RI

#1Rethinking Code Similarity for Automated Algorithm Design with LLMs

2026-03-03 | City University of Hong Kong |2603.02787

Zhang et al. propose BehaveSim, a metric that measures algorithmic similarity by applying Dynamic Time Warping (DTW) to the sequence of intermediate solutions (trajectories) generated during execution, rather than relying on static code analysis. By integrating this into FunSearch and EoH to enforce behavioral diversity, they achieve significant performance gains, notably reducing the optimality gap on TSP by ~7.8% compared to standard FunSearch.Key Takeaway:

#2Learning to Evolve for Optimization via Stability-Inducing Neural Unrolling

2026-03-03 | The Hong Kong Polytechnic University, The University of Hong Kong |2512.11453

Gao et al. propose L2E, a meta-learned neural optimizer that uses Mamba blocks to parameterize evolutionary operators within a stability-enforcing unrolled loop (Krasnosel'skii-Mann iteration). Results on BBOB and LSGO-1000D are strong, showing it outperforms Transformer-based L2O methods (GLHF) and classical heuristics (DE) in sample efficiency and zero-shot generalization.Key Takeaway:

#1AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework

2026-03-03 | Fudan University, Shanghai Innovation Institute, Shanghai Academy of AI for Science |2603.03233

The authors propose a multi-agent framework for scientific code generation that couples an adversarial 'Challenger' (generating difficult test cases) with a 'Solver', governed by a Bayesian update rule. Crucially, they employ Bayesian Optimization with a kernel based on code embeddings (AST + text) to estimate solution qualitybeforerunning expensive tests, effectively acting as a learned surrogate model. Results on SciCode and ScienceAgentBench are strong, showing small models (Qwen-32B) outperforming GPT-4o when using this loop.

#2VisionCreator: A Native Visual-Generation Agentic Model with Understanding, Thinking, Planning and Creation

2026-03-03 | Tencent Hunyuan, Hong Kong University of Science and Technology |2603.02681

This paper introduces VisionCreator, an agent trained via 'Virtual Reinforcement Learning' (VRL) where tool outputs and logic are simulated to train long-horizon planning policies without incurring expensive real-world execution costs. They employ a 'Plan-Driven Reward' model (combining LLM-based plan verification with rule-based execution checks) and prove theoretical bounds for the sim-to-real transfer, achieving performance superior to GPT-5 on visual tasks.Key Takeaway:

#3StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning

2026-03-03 | University of Minnesota-Twin Cities |2603.02637

StitchCUDA automates end-to-end GPU program generation using a multi-agent framework, but its core contribution is a training recipe that solves reward hacking in code optimization. They decompose expensive multi-turn agentic RL into single-turn 'atomic skills' (generation vs. refinement) and use GRPO with an LLM-evaluated 'Rubric Reward' (e.g., 'Did you use tiling?') rather than just sparse outcome metrics. This prevents the model from gaming the system (e.g., wrapping PyTorch code) and forces actual optimization behavior.

#4Enhancing CVRP Solver through LLM-driven Automatic Heuristic Design

2026-02-26 | City University of Hong Kong, Southern University of Science and Technology |2602.23092

This paper integrates LLM-driven evolutionary search into the AILS framework to evolve 'ruin' heuristics for CVRP, employing a Chain-of-Thought 'voting' mechanism to filter out poor heuristics before expensive evaluation. The results are empirically strong: they claim 8 new Best-Known Solutions on the CVRPLib large-scale benchmark, outperforming HGS and AILS-II.Key Takeaway:This is a direct proof-of-concept that LLM-evolved components can beat hand-crafted SOTA on hard OR instances.

#5AI4S-SDS: A Neuro-Symbolic Solvent Design System via Sparse MCTS and Differentiable Physics Alignment

2026-03-04 | Nanjing University, Suzhou Laboratory, Shanghai Artificial Intelligence Laboratory |2603.03686

Chen et al. introduce a neuro-symbolic MCTS framework for mixed discrete-continuous optimization, applying it to solvent design. They solve the LLM context bottleneck via 'Sparse State Storage' (storing only state abstractions and reconstructing paths on-demand) and fix mode collapse using 'Sibling-Aware Expansion' (conditioning the generator on sibling nodes to force orthogonality).

#6Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants

2026-03-03 | DoorDash, WithMetis.ai |2603.03565

This paper presents a production-grade framework for optimizing multi-agent systems by jointly evolving prompt bundles (MAMUT) rather than optimizing agents in isolation. They validate this on a grocery assistant, showing that system-level optimization outperforms local sub-agent optimization by ~7% because it captures coordination dynamics (e.g., context passing) that local metrics miss. The most stealable insight is their 'Judge Calibration' loop: they use evolutionary search (GEPA) to optimize theevaluator'sprompt to match human labels (91.4% agreement) before using that judge to optimize the agents.

#7AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

2026-02-26 | Alibaba Group, Harbin Institute of Technology, Shenzhen |2602.23258

Wang et al. propose a test-time 'firewall' for multi-agent systems that intercepts messages and validates them against a retrieved set of error patterns (mined from offline failure trajectories). They achieve ~6% accuracy gains on math benchmarks by iteratively rectifying or pruning erroneous outputs before they propagate.Failure-Driven Indicator PoolThis effectively turns the 'graveyard' of failed runs into a persistent memory that improves sample efficiency.

#8MuxTune: Efficient Multi-Task LLM Fine-Tuning in Multi-Tenant Datacenters via Spatial-Temporal Backbone Multiplexing

2026-03-03 | Shanghai Jiao Tong University, National University of Singapore |2603.02885

MuxTune introduces a hierarchical scheduler for multi-tenant PEFT that uses Dynamic Programming to optimally fuse tasks (spatial batching) or interleave them (temporal multiplexing) based on a pipeline cost model. Empirical results on H100s show up to 5x throughput gains over NeMo and S-LoRA, validated by ablation studies. The most stealable insight is theirchunk-based data alignment