PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces

M. Yigit Turali; Shreyas Rajesh; M. Efe Lorasdagi; Chenda Duan; Kartik Sharma; Vwani Roychowdhury

cs.CLOct 10, 2026

PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces

Authors: M. Yigit Turali, Shreyas Rajesh, M. Efe Lorasdagi, Chenda Duan, Kartik Sharma, Vwani Roychowdhury

Organizations: University of California, Los Angeles

Abstract

Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. As investigations grow, agents must maintain research state across model calls and check findings before errors propagate into subsequent work. We introduce PANINI-DR, a multi-agent harness that separates coordination of the overall investigation from the research and verification of individual subquestions. A shared workspace, built on the Generative Semantic Workspace representation, records subquestions, their dependencies, findings, and supporting evidence. Researchers investigate individual subquestions, while a separate verification agent checks proposed answers against those subquestions and their evidence. Verification feedback guides further investigation, and recorded findings inform subsequent assignments. We evaluate PANINI-DR on BrowseComp-Plus, FRAMES, and MoNaCo against seven state-of-the-art deep-research harnesses, all using a shared language-model backbone and frozen corpora. PANINI-DR achieves the strongest average performance across the three benchmarks. On BrowseComp-Plus, it achieves 73.3% accuracy, outperforming the next-best harness by 16.0 points. Its advantage is strongest on hard questions, where it answers nearly twice as many as the next-best harness. Ablations further show that structured planning and persistent state improve performance, as does checking each finding against its cited evidence before it is reused. Because a model can answer correctly from memory alone, we also analyze the evidence retained by each harness. PANINI-DR achieves the highest answer recoverability from saved evidence on all three benchmarks, while complementary claim-support audits show stronger evidence-backed answers. Accounting for this evidence changes how harnesses compare and further strengthens PANINI-DR's advantage.

Figures & tables

Figure 1: PANINI-DR illustrated on a sample query. The schematic stages separate the subquestions for explanation, rather than reproduce the recorded dispatch timing. Each $W_{k}=(P,S_{k})$ pairs the plan with per-node research records; $\varnothing$ denotes that no findings have yet been recorded. Dark green marks additions, dashed boxes remain unresolved, and orange outlines indicate readiness. The expanded stage shows each Researcher’s initial retrieval step (labelled “typed resolver”) and, when needed, ReAct agent, followed by verification and admission; the Reagan rejection is hypothetical. Findings supply subsequent subquestions and the date calculation that produces 51. The recorded execution investigated all four factual subquestions in one dispatch.

	BCP CF-150				FRAMES	MoNaCo	Avg.
Method	Easy	Med.	Hard	Overall	Accuracy	F1
PyRAG	56	20	6	27.3	61.9	0.446	44.6
Re-TRAC	70	32	16	39.3	64.9	0.544	52.9
Omni-Decision	84	48	10	47.3	64.6	0.359	49.3
HyMem	82	52	12	48.7	70.8	0.612	60.2
Open Deep Search	82	50	28	53.3	76.0	0.571	62.1

Table 1: Official accuracy (%) on BCP and FRAMES and mean F1 on MoNaCo. Avg. equally weights BCP Overall, FRAMES, and MoNaCo, with F1 rescaled to 0–100. BCP groups contain 50 questions each. Bold: best; underline: second best, including ties.

Method	BCP	FRAMES	MoNaCo	Avg.
PyRAG	26.0	46.6	0.332	35.3
Re-TRAC	14.0	46.1	0.396	33.2
Omni-Decision	45.3	53.9	0.275	42.2
HyMem	46.7	36.7	0.388	40.7
Open Deep Search	51.3	47.6	0.325	43.8
IterResearch	51.3	45.9	0.390	45.4

Table 2: Observed support (Obs.): official answer credit recoverable from saved evidence, as defined in Section 3.2 . BCP and FRAMES report percentages; MoNaCo reports mean F1. Avg. equally weights the three benchmarks, with F1 rescaled to 0–100. Best scores are bold; second-best scores are underlined, including ties.

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

System	Protocol
PyRAG	1 executable retrieval program; no read tool.
Re-TRAC	8 recursive search cycles, each compressed into the next cycle’s starting state.
IterResearch	25 turns; sampling temperature is hard-coded at 0.6.
Omni-Decision	15 iterations behind an evidence-state readiness gate.
Open Deep Search	15 CodeAct steps; search returns model-written summaries.
SLEUTH	Published default of 20 turns and retrieval top- $k=3$ ; maintains ranked hypotheses.

Appendix

Table 3: Baseline protocols used for the reported runs.

System	Primary grader	Second grader	$\Delta$	Agreement	$\kappa$
PANINI-DR (cap 5)	110 (73.3)	111 (74.0)	$+0.7$	99.3	0.983
SLEUTH	86 (57.3)	86 (57.3)	$0.0$	100	1.000
HyMem	73 (48.7)	73 (48.7)	$0.0$	100	1.000
Omni-Decision	71 (47.3)	71 (47.3)	$0.0$	100	1.000
Re-TRAC	59 (39.3)	59 (39.3)	$0.0$	100	1.000

Appendix

Table 4: Grader sensitivity on BCP CF-150 (150 questions): gpt-5.6-luna (primary) versus gpt-5.6-terra , with the same answers, official prompt, and 3-pass majority. Scores are correct-answer counts with accuracy (%) in parentheses;

\Delta

is in percentage points. Agreement is the percentage of matching verdicts;

\kappa

is Cohen’s kappa.

Method	BCP-150	FRAMES-824	MoNaCo-1315
	Accuracy (%)	Accuracy (%)	Mean-F1
HyMem	48.0	43.6	0.352
SLEUTH	55.3	67.1	0.417
PANINI-DR	72.0	73.2	0.443

Appendix

Table 5: Answer quality after a common model auditor filters unsupported claims. Rebuilt answers are re-graded under each benchmark’s official protocol. Every question is included, with empty answers scoring zero. Bold marks the best score.

	BCP-150 (%)		FRAMES-824 (%)		MoNaCo-1315 (F1)
Evidence source	Present	Uncertain	Present	Uncertain	Present	Uncertain
PANINI-DR	72.0	62.7	76.7	69.4	0.601	0.547
SLEUTH	59.3	53.3	70.0	59.3	0.506	0.476
HyMem	54.7	50.0	52.2	43.9	0.470	0.419
Omni-Decision	58.7	55.3	71.2	62.5	0.538	0.515

Appendix

Table 6: Answer quality of a common evaluation reader using each system’s saved evidence. Present assumes the answer is available; Uncertain allows abstention. All questions are included; empty answers score zero. Bold marks the best score.

	FRAMES-824	MoNaCo-1315
Arithmetic/Boolean target records	192	335
Passing calculations	118	184
Answers receiving additional credit	51	55
Obs.	66.1	0.458
Obs-D	72.3	0.498

Appendix

Table 7: PANINI-DR -only calculation audit. FRAMES scores are percentages; MoNaCo scores are mean-F1. All questions remain in the denominator. Only official credit not already retained by Obs. is added.

Benchmark	$n$	Found recall	Cited recall	Cited precision (%)
BCP	150	.860 / .455	.485 / .248	43.3 / 37.0
FRAMES	823	.945 / .820	.774 / .586	91.9 / 84.4
MoNaCo	1,315	.515 / .368	.281 / .250	73.3 / 67.0

Appendix

Table 8: Source coverage: PANINI-DR / SLEUTH. Recall is the fraction of annotated pages found or recorded as support; precision is the annotated share of support pages. Values average per-question fractions, with zero precision when no citation is recorded. Source measures omit one FRAMES question without annotations; answer scores retain all 824. SLEUTH source titles are normalized and matched to recorded pages.

Benchmark	Recovery answers	Official	Obs.
BCP	60	66.7	63.3
FRAMES	103	60.2	52.4
MoNaCo	250	0.430	0.358

Appendix

Table 9: Scores over all identified recovery answers, including incorrect ones: percentages on BCP/FRAMES and mean F1 on MoNaCo. Finalizer outputs number 50/89/241 and stored-candidate fallback outputs 10/14/9, respectively. One additional MoNaCo output has an unclassified origin.

	BCP				FRAMES	MoNaCo
	Easy	Med.	Hard	All	Acc.	F1
PANINI-DR	92	76	52	73.3	79.1	0.549
Annotated-source reference	96	94	90	93.3	79.5	0.550

Appendix

Table 10: Official scores with research or supplied sources: accuracy (%) on BCP/FRAMES and mean F1 on MoNaCo. Denominators are 150/824/1,315; each BCP difficulty group contains 50 questions.

Arm	Official	Obs.	Official	Obs.	All roles, mean
	Recovery off		Recovery on		Prompt (M)
Off : prose memory	41.3	39.3	56.7	53.3	1.38
On : planning/state	58.0	56.0	73.3	68.7	1.78
Full system	46.7	45.3	73.3	70.7	1.43

Appendix

Table 11: Planning/state and common-recovery controls on all 150 BCP questions; scores are percentages. Prompt means cover the recorded reference runs: they exclude post-hoc Finalizer calls on the controlled arms and include live recovery in the full system. Full-system rows restore multiple components and are not isolated planning/state controls.

Benchmark	Verification	Official	Obs.	Prompt (k)
BCP (150)	On	73.3	70.7	1,042
	Off	57.3	54.7	453
FRAMES (200)	On	79.5	69.0	125
	Off	69.5	57.0	35
MoNaCo (200)	On	0.583	0.479	288
	Off	0.517	0.412	47

Appendix

Table 12: Verification ablation on matched questions. Off removes LLM review and source-evidence checks but retains assignment and type checks. Scores are percentages on BCP/FRAMES and mean F1 on MoNaCo. Prompt use is the per-question median in thousands, using trajectory accounting.

Cap	Acc.	Obs.	Hard / 50	Warned / resolved	Prompt (M)
1	67.3	65.3	19	128 / 773	1.249 (0.817)
2	72.0	68.7	23	27 / 636	1.147 (0.854)
5	73.3	70.7	26	2 / 666	1.200 (1.042)
10	66.0	63.3	20	0 / 673	1.317 (1.115)

Appendix

Table 13: Shared review-cap sensitivity on BCP CF-150. Accuracy and Obs. are percentages; Hard counts correct answers out of 50. Warning counts use resolved bindings in the final workspace snapshots, including computed bindings. Prompt use is the per-question mean in millions, with the median in parentheses, using the trajectory accounting in Table 14 . These are benchmark averages for the supplied executions, not averages across research repetitions.

Method	Prompt (M)	Completion (k)
PyRAG	0.002 (0.017)	3.2 (6.5)
SLEUTH	0.037 (0.074)	2.3 (7.3)
Open Deep Search	0.10 (0.11)	10.0 (10.9)
Omni-Decision	0.13 (0.16)	9.0 (10.1)
IterResearch	0.17 (0.17)	9.8 (10.6)
HyMem	0.29 (0.31)	51.0 (65.9)

Appendix

Table 14: BCP CF-150 token use: per-question medians (means), with prompt tokens in millions and completion in thousands. All rows use gpt-oss-120b . Counting details appear in Appendix D.3.1 .

Selected roles: mean prompt tokens per question, k (share of role sum)
	BCP	FRAMES	MoNaCo
Questions	150	824	1,315
Reported trajectory prompt total (M)	180.04	270.38	775.12
Sum of 10 recorded roles (M prompt tokens)	213.94	340.79	1,040.13
Role sum / trajectory total	1.188	1.260	1.342
Orchestrator	58.4 (4.1%)	23.1 (5.6%)	32.8 (4.1%)

Appendix

Table 15: PANINI-DR cap-5 role accounting from saved traces. Role telemetry covers every question; shares use summed role prompt tokens across all 10 roles, including the 6 not listed individually. ReAct denotes the Researcher’s second stage, excluding the typed resolver. k and M denote thousands and millions of tokens. Combined shares use unrounded counts. Table 14 instead reports trajectory totals.

Harness	Input (k)	Cache (%)	Uncached (k)	Generated (k)	PFLOP
PANINI-DR	1,422	66.5	477	78	5.68
SLEUTH	74	7.3	69	7	0.78
Omni-Decision	157	7.1	146	10	1.59
HyMem	309	45.0	170	66	2.41

Appendix

Table 16: Engine measurements over all 150 BCP questions. Tokens and analytically estimated model-core PFLOPs are per-question means; cache percentage is the share of submitted input reused.

Runs	PFLOP/q	vs. ours	Vote acc.	Any correct	Vote Obs.
1	0.76	0.13	61.3	61.3	58.7
2	1.66	0.29	62.0	66.0	59.3
4	3.22	0.57	63.3	69.3	60.7
6	4.79	0.84	64.7	69.3	61.3
7	5.51	0.97	65.3	70.0	62.7
8	6.34	1.12	64.7	70.0	62.0

Appendix

Table 17: Repeated SLEUTH research runs on all 150 BCP questions at cumulative model-core computation. Vote selects the most frequent non-empty answer; “Any correct” credits a question if at least one run answers correctly. Scores are percentages. Individual runs average 55.5% accuracy versus the greedy reference’s 57.3%.

Allowance	Accuracy	Obs.	Mean prompt (M)	Empty
PANINI-DR : turns per Researcher, review cap 5
20 (default)	73.3	70.7	1.20	4
50	74.7	71.3	2.54	2
80	76.0	74.0	3.33	6
PANINI-DR : shared question budget, review cap 5
20	31.3	28.7	0.115	71

Appendix

Table 18: Separate allowance sweeps on all 150 BCP questions, including unanswered cases. Scores are percentages; prompt means use trajectory accounting. Turn limits govern different activity across panels and are not matched computation. Each row is a separate execution, not a continuation of the shorter run.

Method	Table 1	Run 2	Run 3	Mean $\pm$ SD	Mean (%)
PANINI-DR	110	107	110	$\mathbf{109.0\pm 1.7}$	72.7
SLEUTH	86	91	84	$87.0\pm 3.6$	58.0
Open Deep Search	80	88	93	$87.0\pm 6.6$	58.0
IterResearch	82	83	80	$81.7\pm 1.5$	54.4
HyMem	73	73	74	$73.3\pm 0.6$	48.9
Omni-Decision	71	68	59	$66.0\pm 6.2$	44.0

Appendix

Table 19: BCP stability across three research runs per method, each on the same 150 questions under the headline settings. Run columns and mean

\pm

sample SD count correct answers; the final column converts the mean count to accuracy. The first run is the one reported in Table 1 .

	Single item (720)		Collection (595)
Harness	F1	Obs.	P	R	F1	Obs.
PANINI-DR	0.593	0.446	0.690	0.462	0.495	0.474
SLEUTH	0.579	0.338	0.678	0.503	0.528	0.467
Open Deep Search	0.598	0.269	0.652	0.519	0.538	0.394
IterResearch	0.583	0.317	0.617	0.546	0.540	0.479
Omni-Decision	0.410	0.282	0.399	0.281	0.298	0.267

Appendix

Table 20: MoNaCo answer structure for the main-table executions. Columns average over all questions in each group using the same maximum-F1 pass. Mean F1 is not the harmonic mean of aggregate precision and recall. Bold marks the largest value.

			Official		Obs.
Dataset	Comparator	$n$	$\Delta$	95% CI	$\Delta$	95% CI
Headline comparisons: PANINI-DR (cap 5) minus baseline
BCP	SLEUTH	150	$+16.0$	$[+8.0,+24.0]$	$+16.7$	$[+8.7,+24.7]$
FRAMES	SLEUTH	824	$+1.9$	$[-1.0,+4.9]$	$+10.9$	$[+7.8,+14.1]$
MoNaCo	SLEUTH	1,315	$-0.007$	$[-0.029,+0.015]$	$+0.062$	$[+0.041,+0.083]$
BCP	HyMem	150	$+24.7$	$[+16.0,+34.0]$	$+24.0$	$[+14.7,+32.7]$

Appendix

Table 21: Paired score differences on the matched question sets, with bootstrap 95% confidence intervals from 10,000 resamples paired by question. Positive differences favor the first-named arm in each subtraction. Values are percentage points on BCP and FRAMES and mean-F1 units on MoNaCo;

n

is the number of matched questions. Differences use unrounded scores. Each comparison resamples the same question set in both arms, so an interval describes the difference rather than either score separately.

System	Implementation or adaptation
SLEUTH	Paper/prompt-based: published reasoning, memory, commitment, and top-3 retrieval rules; dense and BM25 routes.
Omni-Decision	Paper-based: 15 iterations, top-6 retrieval, zero-novelty termination after 3 iterations.
HyMem	Paper-based: 4 tools, published tool wording, and per-layer budgets.
Open Deep Search	Released code: search timeout raised from 10 to 300 s; local-link gateway.
PyRAG	Output limit raised from 1,024 to 4,096 tokens; JSON-schema output.
IterResearch	Endpoint/return-value compatibility; assistant prefill, XML repair, JSON lift, action seeding, answer extraction; authors’ hard-coded temperature 0.6.

Appendix

Table 22: Baseline implementations and changes for the shared evaluation environment. Model-facing changes are listed separately from interface compatibility within each row.

Deep Research Agents

Deep research agents plan long-horizon searches, synthesize cited evidence, and produce reports for complex open-ended questions.

See all 115 papers

Argus: Evidence Assembly for Scalable Deep Research Agents
May 15, 2026Zhen Zhang, Liangcai Su, Zhuo Chen +7Multi-Agent LLM Systems Tool-Augmented Language Model Agents
MiroMind AI
Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
Mar 30, 2026Bin Zhu, Qianghuai Jia, Tian Lan +6Deep Research Agents LLM Agent Training
Alibaba International Digital Commerce
DeepResearch Bench II: Diagnosing Deep Research Agents via Rubrics from Expert Reports
Jan 13, 2026Ruizhe Li, Mingxuan Du, Benfeng Xu +3Deep Research Agents LLM Agent Evaluation
University of Science and Technology of China · Metastone Technology, Beijing, China

May 15, 2026J/K move · Enter open · S save

Argus: Evidence Assembly for Scalable Deep Research Agents

Zhen Zhang, Liangcai Su, Zhuo Chen, Xiang Lin+6

MiroMind AI

Multi-Agent LLM Systems Tool-Augmented Language Model Agents Deep Research Agents Agentic Search Agentic Reasoning

Open paper AskPDF arXiv

Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of the art systems scale inference time compute via parallel search and aggregation. Yet deep research answers are composed of complementary pieces of evidence, which parallel rollouts often duplicate rather than complete, yielding diminishing returns while pushing the aggregation context toward the model's limit. We propose Argus, an agentic system in which a Searcher and a Navigator cooperate to treat deep research as assembling a jigsaw from complementary evidence pieces, rather than brute forcing the whole answer in parallel. The Searcher collects evidence traces for a given sub-query through ReAct-style interaction. The Navigator maintains a shared evidence graph, verifying which pieces are still missing, dispatching Searchers to gather them, and reasoning over the completed graph to produce a source-traced final answer. We train the Navigator with reinforcement learning to verify, dispatch, and synthesize, while independently training the Searcher to remain a standard ReAct agent. The resulting Navigator supports rollouts with a single Searcher or many in parallel without retraining. With both Searcher and Navigator built on a 35B-A3B MoE backbone, Argus gains 5.5 points with a single Searcher and 12.7 points with 8 parallel Searchers, averaged over eight benchmarks. With 64 Searchers it reaches 86.2 on BrowseComp, surpassing every proprietary agent we benchmark, while the Navigator's reasoning context stays under 21.5K tokens.

Abstract

Deep Research Agents

Explore similar work

Argus: Evidence Assembly for Scalable Deep Research Agents

Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

DeepResearch Bench II: Diagnosing Deep Research Agents via Rubrics from Expert Reports