Papers › HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning

HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning

19 Mar 2024arXiv:2403.12884archive 2025-07-28

Fucai Ke, Zhixi Cai, Simindokht Jahangard, Weiqing Wang, Pari Delir Haghighi, Hamid Rezatofighi

Recent advances in visual reasoning (VR), particularly with the aid of Large Vision-Language Models (VLMs), show promise but require access to large-scale datasets and face challenges such as high computational costs and limited generalization capabilities. Compositional visual reasoning approaches have emerged as effective strategies; however, they heavily rely on the commonsense knowledge encoded in Large Language Models (LLMs) to perform planning, reasoning, or both, without considering the effect of their decisions on the visual reasoning process, which can lead to errors or failed procedures. To address these challenges, we introduce HYDRA, a multi-stage dynamic compositional visual reasoning framework designed for reliable and incrementally progressive general reasoning. HYDRA integrates three essential modules: a planner, a Reinforcement Learning (RL) agent serving as a cognitive controller, and a reasoner. The planner and reasoner modules utilize an LLM to generate instruction samples and executable code from the selected instruction, respectively, while the RL agent dynamically interacts with these modules, making high-level decisions on selection of the best instruction sample given information from the historical state stored through a feedback loop. This adaptable design enables HYDRA to adjust its actions based on previous feedback received during the reasoning process, leading to more reliable reasoning outputs and ultimately enhancing its overall effectiveness. Our framework demonstrates state-of-the-art performance in various VR tasks on four different widely-used datasets.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2403.12884")

Code

Syntology Ran 5 of 8 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ControlNet/HYDRA officialmentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 5 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5ran
3unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ControlNet/HYDRA. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

batch_iou_2d ControlNet/HYDRA/hydra_vl4ai/evaluation/grounding_eval.py official repository ran Apache-2.0 (permissive) · b3ea2529810e5202 · report
general_postprocessing ControlNet/HYDRA/hydra_vl4ai/evaluation/vqa_eval.py official repository ran Apache-2.0 (permissive) · b71b988c6ecd556e · report
iou_2d ControlNet/HYDRA/hydra_vl4ai/evaluation/grounding_eval.py official repository ran fingerprinted Apache-2.0 (permissive) · ab3ed2da520c8d12 · report
parse_model_name ControlNet/HYDRA/hydra_vl4ai/agent/llm.py official repository ran Apache-2.0 (permissive) · f1ab9565c1d4addd · report
process_grounding_result ControlNet/HYDRA/hydra_vl4ai/evaluation/grounding_eval.py official repository ran Apache-2.0 (permissive) · fa3e3e36130c45c0 · report
handle_ollama_exceptions ControlNet/HYDRA/hydra_vl4ai/agent/llm.py official repository unverified Apache-2.0 (permissive) · b1e738dc4b22f232 · report
handle_openai_exceptions ControlNet/HYDRA/hydra_vl4ai/agent/llm.py official repository unverified Apache-2.0 (permissive) · 1ed47a31cbd3ca78 · report
stem_sentence ControlNet/HYDRA/hydra_vl4ai/evaluation/vqa_eval.py official repository unverified Apache-2.0 (permissive) · c13b879e21572028 · report

Tasks

Reinforcement Learning (RL)Visual GroundingVisual Question Answering (VQA)Visual Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Grounding RefCOCO testA HYDRA IoU 61.7 #1 of 1 Archive leaderboard report
Visual Grounding RefCOCO+ testA HYDRA IoU 61.1 #7 of 7 Archive leaderboard report
Visual Question Answering (VQA) A-OKVQA HYDRA MC Accuracy 56.35 #6 of 15 Archive leaderboard report
Visual Question Answering (VQA) GQA test-dev HYDRA Accuracy 47.9 #9 of 17 Archive leaderboard report
Visual Question Answering (VQA) OK-VQA HYDRA Accuracy 48.6 #20 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: HYDRA (VL4AI)

HYDRA (VL4AI)

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections