Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction.
For group-relative objectives, however, this signal vanishes when all rollouts receive the same reward, even though their trajectories may reveal useful information about what the task requires and how the agent fails.
When using an LLM agent in a consequential domain, making an informed decision about whether to trust its output or intervene requires calibrated confidence in the agent's success.
To address these challenges, we introduce Confidence Reasoning Graphs (CRGs), an inference-time framework that estimates the probability an agent accomplished its task from a single trajectory, without privileged model access or training…
Yupeng Su, Jiayi Tian, Zheng Zhang, Souvik Kundu · Oct 6, 2026 · Citations: 0
Automatic MetricsGeneral
Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with steps until the sessions exceed the context window.
It removes two kinds of inter-turn redundancy without an auxiliary predictor: content an earlier turn already displayed, replaced by a stub, and turns the agent itself reports finished, folded into a one-line note.
Haibo Jin, Xinjie Li, Peng Kuang, Haohan Wang · Oct 6, 2026 · Citations: 0
Automatic MetricsMedicineCoding
However, existing agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across source files, configurations, tests, dependencies, and runtime behavior, leading to increasingly long…
Each Dev-Primitive pairs a repository artifact with a resident LLM, which gives the artifact an agent-native interface grounded in its own implementation and dependencies, enabling natural-language reasoning, inter-component communication,…
Myunghoon Kang, Jungseob Lee, Jaehyung Seo, Heuiseok Lim · Oct 6, 2026 · Citations: 0
MathCoding
Extensive experiments demonstrate that ThinkFuse outperforms baselines on mathematical and knowledge-intensive reasoning benchmarks, with consistent gains across model-family combinations, and remains robust with a smaller primary model.
Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand.
We study where this evidence-to-action chain breaks as agents move from deciding whether to act to executing single actions and dependent workflows.
Qizheng Zhang, Changxiu Ji, Isaac Sun, Yuetai Li, Shubhangi Upasani, Sherry Ruan · Oct 6, 2026 · Citations: 0
Coding
Automated research systems increasingly run LLM agents over long horizons, but more inference does not by itself produce more progress: agents replay growing histories, duplicate one another's work, or stop experimenting while token…
We introduce Stateless Language Agents (SLAs), built on the principle of stateful search with stateless agents: no agent carries its conversation across invocations; instead, the harness owns the research state (candidate solutions and…
Victor De Lima, Grace Hui Yang · Oct 5, 2026 · Citations: 0
Pairwise PreferenceSimulation EnvCoding
In agentic elicitation, these decisions may be delegated to a foundation model, yet how model choice shapes the resulting information-seeking behavior remains understudied.
Using this setting, we characterize the breadth-depth behavior that emerges from model-specific information-seeking preferences over the course of elicitation.
Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of agentic behavior and MoE structures remains underexplored.
To address this, we introduce a hierarchical routing control framework for agentic tasks.
Haozhen Zhang, Haodong Yue, Quanyu Long, Jianzhu Bao, Qingyuan Liu, Tao Feng · Oct 5, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsGeneral
Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions.
To address this challenge, we present MemPilot, a flexible framework that orchestrates on-demand memory curation under different performance--cost--latency preferences.
Yifan Zhang, Yutong Dai, Viraj Prabhu, Zhiyuan Hu, Ran Xu, Zeyuan Chen · Oct 5, 2026 · Citations: 0
Simulation EnvGeneral
Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak supervision: binary task success is too sparse for credit assignment, while…
During training, the agent answers natural-language verification questions about its own rollouts; a Compositional Conformal Certifier keeps only question signals whose URL-conditional evidence agrees with a training-time judge, assigns…
Olga Tsymboi, Ramil Latypov, Aleksandr Medvedev, Danil Taranets, Dmitrii Stoianov, Nikita Gulyakov · Oct 5, 2026 · Citations: 0
Automatic MetricsGeneral
We present T-Search, an open-weight agentic retriever for hard multi-step search.
Averaged over seven English and Russian benchmarks with gold evidence annotations, it reaches 56.0 Recall@10 with one rollout, 14.4 points above its base, and 61.3 with three fused rollouts, outperforming larger open models.
Jiaming Qian, Huiyan Yang, Mandi Liu, Jie Liu, Wenkai Shen, Pengyang Zhou · Oct 5, 2026 · Citations: 0
Automatic MetricsCoding
We introduce Programmatic Search Agent (PSA), which makes a local executable computation over candidates the unit of a search action.
Relative to the Query-based Agent, PSA improves macro-averaged task success by 4.00 and 7.56 percentage points on the two benchmarks, respectively; within-backbone reductions in final-step tokens average 28.3% and 33.9%.
Mohamed Chenene, Carlos Rosas-Hinostroza, Anastasia Stasenko, Shani Evenstein Sigalov, Pierre-Carl Langlais · Oct 5, 2026 · Citations: 0
Automatic MetricsGeneral
We study agents that instead answer by exploring the graph, and argue that two obstacles limit them: the lack of training data recording how a solver explores, and interfaces that add large graph results directly to the model's context.
Fangxin Wang, Xiang Gao, Yuguang Yao, Kaiwen Dong, Nikash Walia, Kamalika Das · Oct 5, 2026 · Citations: 0
General
World models must predict how an environment evolves under sequences of actions, enabling agents to compare possible futures and reason about counterfactual actions before acting.
