Updated August 2026

2026

Paper

ScrambleToolBench studies how autonomous agents adapt to structural environment changes

An interactive terminal benchmark that evaluates whether autonomous agents can infer tool behaviors through trial-and-error and recover from mapping drift without documentation.

Paper

Σ-Mem introduces online reliability memory for multi-agent systems

A real symmetric reliability memory state that tracks peer competence and relationship evidence from post-decision feedback, enabling stable online coordination without retraining.

Paper

IDEAgent introduces agentic quality-diversity search for research idea generation

IDEAgent formalizes scientific discovery as an agentic quality-diversity search problem, generating diverse, high-novelty hypotheses while continually repairing and refining candidate ideas.

Paper

RQ-Bench evaluates limitations of LLMs judging scientific novelty

Reconstructs author-anchored research questions from published papers to benchmark automated novelty assessment, finding significant divergences between LLM judges and human domain experts.

Paper

GRAIL introduces gradient-reweighted advantages for RL reasoning

Uses gradient-activation saliency to assign token-level advantage weights in reinforcement learning with verifiable rewards, improving mathematical reasoning without process reward models.

Paper

Two papers accepted to ICML 2026

Work spanning end-to-end data selection for efficient training and search-guided progressive reasoning over video.

  • Data Agent: end-to-end dynamic data selection for training-aware efficiency
  • Chain-of-Glimpse: search-guided, object-grounded progressive reasoning over video
Media

VentureBeat features δ-mem as working memory for AI agents

Coverage of δ-mem, a 0.12% parameter addition that provides fast online memory modulation for LLM agents during long-horizon interaction.

Paper

PODS schedules data volume over training for data-centric efficiency

A plug-and-play scheduling framework that alternates between low-ratio regularization and high-ratio recovery phases to improve data selection efficiency.

Paper

Stacked from One extends context windows via self-injection

A multi-scale self-injection approach that expands usable model context without retraining from scratch.

Paper

From Perception to Action benchmarks interactive visual reasoning

Evaluates whether multimodal models maintain spatial and visual reasoning consistency when interacting with simulated physical environments.

Paper

Four papers accepted to ICLR 2026

Work spanning text-to-audio generation, operational safety, multi-agent social dynamics, and retrieval evaluation.

  • TangoFlux: fast, faithful text-to-audio generation with flow matching
  • OffTopicEval: whether task-specific agents accept in-domain queries while refusing the rest
  • LLMs Can't Handle Peer Pressure: models crumbling under multi-agent social influence
  • Demystifying Deep Search: a hint-free multi-hop evaluation of search agents
Paper

Epistemic Context Learning builds trust in multi-agent systems

Formulates evidence accumulation principles for determining belief formation and peer reliability in LLM-based multi-agent networks.

Grant

Embodied Foundational Models funded by CNRS@CREATE and NRF

The project supports research on embodied foundation models, generalist interactive AI, and vision-language-action systems.

Grant

Toward Generalist Vision Language Action Models supported by KLASS

This funded project focuses on VLA models, action grounding, and embodied evaluation across robotic platforms.

Award

Highly Cited Researcher recognition

Soujanya Poria was recognized by Web of Science as a Highly Cited Researcher.

Grant

Google DeepMind GCP grant supports large-scale training

S$100K compute grant supporting language, multimodal, and agentic training runs.

2025

Paper

Two papers accepted to AAAI 2026

A position paper on future directions in vision-language-action research and a study of multimodal reasoning on visual puzzles.

  • 10 Open Challenges Steering the Future of Vision-Language-Action Models
  • Tracking the Evolution of Multimodal Reasoning on Visual Puzzles
Paper

NORA-1.5 improves vision-language-action policies via preference rewards

Integrates a flow-matching action expert into the pre-trained NORA backbone and applies world model and action-based preference optimization for embodied robotics tasks.

Paper

10 Open Challenges Steering the Future of Vision-Language-Action Models

A roadmap paper outlining ten core milestones for generalist VLA models across spatial reasoning, world dynamics, post-training, and cross-embodiment action generalization.

Paper

Demystifying Deep Search introduces hint-free multi-hop evaluation

Presents WebDetective, a benchmark evaluating whether web agents discover multi-hop reasoning chains autonomously rather than following surface cues in question prompts.

Paper

OffTopicEval evaluates operational safety and out-of-domain refusal in LLM agents

Introduces an evaluation benchmark measuring whether LLM agents refuse out-of-scope requests, finding significant vulnerability across 20 open-weight models.

Paper

Training Vision-Language PRMs for Test-Time Scaling in Multimodal Reasoning

Analyzes dataset synthesis, perception-level supervision, and test-time scaling strategies for vision-language process reward models.

Paper

LLMs Can't Handle Peer Pressure evaluates multi-agent social influence

Introduces KAIROS to analyze how rapport, peer actions, and model confidence affect consensus and vulnerability in multi-agent LLM systems.

Lab

DeCLaRe Lab moves to Nanyang Technological University

The lab established its base at Nanyang Technological University, Singapore, continuing research across language, multimodal, and embodied AI.

Grant

Meta Audiobox Research Grant supports audio generation research

The grant supports research on audio generation and multimodal generative modeling.

Release

NORA and NORA 1.5 project pages released

Project pages and code releases for compact vision-language-action models and reward-guided post-training for embodied tasks.

Paper

Trust-Score/Trust-Align and MOOSE-Chem accepted at ICLR

Papers studying trustworthy retrieval-augmented generation and chemistry hypothesis discovery.