows researchers to inspect, modify, and evaluate its orchestration logic, tool-use behavior, and harness design, while retaining strong benchmark performance and an application-level user experience.

Junhao Ruan, Yuan Ge, Bei Li +7

Northeastern University, China · LongCat RSI, Meituan · NiuTrans Research

Tool-Augmented Language Model Agents Software Engineering Agents LLM Agent Orchestration Tool-Using Agents LLM Agent Harnesses

Jul 13, 2026cs.SE

Inference Economics of Enterprise Coding Agents: A Case Study of Cloud vs. On-Premise LLMs

Autonomous coding agents force engineering organizations to choose between API-based frontier models -- strong reasoning at high token cost -- and on-premise quantized open-weights models, which promise low-marginal-cost scaling and data sovereignty at some loss of reasoning fidelity. We study this trade-off through a single-developer, non-randomized longitudinal case study over two contiguous 28-day periods on a production monorepo: an API-based Claude Opus 4.7/4.8 configuration using Claude Code versus an on-premise GLM-5.1/5.2 configuration using Opencode, quantized to NVFP4, on NVIDIA Blackwell hardware. Analyzing LLM telemetry and Git history, we find that prompt caching (99.3% hit rate) cuts realized API cost by 88.6% to an effective $0.57 per million tokens -- below even the $2.83 amortized unit cost of the shared on-premise slice (a utilization-dependent inversion; total realized spend and total cost of ownership (TCO) are the robust quantities). At comparable gross code churn, the local configuration was associated with a far higher defect-repair burden: a Fix Commit Ratio (FCR) of 74.9% versus 45.9%, with the odds of a commit being a repair 2.6 to 4.9 times higher within every difficulty tier (Mantel-Haenszel OR = 3.61). Under Taiwan-market parameters and a symmetric labor model, on-premise deployment nonetheless saves 40.1% of true TCO under shared GPU allocation, whereas dedicated reservation costs 43.8% more than the cached API. Under shared allocation, the genuine penalty is not monetary but a measurable developer-experience burden -- timestamp indicators show more work trapped in debugging spirals and a slower commit cadence -- and an offline replay shows hybrid routing gateways trade defect rate for infrastructure savings along a cost-quality frontier rather than dominate the pure-API baseline.

Sheng-Wei Peng, Yi-Hsun Lin, Yi-Pei Lee

Pegatron Corporation Taipei, Taiwan

LLM Serving Software Engineering Agents Cost-Aware Inference LLM Agent Reliability

Jul 12, 2026cs.SE

How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study

The rise of Software Engineering (SE) agents, i.e., LLM-based agents that can understand large codebases and carry out engineering tasks with limited human intervention, has been marked by rapid advances and adoption, but little is known about how developers build these systems in practice: existing studies mine repositories or examine deployment, but few investigate how SE agents are constructed. Through semi-structured interviews with 20 practitioners from 12 organizations and an online survey of 80 practitioners, this paper is the first to study how SE processes are changing in the development of SE agents and what challenges developers face. We find that as implementation becomes cheaper, bottlenecks shift rather than disappear: long-standing non-coding work such as requirements, coordination, review, and deployment becomes more visible, while reviewing and evaluating agent output becomes new and central. We characterize a seven-stage workflow and a shift toward evaluation-driven development, in which evaluation steers iteration and specifications become versioned artifacts read by both humans and agents. We further identify six challenges that teams face, together with the practices they adopt to address them, including unreliable evaluation signals, comprehension debt as code outpaces understanding, and behavioral changes introduced by provider-side model updates.

Yunbo Lyu, David Williams, Jieke Shi +5

Singapore Management University, Singapore · University College London, UK · Tencent, China +2

Software Engineering Agents LLM Agent Evaluation LLM Agents

Jul 10, 2026cs.SE

Do These Violent Delights Have Violent Ends? Measuring the Post-Merge Fate of Agentic Code

Agentic coding tools are increasingly used to make autonomous repository-level changes to real-world projects. Prior work has largely evaluated these contributions at the pre-merge stage, through outcomes such as pull request acceptance and review effort. Far less is known about what happens to agentic code post-merge. Yet merge success alone does not reveal whether a contribution will remain stable or require bug fixes and other corrective maintenance downstream. We conduct a longitudinal empirical analysis of agentic and human contributions across 182 repositories, tracking their post-merge fate over time, characterizing the intent of subsequent modifications, and analyzing the defects and vulnerabilities they introduce. While the overall maintenance rates are similar, agentic contributions require significantly higher rates of corrective maintenance and introduce more security weaknesses and dependency vulnerabilities. We also find statistically significant evidence that agentic maintenance burden is associated with repository characteristics. In particular, each 10 percentage-point increase in a project's no-review rate is associated with roughly a 6% increase in agentic maintenance burden on average. As coding agents become pervasive in software development, our findings highlight the need to evaluate and design agentic tools not only to produce mergeable changes, but to produce contributions that remain secure and maintainable.

Chunqiu Steven Xia, Courtney Miller

University of Illinois Urbana-Champaign · Urbana, IL, USA · George Washington University +1

Software Engineering Software Engineering Agents Software Security Agentic Code Generation

Jul 9, 2026cs.SE

Aleena: Alignment Agent for Research Software Engineering Collaborations

Research software collaborations span meetings, informal chats, pull requests, and GitHub issues. A decision surfaced in a Slack thread, refined in a meeting, and implemented in a pull request can lose its original rationale across these artifacts, leaving domain researchers and research software engineers with divergent mental models of project intent, ownership, and scientific assumptions. We argue that alignment in research software engineering is a continuous lifecycle problem, and that agentic AI can support stakeholder alignment and project-state tracking without replacing human decision-making. We present Aleena, an open-source lifecycle alignment agent that uses GitHub as a shared collaboration surface, transforming multi-modal stakeholder interactions into structured project records that surface risks, track open questions, and preserve decision continuity. Grounded in university-based research software engineering center experiences, this paper presents the motivating problem, system design, prototype, and illustrative lifecycle scenarios for Aleena.

Kshitij Dani, Cordero Core, Landung Setiawan +4

eScience Institute University of Washington Seattle, Washington, USA · eScience Institute University of Washington Seattle, Washington 많은 USA

Software Engineering Agents Human-AI Collaboration

Jul 7, 2026cs.SE

Reliable and Developer-Aligned Evaluation of Agents for Software Engineering

Large language models are rapidly moving towards closing the development cycle, transitioning from simple assistive companions to autonomous contributors deeply embedded into collaborative development environments. Despite their accelerated adoption, existing evaluation techniques are limited due to their fragmented nature and distorted projection of true model capabilities, often obtained from hypothetical syntactic scenarios. This research aims to bridge this gap by providing a comprehensive evaluation methodology for LLM-powered agents that is grounded in real-world software development practice. Our evaluation approach focuses on contamination-awareness, in-the-wild agentic behavior assessment, and trajectory-aware benchmarks and metrics capturing realistic coding contexts, human-aligned behavior, and model failure modes.

Razvan Mihai Popescu

Delft University of Technology Delft, The Netherlands

Software Engineering Agents LLM Agent Evaluation Agent Evaluation AI Agent Benchmarks LLM Agent Reliability

Jul 7, 2026cs.FL

Harnessing Code Agents for Automatic Software Verification

Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive theorem provers such as Coq require enormous expert effort. Large language models (LLMs) promise to generate these proofs automatically, yet existing approaches wire a fixed, human-designed proof strategy into the system and constrain the model to follow it (retrieving premises and predicting tactics one step at a time, or splitting goals by divide-and-conquer), and still prove only a fraction of their target theorems. We show that imposing such a strategy is unnecessary and limiting. Handing the whole lemma to a general LLM code agent (for example, Claude Code), free to choose its own approach, and wrapping it in a verification harness is both simpler and more effective, achieving full coverage: every targeted lemma proved, with no failures and no Coq expert intervention. The agent writes the proofs under feedback and hard constraints from the harness that keep each one sound (accepted only when the prover's kernel closes it), complete (no obligation left unproved or silently dropped), and terminating (no divergent tactics). We evaluate this harness plus code agent along three dimensions. (1) Core logic: on Iris, the state-of-the-art separation logic for concurrent and memory-manipulating programs, Aria proves all 4,257 lemmas of the four core modules and the 217 lemmas verifying Rust's standard libraries built on it, fully automatically. (2) Comparison with prior LLM provers: on reglang, where prior provers manage barely one in eight, Aria proves all 318. (3) Generality: on iris-lean, the unfinished Lean 4 port of Iris, it proves 72 not-yet-ported lemmas, showing the approach is not specific to Coq. A state-of-the-art model (Claude Opus 4.7) can write proofs for verified software development fully and automatically.

Shuangxiang Kan, Shuanglong Kan, Sebastian Ertel

Singapore Management University · Singapore · Barkhausen Institut +1

Software Engineering Agents Automated Theorem Proving Formal Verification LLM Agent Harnesses

Jul 6, 2026cs.SE

What Do AI Agents Actually Change? An Empirical Taxonomy of Mutation Patterns in Performance-Improving Pull Requests

AI coding agents are black boxes: we cannot inspect how they generate code, but we can inspect what they change. This distinction matters for search-based software engineering (SBSE), where techniques such as genetic improvement (in the performance-optimisation application we study) depend on mutation operators that reflect how code is actually transformed. Fewer than 1% of the 33,596 agent PRs in AIDev-pop target performance, making each case a rare window into otherwise opaque agent behaviour. We classify 1,254 performance-relevant diff hunks from 216 of these PRs, spanning five agent systems, against the 18-category syntactic mutation taxonomy of Even-Mendoza et al. (2025) using a dual-LLM intersection pipeline. Three categories dominate: name modification (37.0%), object creation (26.4%), and type change (22.7%), a profile markedly different from prior GI corpora where no change accounted for 84%. Each agent's deployed system commits to a distinctive mutation vocabulary, and each performance strategy activates a largely disjoint category subset. Agent identity and target strategy are therefore informative priors that narrow the effective SBSE operator space. Replication package: https://github.com/5uper6rain/ssbse-challenge-2026

Illia Dovhoshliubnyi, Nima Soroush, Ashkan Sami +1

Edinburgh Napier University, Edinburgh, UK · University of Stirling, Stirling, UK

Software Engineering Software Engineering Agents AI Coding Agents

Jul 6, 2026cs.LG

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents

Long-horizon agentic LLMs are increasingly limited by finite context windows, as extended interaction trajectories can exceed the maximum context length before a task is completed. Context compaction offers a natural solution by summarizing previous interaction states and continuing the rollout under a compressed context, but incorporating compaction into reinforcement learning remains underexplored. We propose CompactionRL, a reinforcement learning strategy to train long-horizon agentic LLMs with context compaction. Our approach jointly optimizes task execution and summary generation with token-level loss normalization and cross-segment generalized advantage estimation. This design enables the LLM agents to learn from compacted long-horizon trajectories. We train CompactionRL on top of open models and observe consistent performance gains on agentic coding tasks. CompactionRL enables the open GLM-4.5-Air model (106B-A12B) to achieve Pass@1 scores of 66.4% on SWE-bench Verified and 26.2% on Terminal-Bench 2.0, exceeding the base model under inference-time compaction by 6.6 and 4.9 points, respectively. Built upon GLM-4.7-Flash (30B-A3B), CompactionRL improves Pass@1 by 5.5 and 6.7 points against the base model, reaching 56.0% on SWE-bench Verified and 20.2% on Terminal-Bench 2.0. CompactionRL is thus deployed in the RL pipeline for training the open GLM-5.2 model (750B-A40B).

Yujiang Li, Zhenyu Hou, Yi Jing +2

Work done while YL, ZH, and YJ interned at Z.AI. · Tsinghua University

Software Engineering Agents Long-Horizon LLM Agents RL for LLM Agents Context Compression

Jul 6, 2026cs.SE

KAT-Coder-V2.5 Technical Report

We present KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real, executable repositories rather than as a single-turn code generator. Its capability is bottlenecked less by model scale than by the scarcity of reproducible environments, verifiable rewards, and high-value trajectories, which we address with an end-to-end agentic post-training framework. AutoBuilder reconstructs multilingual repositories into sandboxed environments with fail-to-pass and pass-to-pass verification at scale, from which we regenerate self-contained task specifications, recover near-miss trajectories, and distill supervision through process-aware filtering, while KwaiClawEnv synthesizes large-scale tool-use trajectories from executable services and real task seeds. We further scale reinforcement learning with harness randomization, a reliability-hardened sandbox, an asymmetric actor--critic PPO with hindsight-augmented value estimation, and a harness-oriented reward framework, and unify SWE, Agent-Claw, and WebCoding experts via Multi-Teacher On-Policy Distillation. Across six software-engineering and agentic benchmarks, KAT-Coder-V2.5 delivers the best agentic tool-use result on PinchBench and ranks second only to the frontier Opus 4.8 on repository-level software engineering. Our service is available at https://streamlake.com/product/kat-coder.

Bo Huang, Fengxiang Li, Hao Xu +50

RL for Code Generation Software Engineering Agents Agentic Code Generation Repository-Level Code Generation RL for Tool Use

Jul 5, 2026cs.AI

Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents

Software-agent benchmarks usually report whether an agent solves a task, but the agent reaches that outcome through a harness that controls what it sees, which actions it can take, which failures are repaired, which states are verified, and which evidence is logged. We show that this harness can change the agent's multi-step beliefs even when the task, environment, and base LLM are fixed. We introduce a belief-rollout diagnostic that elicits structured K-step trajectories over progress, risk, recoverability, constraints, failure mode, uncertainty, future success, repair cost, and next action under alternative harnesses. We define a cross-harness belief divergence and decompose it into an arrival term for immediate interface shifts and a growth term for horizon-dependent belief changes. On controlled coding tasks and public-benchmark stress tests, blocked actions, compressed repairs, selective verification, and cost-aware evidence pruning often preserve terminal success while changing the beliefs that drive later decisions. We further introduce BIWM, a no-training protocol that canonicalizes observations, logs censored branches, expands repair traces, records verification masks, executes risky branches in shadow, and aligns belief trajectories across harness views. The results suggest that harness design is an experimental variable in agent evaluation, not an implementation detail. Our code is available at https://github.com/Hik289/Harness-induce-bias.git.

Haiwen Yi, Xinyuan Song

University of Toronto · Emory University

Software Engineering Agents LLM Agent Evaluation Long-Horizon Agent Evaluation LLM Agent Harnesses