PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit

Viral Patel; Boyin Tan; Jason Xue; Youcheng Sun

cs.SEOct 21, 2026

PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit

Authors: Viral Patel, Boyin Tan, Jason Xue, Youcheng Sun

Organizations: Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

Abstract

Coding agents can invest substantial effort in repository exploration and testing yet still produce unsuccessful patches. Existing online steering methods review trajectories periodically or invoke an advisor when a monitor detects behavioral problems; frequent reviews are costly, and the absence of anomalous behavior does not mean that an agent is on the right track. We propose PAUSE, a framework for steering coding agents with a single planning intervention. Agents reach their first source-code edit at a median of 60% of trajectory progress, after exploration, bug reproduction, and testing. PAUSE intercepts this edit request before it executes, which requires no learned monitor, no search over checkpoints, and no extra model call (search-free). A separate Planner reads the task and the pre-edit transcript and writes one repair plan; the same agent, the Executor, resumes with this plan, keeping its context and workspace. PAUSE applies online, during a live run, and offline, from a recorded trajectory prefix. We evaluate PAUSE on SWE-bench Verified and SWE-bench Multilingual with two Executors and three agent harnesses. With Qwen3-coder as Executor and GPT-5.6 Sol as Planner, online steering improves resolution by 16.8% on Verified in OpenHands and by 14.7% on Multilingual in SWE-agent. In SWE-agent, PAUSE outperforms LivePlan, a rule-triggered advisor, by 3.2% on Verified and 3.7% on Multilingual at similar Planner cost, and is comparable to SICA's periodic overseer at about 11-15% of its Planner cost. Offline, PAUSE recovers 35.4% of eligible failed Verified tasks, and resuming from the recorded prefix uses 33-41% fewer Executor tokens than restarting.

Figures & tables

Method	Trigger	Timing model call	Needs detected problem	Interventions
SWE-PRM ( Gandhi et al., 2025b )	Fixed step interval	Yes	Yes	Repeated
SICA ( Robeyns et al., 2025 )	Overseer-chosen interval	Yes	Yes	Repeated
LivePlan ( Liu et al., 2026b )	Rule-detected anomaly	No	Yes	Repeated
PAUSE (Ours)	First source-code edit	No	No	One

Table 1. Online steering methods compared by how they decide when to guide. Trigger : the event that starts an intervention. Timing model call : whether a model must be called to decide when to intervene. Needs detected problem : whether guidance is given only after a problem in the trajectory is detected. Interventions : how many times guidance is inserted into a single run.

Figure 1. Actions in 500 Qwen3-coder runs on SWE-bench Verified. The curve marks first source-code edits (median 60.0%); 24 runs without one lie below the divider. A heatmap of 500 trajectories over normalized action progress from 0 to 100 percent. Yellow denotes think actions, blue file reads, green shell commands, red file-editor actions, and gray other or finish actions. The first 476 rows are sorted by their first source-code edit, traced by a black curve; a marker on the top edge labels their median position, 60.0 percent. The final 24 rows have no source-code edit and appear below a horizontal divider.

Figure 2. Overview of PAUSE . The Executor investigates the repository by reading code, writing scratch scripts, and running them. When the Executor issues its first source-code edit, PAUSE blocks the request and passes the task and the observed evidence to the Planner. The Planner returns one repair plan, which PAUSE appends to the Executor’s conversation, and the same Executor resumes with its context and workspace preserved. A reconstructed coding trajectory with small tool windows, bold action borders, and ellipses between representative investigation steps. Source reads and a scratch reproduction show that successive evaluations using the same cross-validation generator obtain two folds and then zero folds. Candidate scoring in the sequential feature selector repeatedly passes the original cv object through validation and splitter normalization. PAUSE blocks the first source-code edit. A lavender Planner panel combines these observations into a plan to normalize CV once per fit and propagate the reusable splitter to each candidate. A purple arrow appends the plan to context; the same Executor edits the sequential feature selector and checks that both evaluations retain two folds. The displayed fold counts come from local execution of the actual splitter functions.

Component or setting	Configuration
Executors	Temperature 0; top- $p$ 1; 4,096 output tokens
Executor context	262,144 tokens (Qwen3-coder); 131,072 (Devstral-small)
PAUSE API Planners, default	Temperature 0; 8,192 output tokens
Qwen3-30B-Thinking Planner	Temperature 0.99; top- $p$ 0.95; seed 0; 81,920 output tokens
LivePlan advisor	Temperature 0; 3,000 output tokens
SICA overseer	Temperature 0; 8,192 output tokens

Table 2. Decoding settings and execution budgets.

Method	Planner	Resolved	Resolution (%)	Tokens (M)		Cost ($)
Method	Planner	Resolved	Resolution (%)	Planner	Executor	Cost ($)
SWE-bench Verified, 500 tasks
Baseline	–	251/500	50.2	0	595.5	0
LivePlan ( Liu et al., 2026b )	GPT-5.6 Sol	309/500	61.8 ( +11.6 )	9.2	561.9	26.10
SICA overseer ( Robeyns et al., 2025 )	GPT-5.6 Sol	338/500	67.6 ( +17.4 )	80.9	1056.4	231.71
PAUSE	GPT-5.6 Sol	325/500	65.0 ( +14.8 )	9.0	564.2	26.13

Table 3. Steering compared with monitoring-based methods. Qwen3-coder Executor and GPT-5.6 Sol Planner in SWE-agent on all 500 SWE-bench Verified and all 300 SWE-bench Multilingual tasks. Resolution : resolved tasks over the full benchmark, with the gain over each block’s baseline. Tokens are in millions; Cost covers Planner inference only.

Intervention	Qwen3-coder Executor	Devstral-small Executor
N: no plan	9/223 (4.0%)	14/174 (8.0%)
S: self-reconsideration	13/223 (5.8%)	17/174 (9.8%)
P: Executor Model	12/223 (5.4%)	20/174 (11.5%)
P: Gemini 3.5 Flash Lite	22/223 (9.9%)	12/174 (6.9%)
P: Gemini 3.8 Flash	31/223 (13.9%)	29/174 (16.7%)
P: GPT-5.6 Sol	79/223 (35.4%)	53/174 (30.5%)

Table 4. Offline recovery in OpenHands on SWE-bench Verified across Executors. Each failed trajectory resumes from its restored checkpoint, the last think before the first source-code edit, with its remaining budget. Recovered reports solved eligible failures: 223 for Qwen3-coder and 174 for Devstral-small. N: no plan; S: self-reconsideration; P: plan from the named Planner.

Method	Planner	Resolved	Resolution (%)	Tokens (M)		Cost ($)
Method	Planner	Resolved	Resolution (%)	Planner	Executor	Cost ($)
Baseline	–	228/500	45.6	0	791.9	0
SHERLOC ( Tamoyan et al., 2026 )	Qwen3-30B-Thinking	211/500	42.2 ( $-$ 3.4)	65.7	703.9	0
PAUSE (restart)	Qwen3-30B-Thinking	207/500	41.4 ( $-$ 4.2)	16.0	641.6	0
PAUSE (resume)	Qwen3-30B-Thinking	217/500	43.4 ( $-$ 2.2)	14.5	375.7	0
PAUSE (restart)	GPT-5.6 Sol	293/500	58.6 ( +13.0 )	8.7	519.1	25.75

Table 5. Full-benchmark offline evaluation on SWE-bench Verified. Qwen3-coder in OpenHands, 500 tasks. Resume retains history and workspace with the remaining budget; restart uses the same plan from the initial repository with the full budget. Resume counts add recoveries to original successes and subtract observed regressions. Tokens (M) exclude the original run for continuations; costs cover Planner inference.

Harness	Method	Resolved	Resolution (%)	Tokens (M)		Cost ($)
Harness	Method	Resolved	Resolution (%)	Planner	Executor	Cost ($)
SWE-agent no think tool	Baseline	251/500	50.2	0	595.5	0
SWE-agent no think tool	PAUSE	325/500	65.0 ( +14.8 )	9.0	564.2	26.13
Pi no think tool	Baseline	185/500	37.0	0	341.9	0
Pi no think tool	PAUSE	215/500	43.0 ( +6.0 )	6.7	358.8	18.57
OpenHands think tool	Baseline	227/500	45.4	0	372.5	0

Table 6. Transfer across agent harnesses. Online PAUSE with Qwen3-coder Executor and GPT-5.6 Sol Planner on 500 Verified tasks. Think stripped hides think content from the Planner; units follow Table 3 .

Pause position	Common	Paired with PAUSE
Pause position	Resolved (%)	Tasks	Arm (%)	PAUSE (%)	Only arm / PAUSE	$p$
PAUSE checkpoint	56/161 (34.8)	–	–	–	–	–
After 20% of actions	43/161 (26.7)	207	27.5	32.9	15 / 26	0.12
Immediately before the edit	50/161 (31.1)	196	30.1	33.2	14 / 20	0.39
After 90% of actions	50/161 (31.1)	167	32.3	34.7	16 / 20	0.62

Table 7. Recovery under different pause positions on SWE-bench Verified. Each arm restores its own prefix of the same recorded failures and obtains its own GPT-5.6 Sol plan. Common : the 161 tasks graded in every arm. Paired : each arm against the PAUSE checkpoint on their largest shared set, with the tasks solved only by the arm or only by PAUSE and the exact McNemar

p

-value.

Coding Agents

Coding agents use language models, tools, and feedback to modify software and complete engineering tasks.

See all 139 papers

Teaching Agents to Code Reliably
Oct 2, 2026Muhammad Ahmed Mohsin, Myeongsoo Kim, Kangrui Ruan +3Repository-Level Program Repair AI Coding Agents
Stanford University · AWS AI Labs
Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
Mar 25, 2026Myeongsoo Kim, Dingmin Wang, Siwei Cui +6Agent Failure Analysis AI Coding Agents
AWS AI Labs · Monash University
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
Mar 3, 2026Guoxin Chen, Fanzhe Meng, Jiale Zhao +12Retrieval-Augmented Code Generation Software Engineering Benchmarks

Oct 2, 2026J/K move · Enter open · S save

Teaching Agents to Code Reliably

Muhammad Ahmed Mohsin, Myeongsoo Kim, Kangrui Ruan, Shweta Garg+2

Stanford University · AWS AI Labs

Repository-Level Program Repair AI Coding Agents LLM Agent Reliability Automated Program Repair Reinforcement Learning with Verifiable Rewards

Open paper AskPDF arXiv

Autonomous coding agents solve repository issues by reading code, running commands, editing files, and submitting patches. Extra inference-time compute yields gains only when it produces a useful repair and supplies reliable evidence for choosing one. Three behaviors decide both, and we argue they are teachable rather than byproducts of scale, so a policy can carry them instead of a scaffold. Location diversity remains narrow, since attempts return to the same site and extra samples add no coverage. Edit diversity is left unexploited, since methodologies that differ resolve complementary issues no single run reaches. Verification misleads, since a test the agent writes for its own patch accepts many incorrect ones. Directing search by execution feedback and scoring each patch against its own reverted tree resolves 52.8% of SWE-bench Verified using 48.1% of the agent-steps an eight-sample baseline spends. Training moves these behaviors into the policy. On the 270 issues held out from SFT and RL training, weighted supervised fine-tuning raises pass@1 from 31.9% to 35.2% and pass@8 from 46.7% to 51.1%. A reinforcement objective then trains the verifier against gold-labeled repairs and incorrect variants, crediting the assertions that detect them. It raises pass@1 to 43.0% and pass@8 to 60.7%, lifts verifier precision from 26.8% to 41.7%, and more than halves false acceptance. Resolution improves on two of three out-of-distribution suites and verifier precision on all three, and the gains hold at 7B, 14B, and 30B against published coder baselines.

Abstract

Coding Agents

Explore similar work

Teaching Agents to Code Reliably

Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?